WorldWideScience

Sample records for extraction feature selection

  1. Medical Image Feature, Extraction, Selection And Classification

    Directory of Open Access Journals (Sweden)

    M.VASANTHA,

    2010-06-01

    Full Text Available Breast cancer is the most common type of cancer found in women. It is the most frequent form of cancer and one in 22 women in India is likely to suffer from breast cancer. This paper proposes a image classifier to classify the mammogram images. Mammogram image is classified into normal image, benign image and malignant image. Totally 26 features including histogram intensity features and GLCM features are extracted from mammogram image. A hybrid approach of feature selection is proposed in this paper which reduces 75% of the features. Decision tree algorithms are applied to mammography lassification by using these reduced features. Experimental results have been obtained for a data set of 113 images taken from MIAS of different types. This technique of classification has not been attempted before and it reveals the potential of Data mining in medical treatment.

  2. Feature Extraction and Selection Strategies for Automated Target Recognition

    Science.gov (United States)

    Greene, W. Nicholas; Zhang, Yuhan; Lu, Thomas T.; Chao, Tien-Hsin

    2010-01-01

    Several feature extraction and selection methods for an existing automatic target recognition (ATR) system using JPLs Grayscale Optical Correlator (GOC) and Optimal Trade-Off Maximum Average Correlation Height (OT-MACH) filter were tested using MATLAB. The ATR system is composed of three stages: a cursory region of-interest (ROI) search using the GOC and OT-MACH filter, a feature extraction and selection stage, and a final classification stage. Feature extraction and selection concerns transforming potential target data into more useful forms as well as selecting important subsets of that data which may aide in detection and classification. The strategies tested were built around two popular extraction methods: Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Performance was measured based on the classification accuracy and free-response receiver operating characteristic (FROC) output of a support vector machine(SVM) and a neural net (NN) classifier.

  3. Feature Extraction and Selection Strategies for Automated Target Recognition

    Science.gov (United States)

    Greene, W. Nicholas; Zhang, Yuhan; Lu, Thomas T.; Chao, Tien-Hsin

    2010-01-01

    Several feature extraction and selection methods for an existing automatic target recognition (ATR) system using JPLs Grayscale Optical Correlator (GOC) and Optimal Trade-Off Maximum Average Correlation Height (OT-MACH) filter were tested using MATLAB. The ATR system is composed of three stages: a cursory region of-interest (ROI) search using the GOC and OT-MACH filter, a feature extraction and selection stage, and a final classification stage. Feature extraction and selection concerns transforming potential target data into more useful forms as well as selecting important subsets of that data which may aide in detection and classification. The strategies tested were built around two popular extraction methods: Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Performance was measured based on the classification accuracy and free-response receiver operating characteristic (FROC) output of a support vector machine(SVM) and a neural net (NN) classifier.

  4. Feature Extraction and Selection From the Perspective of Explosive Detection

    Energy Technology Data Exchange (ETDEWEB)

    Sengupta, S K

    2009-09-01

    ) digitized 3-dimensional attenuation images with a voxel resolution of the order of one quarter of a milimeter. In the task of feature extraction and subsequent selection of an appropriate subset thereof, several important factors need to be considered. Foremost among them are: (1) Definition of the sampling unit from which the features will be extracted for the purpose of detection/ identification of the explosives. (2) The choice of features ( given the sampling unit) to be extracted that can be used to signal the existence / identity of the explosive. (3) Robustness of the computed features under different inspection conditions. To attain robustness, invariance under the transformations of translation, scaling, rotation and change of orientation is highly desirable. (4) The computational costs in the process of feature extraction, selection and their use in explosive detection/ identification In the search for extractable features, we have done a thorough literature survey with the above factors in mind and come out with a list of features that could possibly help us in meeting our objective. We are assuming that features will be based on sampling units that are single CT slices of the target. This may however change when appropriate modifications should be made to the feature extraction process. We indicate below some of the major types of features in 2- or 3-dimensional images that have been used in the literature on application of pattern recognition (PR) techniques in image understanding and are possibly pertinent to our study. In the following paragraph, we briefly indicate the motivation that guided us in the choice of these features, and identify the nature of the constraints. The principal feature types derivable from an image will be discussed in section 2. Once the features are extracted, one must select a subset of this feature set that will retain the most useful information and remove any redundant and irrelevant information that may have a detrimental effect

  5. Magnetic Field Feature Extraction and Selection for Indoor Location Estimation

    Directory of Open Access Journals (Sweden)

    Carlos E. Galván-Tejada

    2014-06-01

    Full Text Available User indoor positioning has been under constant improvement especially with the availability of new sensors integrated into the modern mobile devices, which allows us to exploit not only infrastructures made for everyday use, such as WiFi, but also natural infrastructure, as is the case of natural magnetic field. In this paper we present an extension and improvement of our current indoor localization model based on the feature extraction of 46 magnetic field signal features. The extension adds a feature selection phase to our methodology, which is performed through Genetic Algorithm (GA with the aim of optimizing the fitness of our current model. In addition, we present an evaluation of the final model in two different scenarios: home and office building. The results indicate that performing a feature selection process allows us to reduce the number of signal features of the model from 46 to 5 regardless the scenario and room location distribution. Further, we verified that reducing the number of features increases the probability of our estimator correctly detecting the user’s location (sensitivity and its capacity to detect false positives (specificity in both scenarios.

  6. UNLABELED SELECTED SAMPLES IN FEATURE EXTRACTION FOR CLASSIFICATION OF HYPERSPECTRAL IMAGES WITH LIMITED TRAINING SAMPLES

    Directory of Open Access Journals (Sweden)

    A. Kianisarkaleh

    2015-12-01

    Full Text Available Feature extraction plays a key role in hyperspectral images classification. Using unlabeled samples, often unlimitedly available, unsupervised and semisupervised feature extraction methods show better performance when limited number of training samples exists. This paper illustrates the importance of selecting appropriate unlabeled samples that used in feature extraction methods. Also proposes a new method for unlabeled samples selection using spectral and spatial information. The proposed method has four parts including: PCA, prior classification, posterior classification and sample selection. As hyperspectral image passes these parts, selected unlabeled samples can be used in arbitrary feature extraction methods. The effectiveness of the proposed unlabeled selected samples in unsupervised and semisupervised feature extraction is demonstrated using two real hyperspectral datasets. Results show that through selecting appropriate unlabeled samples, the proposed method can improve the performance of feature extraction methods and increase classification accuracy.

  7. [Feature extraction for breast cancer data based on geometric algebra theory and feature selection using differential evolution].

    Science.gov (United States)

    Li, Jing; Hong, Wenxue

    2014-12-01

    The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.

  8. Feature Extraction

    CERN Document Server

    CERN. Geneva

    2015-01-01

    Feature selection and reduction are key to robust multivariate analyses. In this talk I will focus on pros and cons of various variable selection methods and focus on those that are most relevant in the context of HEP.

  9. Object learning improves feature extraction but does not improve feature selection.

    Directory of Open Access Journals (Sweden)

    Linus Holm

    Full Text Available A single glance at your crowded desk is enough to locate your favorite cup. But finding an unfamiliar object requires more effort. This superiority in recognition performance for learned objects has at least two possible sources. For familiar objects observers might: 1 select more informative image locations upon which to fixate their eyes, or 2 extract more information from a given eye fixation. To test these possibilities, we had observers localize fragmented objects embedded in dense displays of random contour fragments. Eight participants searched for objects in 600 images while their eye movements were recorded in three daily sessions. Performance improved as subjects trained with the objects: The number of fixations required to find an object decreased by 64% across the 3 sessions. An ideal observer model that included measures of fragment confusability was used to calculate the information available from a single fixation. Comparing human performance to the model suggested that across sessions information extraction at each eye fixation increased markedly, by an amount roughly equal to the extra information that would be extracted following a 100% increase in functional field of view. Selection of fixation locations, on the other hand, did not improve with practice.

  10. Toward high-throughput phenotyping: unbiased automated feature extraction and selection from knowledge sources.

    Science.gov (United States)

    Yu, Sheng; Liao, Katherine P; Shaw, Stanley Y; Gainer, Vivian S; Churchill, Susanne E; Szolovits, Peter; Murphy, Shawn N; Kohane, Isaac S; Cai, Tianxi

    2015-09-01

    Analysis of narrative (text) data from electronic health records (EHRs) can improve population-scale phenotyping for clinical and genetic research. Currently, selection of text features for phenotyping algorithms is slow and laborious, requiring extensive and iterative involvement by domain experts. This paper introduces a method to develop phenotyping algorithms in an unbiased manner by automatically extracting and selecting informative features, which can be comparable to expert-curated ones in classification accuracy. Comprehensive medical concepts were collected from publicly available knowledge sources in an automated, unbiased fashion. Natural language processing (NLP) revealed the occurrence patterns of these concepts in EHR narrative notes, which enabled selection of informative features for phenotype classification. When combined with additional codified features, a penalized logistic regression model was trained to classify the target phenotype. The authors applied our method to develop algorithms to identify patients with rheumatoid arthritis and coronary artery disease cases among those with rheumatoid arthritis from a large multi-institutional EHR. The area under the receiver operating characteristic curves (AUC) for classifying RA and CAD using models trained with automated features were 0.951 and 0.929, respectively, compared to the AUCs of 0.938 and 0.929 by models trained with expert-curated features. Models trained with NLP text features selected through an unbiased, automated procedure achieved comparable or slightly higher accuracy than those trained with expert-curated features. The majority of the selected model features were interpretable. The proposed automated feature extraction method, generating highly accurate phenotyping algorithms with improved efficiency, is a significant step toward high-throughput phenotyping. © The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association. All

  11. A Novel Feature Selection Strategy for Enhanced Biomedical Event Extraction Using the Turku System

    Directory of Open Access Journals (Sweden)

    Jingbo Xia

    2014-01-01

    Full Text Available Feature selection is of paramount importance for text-mining classifiers with high-dimensional features. The Turku Event Extraction System (TEES is the best performing tool in the GENIA BioNLP 2009/2011 shared tasks, which relies heavily on high-dimensional features. This paper describes research which, based on an implementation of an accumulated effect evaluation (AEE algorithm applying the greedy search strategy, analyses the contribution of every single feature class in TEES with a view to identify important features and modify the feature set accordingly. With an updated feature set, a new system is acquired with enhanced performance which achieves an increased F-score of 53.27% up from 51.21% for Task 1 under strict evaluation criteria and 57.24% according to the approximate span and recursive criterion.

  12. Simultaneous Spectral-Spatial Feature Selection and Extraction for Hyperspectral Images.

    Science.gov (United States)

    Zhang, Lefei; Zhang, Qian; Du, Bo; Huang, Xin; Tang, Yuan Yan; Tao, Dacheng

    2016-09-12

    In hyperspectral remote sensing data mining, it is important to take into account of both spectral and spatial information, such as the spectral signature, texture feature, and morphological property, to improve the performances, e.g., the image classification accuracy. In a feature representation point of view, a nature approach to handle this situation is to concatenate the spectral and spatial features into a single but high dimensional vector and then apply a certain dimension reduction technique directly on that concatenated vector before feed it into the subsequent classifier. However, multiple features from various domains definitely have different physical meanings and statistical properties, and thus such concatenation has not efficiently explore the complementary properties among different features, which should benefit for boost the feature discriminability. Furthermore, it is also difficult to interpret the transformed results of the concatenated vector. Consequently, finding a physically meaningful consensus low dimensional feature representation of original multiple features is still a challenging task. In order to address these issues, we propose a novel feature learning framework, i.e., the simultaneous spectral-spatial feature selection and extraction algorithm, for hyperspectral images spectral-spatial feature representation and classification. Specifically, the proposed method learns a latent low dimensional subspace by projecting the spectral-spatial feature into a common feature space, where the complementary information has been effectively exploited, and simultaneously, only the most significant original features have been transformed. Encouraging experimental results on three public available hyperspectral remote sensing datasets confirm that our proposed method is effective and efficient.

  13. A Novel Feature Extraction Method with Feature Selection to Identify Golgi-Resident Protein Types from Imbalanced Data.

    Science.gov (United States)

    Yang, Runtao; Zhang, Chengjin; Gao, Rui; Zhang, Lina

    2016-02-06

    The Golgi Apparatus (GA) is a major collection and dispatch station for numerous proteins destined for secretion, plasma membranes and lysosomes. The dysfunction of GA proteins can result in neurodegenerative diseases. Therefore, accurate identification of protein subGolgi localizations may assist in drug development and understanding the mechanisms of the GA involved in various cellular processes. In this paper, a new computational method is proposed for identifying cis-Golgi proteins from trans-Golgi proteins. Based on the concept of Common Spatial Patterns (CSP), a novel feature extraction technique is developed to extract evolutionary information from protein sequences. To deal with the imbalanced benchmark dataset, the Synthetic Minority Over-sampling Technique (SMOTE) is adopted. A feature selection method called Random Forest-Recursive Feature Elimination (RF-RFE) is employed to search the optimal features from the CSP based features and g-gap dipeptide composition. Based on the optimal features, a Random Forest (RF) module is used to distinguish cis-Golgi proteins from trans-Golgi proteins. Through the jackknife cross-validation, the proposed method achieves a promising performance with a sensitivity of 0.889, a specificity of 0.880, an accuracy of 0.885, and a Matthew's Correlation Coefficient (MCC) of 0.765, which remarkably outperforms previous methods. Moreover, when tested on a common independent dataset, our method also achieves a significantly improved performance. These results highlight the promising performance of the proposed method to identify Golgi-resident protein types. Furthermore, the CSP based feature extraction method may provide guidelines for protein function predictions.

  14. A Novel Feature Extraction Method with Feature Selection to Identify Golgi-Resident Protein Types from Imbalanced Data

    Directory of Open Access Journals (Sweden)

    Runtao Yang

    2016-02-01

    Full Text Available The Golgi Apparatus (GA is a major collection and dispatch station for numerous proteins destined for secretion, plasma membranes and lysosomes. The dysfunction of GA proteins can result in neurodegenerative diseases. Therefore, accurate identification of protein subGolgi localizations may assist in drug development and understanding the mechanisms of the GA involved in various cellular processes. In this paper, a new computational method is proposed for identifying cis-Golgi proteins from trans-Golgi proteins. Based on the concept of Common Spatial Patterns (CSP, a novel feature extraction technique is developed to extract evolutionary information from protein sequences. To deal with the imbalanced benchmark dataset, the Synthetic Minority Over-sampling Technique (SMOTE is adopted. A feature selection method called Random Forest-Recursive Feature Elimination (RF-RFE is employed to search the optimal features from the CSP based features and g-gap dipeptide composition. Based on the optimal features, a Random Forest (RF module is used to distinguish cis-Golgi proteins from trans-Golgi proteins. Through the jackknife cross-validation, the proposed method achieves a promising performance with a sensitivity of 0.889, a specificity of 0.880, an accuracy of 0.885, and a Matthew’s Correlation Coefficient (MCC of 0.765, which remarkably outperforms previous methods. Moreover, when tested on a common independent dataset, our method also achieves a significantly improved performance. These results highlight the promising performance of the proposed method to identify Golgi-resident protein types. Furthermore, the CSP based feature extraction method may provide guidelines for protein function predictions.

  15. Driver Fatigue Features Extraction

    Directory of Open Access Journals (Sweden)

    Gengtian Niu

    2014-01-01

    Full Text Available Driver fatigue is the main cause of traffic accidents. How to extract the effective features of fatigue is important for recognition accuracy and traffic safety. To solve the problem, this paper proposes a new method of driver fatigue features extraction based on the facial image sequence. In this method, first, each facial image in the sequence is divided into nonoverlapping blocks of the same size, and Gabor wavelets are employed to extract multiscale and multiorientation features. Then the mean value and standard deviation of each block’s features are calculated, respectively. Considering the facial performance of human fatigue is a dynamic process that developed over time, each block’s features are analyzed in the sequence. Finally, Adaboost algorithm is applied to select the most discriminating fatigue features. The proposed method was tested on a self-built database which includes a wide range of human subjects of different genders, poses, and illuminations in real-life fatigue conditions. Experimental results show the effectiveness of the proposed method.

  16. Feature Extraction and Selection Scheme for Intelligent Engine Fault Diagnosis Based on 2DNMF, Mutual Information, and NSGA-II

    Directory of Open Access Journals (Sweden)

    Peng-yuan Liu

    2016-01-01

    Full Text Available A novel feature extraction and selection scheme is presented for intelligent engine fault diagnosis by utilizing two-dimensional nonnegative matrix factorization (2DNMF, mutual information, and nondominated sorting genetic algorithms II (NSGA-II. Experiments are conducted on an engine test rig, in which eight different engine operating conditions including one normal condition and seven fault conditions are simulated, to evaluate the presented feature extraction and selection scheme. In the phase of feature extraction, the S transform technique is firstly utilized to convert the engine vibration signals to time-frequency domain, which can provide richer information on engine operating conditions. Then a novel feature extraction technique, named two-dimensional nonnegative matrix factorization, is employed for characterizing the time-frequency representations. In the feature selection phase, a hybrid filter and wrapper scheme based on mutual information and NSGA-II is utilized to acquire a compact feature subset for engine fault diagnosis. Experimental results by adopted three different classifiers have demonstrated that the proposed feature extraction and selection scheme can achieve a very satisfying classification performance with fewer features for engine fault diagnosis.

  17. Parallel Feature Extraction System

    Institute of Scientific and Technical Information of China (English)

    MAHuimin; WANGYan

    2003-01-01

    Very high speed image processing is needed in some application specially for weapon. In this paper, a high speed image feature extraction system with parallel structure was implemented by Complex programmable logic device (CPLD), and it can realize image feature extraction in several microseconds almost with no delay. This system design is presented by an application instance of flying plane, whose infrared image includes two kinds of feature: geometric shape feature in the binary image and temperature-feature in the gray image. Accordingly the feature extraction is taken on the two kind features. Edge and area are two most important features of the image. Angle often exists in the connection of the different parts of the target's image, which indicates that one area ends and the other area begins. The three key features can form the whole presentation of an image. So this parallel feature extraction system includes three processing modules: edge extraction, angle extraction and area extraction. The parallel structure is realized by a group of processors, every detector is followed by one route of processor, every route has the same circuit form, and works together at the same time controlled by a set of clock to realize feature extraction. The extraction system has simple structure, small volume, high speed, and better stability against noise. It can be used in the war field recognition system.

  18. Discharges Classification using Genetic Algorithms and Feature Selection Algorithms on Time and Frequency Domain Data Extracted from Leakage Current Measurements

    Directory of Open Access Journals (Sweden)

    D. Pylarinos

    2013-12-01

    Full Text Available A number of 387 discharge portraying waveforms recorded on 18 different 150 kV post insulators installed at two different Substations in Crete, Greece are considered in this paper. Twenty different features are extracted from each waveform and two feature selection algorithms (t-test and mRMR are employed. Genetic algorithms are used to classify waveforms in two different classes related to the portrayed discharges. Five different data sets are employed (1. the original feature vector, 2. time domain features, 3. frequency domain features, 4. t-test selected features 5. mRMR selected features. Results are discussed and compared with previous classification implementations on this particular data group.

  19. Feature extraction and selection for objective gait analysis and fall risk assessment by accelerometry

    Directory of Open Access Journals (Sweden)

    Cremer Gerald

    2011-01-01

    Full Text Available Abstract Background Falls in the elderly is nowadays a major concern because of their consequences on elderly general health and moral states. Moreover, the aging of the population and the increasing life expectancy make the prediction of falls more and more important. The analysis presented in this article makes a first step in this direction providing a way to analyze gait and classify hospitalized elderly fallers and non-faller. This tool, based on an accelerometer network and signal processing, gives objective informations about the gait and does not need any special gait laboratory as optical analysis do. The tool is also simple to use by a non expert and can therefore be widely used on a large set of patients. Method A population of 20 hospitalized elderlies was asked to execute several classical clinical tests evaluating their risk of falling. They were also asked if they experienced any fall in the last 12 months. The accelerations of the limbs were recorded during the clinical tests with an accelerometer network distributed on the body. A total of 67 features were extracted from the accelerometric signal recorded during a simple 25 m walking test at comfort speed. A feature selection algorithm was used to select those able to classify subjects at risk and not at risk for several classification algorithms types. Results The results showed that several classification algorithms were able to discriminate people from the two groups of interest: fallers and non-fallers hospitalized elderlies. The classification performances of the used algorithms were compared. Moreover a subset of the 67 features was considered to be significantly different between the two groups using a t-test. Conclusions This study gives a method to classify a population of hospitalized elderlies in two groups: at risk of falling or not at risk based on accelerometric data. This is a first step to design a risk of falling assessment system that could be used to provide

  20. Fingerprint Feature Extraction Algorithm

    Directory of Open Access Journals (Sweden)

    Mehala. G

    2014-03-01

    Full Text Available The goal of this paper is to design an efficient Fingerprint Feature Extraction (FFE algorithm to extract the fingerprint features for Automatic Fingerprint Identification Systems (AFIS. FFE algorithm, consists of two major subdivisions, Fingerprint image preprocessing, Fingerprint image postprocessing. A few of the challenges presented in an earlier are, consequently addressed, in this paper. The proposed algorithm is able to enhance the fingerprint image and also extracting true minutiae.

  1. Fingerprint Feature Extraction Algorithm

    OpenAIRE

    Mehala. G

    2014-01-01

    The goal of this paper is to design an efficient Fingerprint Feature Extraction (FFE) algorithm to extract the fingerprint features for Automatic Fingerprint Identification Systems (AFIS). FFE algorithm, consists of two major subdivisions, Fingerprint image preprocessing, Fingerprint image postprocessing. A few of the challenges presented in an earlier are, consequently addressed, in this paper. The proposed algorithm is able to enhance the fingerprint image and also extractin...

  2. EVALUATION OF THE IMPACT OF THE ECKLONIA MAXIMA EXTRACT ON SELECTED MORPHOLOGICAL FEATURES OF YELLOW PINE, SPRUCE AND THUJA STABBING

    Directory of Open Access Journals (Sweden)

    Jacek Sosnowski Sosnowski

    2016-07-01

    Full Text Available The study was focused on the impact of an extract of Ecklonia maxima on selected morphological features of yellow pine (Pinus ponderosa Dougl. ex C. Lawson, prickly spruce (Picea pungens Engelm. Variety Glauca, thuja (Thuja occidentalis variety Smaragd. The experiment was established in April 12, 2012 on the forest nursery in Ceranów. April 15, 2013 was introduced research agent in the form of a spraying an aqueous solution extract of Ecklonia maxima with trade name Kelpak SL. Biologically active compounds in the extract are plant hormones: auxin and cytokinin. There were studied increment in plant height, needle length of yellow pine, twigs length in prickly spruce and thuja. The measurements of increment in length of twigs and needles were made in each case on the same, specially marked parts of plants and have carried them on the 27th of each month beginning in May and ending in September. The results were evaluated statistically using the analysis of variance. Medium differentiations were verified by Tukey's test at a significance level p ≤ 0.05. The study showed that the diversity of traits features in the experiment was depended on the extract, the tree species and the measurement time. The best results after the extract using showed a pine and spruce. Seaweed preparation contributed to increment increased of trees height for in the pine and spruce and the needles length of pine and twigs of spruce. The species showing no reaction to the extract was thuja.

  3. Live facial feature extraction

    Institute of Scientific and Technical Information of China (English)

    ZHAO JieYu

    2008-01-01

    Precise facial feature extraction is essential to the high-level face recognition and expression analysis. This paper presents a novel method for the real-time geomet-ric facial feature extraction from live video. In this paper, the input image is viewed as a weighted graph. The segmentation of the pixels corresponding to the edges of facial components of the mouth, eyes, brows, and nose is implemented by means of random walks on the weighted graph. The graph has an 8-connected lattice structure and the weight value associated with each edge reflects the likelihood that a random walker will cross that edge. The random walks simulate an anisot-ropic diffusion process that filters out the noise while preserving the facial expres-sion pixels. The seeds for the segmentation are obtained from a color and motion detector. The segmented facial pixels are represented with linked lists in the origi-nal geometric form and grouped into different parts corresponding to facial com-ponents. For the convenience of implementing high-level vision, the geometric description of facial component pixels is further decomposed into shape and reg-istration information. Shape is defined as the geometric information that is invari-ant under the registration transformation, such as translation, rotation, and iso-tropic scale. Statistical shape analysis is carried out to capture global facial fea-tures where the Procrustes shape distance measure is adopted. A Bayesian ap-proach is used to incorporate high-level prior knowledge of face structure. Ex-perimental results show that the proposed method is capable of real-time extraction of precise geometric facial features from live video. The feature extraction is robust against the illumination changes, scale variation, head rotations, and hand inter-ference.

  4. Unsupervised Feature Subset Selection

    DEFF Research Database (Denmark)

    Søndberg-Madsen, Nicolaj; Thomsen, C.; Pena, Jose

    2003-01-01

    This paper studies filter and hybrid filter-wrapper feature subset selection for unsupervised learning (data clustering). We constrain the search for the best feature subset by scoring the dependence of every feature on the rest of the features, conjecturing that these scores discriminate some...... irrelevant features. We report experimental results on artificial and real data for unsupervised learning of naive Bayes models. Both the filter and hybrid approaches perform satisfactorily....

  5. Vinegar Classification Based on Feature Extraction and Selection From Tin Oxide Gas Sensor Array Data

    Directory of Open Access Journals (Sweden)

    Huang Xingyi

    2003-03-01

    Full Text Available Tin oxide gas sensor array based devices were often cited in publications dealing with food products. However, during the process of using a tin oxide gas sensor array to analysis and identify different gas, the most important and difficult was how to get useful parameters from the sensors and how to optimize the parameters. Which can make the sensor array can identify the gas rapidly and accuracy, and there was not a comfortable method. For this reason we developed a device which satisfied the gas sensor array act with the gas from vinegar. The parameters of the sensor act with gas were picked up after getting the whole acting process data. In order to assure whether the feature parameter was optimum or not, in this paper a new method called “distinguish index”(DI has been proposed. Thus we can assure the feature parameter was useful in the later pattern recognition process. Principal component analysis (PCA and artificial neural network (ANN were used to combine the optimum feature parameters. Good separation among the gases with different vinegar is obtained using principal component analysis. The recognition probability of the ANN is 98 %. The new method can also be applied to other pattern recognition problems.

  6. Rapid Feature Extraction for Optical Character Recognition

    CERN Document Server

    Hossain, M Zahid; Yan, Hong

    2012-01-01

    Feature extraction is one of the fundamental problems of character recognition. The performance of character recognition system is depends on proper feature extraction and correct classifier selection. In this article, a rapid feature extraction method is proposed and named as Celled Projection (CP) that compute the projection of each section formed through partitioning an image. The recognition performance of the proposed method is compared with other widely used feature extraction methods that are intensively studied for many different scripts in literature. The experiments have been conducted using Bangla handwritten numerals along with three different well known classifiers which demonstrate comparable results including 94.12% recognition accuracy using celled projection.

  7. Feature selection in bioinformatics

    Science.gov (United States)

    Wang, Lipo

    2012-06-01

    In bioinformatics, there are often a large number of input features. For example, there are millions of single nucleotide polymorphisms (SNPs) that are genetic variations which determine the dierence between any two unrelated individuals. In microarrays, thousands of genes can be proled in each test. It is important to nd out which input features (e.g., SNPs or genes) are useful in classication of a certain group of people or diagnosis of a given disease. In this paper, we investigate some powerful feature selection techniques and apply them to problems in bioinformatics. We are able to identify a very small number of input features sucient for tasks at hand and we demonstrate this with some real-world data.

  8. Extraction and assessment of chatter feature

    Institute of Scientific and Technical Information of China (English)

    2002-01-01

    Presents feature wavelet packets(FWP)a new method of chatter feature extraction in milling process based on wavelet packets transform(WPF)and using vibration signal.Studies the procedure of automatic feature selection for a given process.Establishes an exponential autoregressive(EAR)model to extract limit cycle behavior of chatter since chatter is a nonlinear oscillation with limit cycle.And gives a way to determine FWTsnumber,and experimental data to assess the effectiveness of the WPT feature extraction by unforced response of EAR model of reconstructed signal.

  9. Online feature selection with streaming features.

    Science.gov (United States)

    Wu, Xindong; Yu, Kui; Ding, Wei; Wang, Hao; Zhu, Xingquan

    2013-05-01

    We propose a new online feature selection framework for applications with streaming features where the knowledge of the full feature space is unknown in advance. We define streaming features as features that flow in one by one over time whereas the number of training examples remains fixed. This is in contrast with traditional online learning methods that only deal with sequentially added observations, with little attention being paid to streaming features. The critical challenges for Online Streaming Feature Selection (OSFS) include 1) the continuous growth of feature volumes over time, 2) a large feature space, possibly of unknown or infinite size, and 3) the unavailability of the entire feature set before learning starts. In the paper, we present a novel Online Streaming Feature Selection method to select strongly relevant and nonredundant features on the fly. An efficient Fast-OSFS algorithm is proposed to improve feature selection performance. The proposed algorithms are evaluated extensively on high-dimensional datasets and also with a real-world case study on impact crater detection. Experimental results demonstrate that the algorithms achieve better compactness and higher prediction accuracy than existing streaming feature selection algorithms.

  10. Feature Extraction Using Mfcc

    Directory of Open Access Journals (Sweden)

    Shikha Gupta

    2013-08-01

    Full Text Available Mel Frequency Ceptral Coefficient is a very common and efficient technique for signal processing. Thispaper presents a new purpose of working with MFCC by using it for Hand gesture recognition. Theobjective of using MFCC for hand gesture recognition is to explore the utility of the MFCC for imageprocessing. Till now it has been used in speech recognition, for speaker identification. The present systemis based on converting the hand gesture into one dimensional (1-D signal and then extracting first 13MFCCs from the converted 1-D signal. Classification is performed by using Support Vector Machine.Experimental results represents that proposed application of using MFCC for gesture recognition havevery good accuracy and hence can be used for recognition of sign language or for other householdapplication with the combination for other techniques such as Gabor filter, DWT to increase the accuracyrate and to make it more efficient.

  11. Feature extraction using fractal codes

    NARCIS (Netherlands)

    Schouten, Ben; Zeeuw, Paul M. de

    1999-01-01

    Fast and successful searching for an object in a multimedia database is a highly desirable functionality. Several approaches to content based retrieval for multimedia databases can be found in the literature [9,10,12,14,17]. The approach we consider is feature extraction. A feature can be seen as a

  12. Feature Extraction Using Fractal Codes

    NARCIS (Netherlands)

    Schouten, B.A.M.; Zeeuw, P.M. de

    1999-01-01

    Fast and successful searching for an object in a multimedia database is a highly desirable functionality. Several approaches to content based retrieval for multimedia databases can be found in the literature [9,10,12,14,17]. The approach we consider is feature extraction. A feature can be seen as a

  13. Genetic Feature Selection for Texture Classification

    Institute of Scientific and Technical Information of China (English)

    PAN Li; ZHENG Hong; ZHANG Zuxun; ZHANG Jianqing

    2004-01-01

    This paper presents a novel approach to feature subset selection using genetic algorithms. This approach has the ability to accommodate multiple criteria such as the accuracy and cost of classification into the process of feature selection and finds the effective feature subset for texture classification. On the basis of the effective feature subset selected, a method is described to extract the objects which are higher than their surroundings, such as trees or forest, in the color aerial images. The methodology presented in this paper is illustrated by its application to the problem of trees extraction from aerial images.

  14. THE FEATURE SUBSET SELECTION ALGORITHM

    Institute of Scientific and Technical Information of China (English)

    LiuYongguo; LiXueming; 等

    2003-01-01

    The motivation of data mining is how to extract effective information from huge data in very large database.However,some redundant irrelevant attributes,which result in low performance and high computing complexity,are included in the very large database in general.So,Feature Selection(FSS)becomes one important issue in the field of data mining.In this letter,an Fss model based on the filter approach is built,which uses the simulated annealing gentic algorithm.Experimental results show that convergence and stability of this algorithm are adequately achieved.

  15. THE FEATURE SUBSET SELECTION ALGORITHM

    Institute of Scientific and Technical Information of China (English)

    Liu Yongguo; Li Xueming; Wu Zhongfu

    2003-01-01

    The motivation of data mining is how to extract effective information from huge data in very large database. However, some redundant and irrelevant attributes, which result in low performance and high computing complexity, are included in the very large database in general.So, Feature Subset Selection (FSS) becomes one important issue in the field of data mining. In this letter, an FSS model based on the filter approach is built, which uses the simulated annealing genetic algorithm. Experimental results show that convergence and stability of this algorithm are adequately achieved.

  16. A comparison of the usefulness of canonical analysis, principal components analysis, and band selection for extraction of features from TMS data for landcover analysis

    Science.gov (United States)

    Boyd, R. K.; Brumfield, J. O.; Campbell, W. J.

    1984-01-01

    Three feature extraction methods, canonical analysis (CA), principal component analysis (PCA), and band selection, have been applied to Thematic Mapper Simulator (TMS) data in order to evaluate the relative performance of the methods. The results obtained show that CA is capable of providing a transformation of TMS data which leads to better classification results than provided by all seven bands, by PCA, or by band selection. A second conclusion drawn from the study is that TMS bands 2, 3, 4, and 7 (thermal) are most important for landcover classification.

  17. Feature extraction for speaker diarization

    OpenAIRE

    Negre Rabassa, Enric

    2016-01-01

    Se explorarán y compararán diferentes características de bajo y alto nivel para la diarización automática de locutores Feature extraction for speaker diarization using different databases Extracción de características para la diarización de locutores utilizando diferentes bases de datos Extracció de caracteristiques per a la diarització de locutors utilitzant diferents bases de dades

  18. A Genetic Algorithm-Based Feature Selection

    Directory of Open Access Journals (Sweden)

    Babatunde Oluleye

    2014-07-01

    Full Text Available This article details the exploration and application of Genetic Algorithm (GA for feature selection. Particularly a binary GA was used for dimensionality reduction to enhance the performance of the concerned classifiers. In this work, hundred (100 features were extracted from set of images found in the Flavia dataset (a publicly available dataset. The extracted features are Zernike Moments (ZM, Fourier Descriptors (FD, Lengendre Moments (LM, Hu 7 Moments (Hu7M, Texture Properties (TP and Geometrical Properties (GP. The main contributions of this article are (1 detailed documentation of the GA Toolbox in MATLAB and (2 the development of a GA-based feature selector using a novel fitness function (kNN-based classification error which enabled the GA to obtain a combinatorial set of feature giving rise to optimal accuracy. The results obtained were compared with various feature selectors from WEKA software and obtained better results in many ways than WEKA feature selectors in terms of classification accuracy

  19. Feature Selection: Algorithms and Challenges

    Institute of Scientific and Technical Information of China (English)

    Xindong Wu; Yanglan Gan; Hao Wang; Xuegang Hu

    2006-01-01

    Feature selection is an active area in data mining research and development. It consists of efforts and contributions from a wide variety of communities, including statistics, machine learning, and pattern recognition. The diversity, on one hand, equips us with many methods and tools. On the other hand, the profusion of options causes confusion. This paper reviews various feature selection methods and identifies research challenges that are at the forefront of this exciting area.

  20. Feature extraction for structural dynamics model validation

    Energy Technology Data Exchange (ETDEWEB)

    Hemez, Francois [Los Alamos National Laboratory; Farrar, Charles [Los Alamos National Laboratory; Park, Gyuhae [Los Alamos National Laboratory; Nishio, Mayuko [UNIV OF TOKYO; Worden, Keith [UNIV OF SHEFFIELD; Takeda, Nobuo [UNIV OF TOKYO

    2010-11-08

    This study focuses on defining and comparing response features that can be used for structural dynamics model validation studies. Features extracted from dynamic responses obtained analytically or experimentally, such as basic signal statistics, frequency spectra, and estimated time-series models, can be used to compare characteristics of structural system dynamics. By comparing those response features extracted from experimental data and numerical outputs, validation and uncertainty quantification of numerical model containing uncertain parameters can be realized. In this study, the applicability of some response features to model validation is first discussed using measured data from a simple test-bed structure and the associated numerical simulations of these experiments. issues that must be considered were sensitivity, dimensionality, type of response, and presence or absence of measurement noise in the response. Furthermore, we illustrate a comparison method of multivariate feature vectors for statistical model validation. Results show that the outlier detection technique using the Mahalanobis distance metric can be used as an effective and quantifiable technique for selecting appropriate model parameters. However, in this process, one must not only consider the sensitivity of the features being used, but also correlation of the parameters being compared.

  1. Feature Engineering for Drug Name Recognition in Biomedical Texts: Feature Conjunction and Feature Selection

    Directory of Open Access Journals (Sweden)

    Shengyu Liu

    2015-01-01

    Full Text Available Drug name recognition (DNR is a critical step for drug information extraction. Machine learning-based methods have been widely used for DNR with various types of features such as part-of-speech, word shape, and dictionary feature. Features used in current machine learning-based methods are usually singleton features which may be due to explosive features and a large number of noisy features when singleton features are combined into conjunction features. However, singleton features that can only capture one linguistic characteristic of a word are not sufficient to describe the information for DNR when multiple characteristics should be considered. In this study, we explore feature conjunction and feature selection for DNR, which have never been reported. We intuitively select 8 types of singleton features and combine them into conjunction features in two ways. Then, Chi-square, mutual information, and information gain are used to mine effective features. Experimental results show that feature conjunction and feature selection can improve the performance of the DNR system with a moderate number of features and our DNR system significantly outperforms the best system in the DDIExtraction 2013 challenge.

  2. Feature engineering for drug name recognition in biomedical texts: feature conjunction and feature selection.

    Science.gov (United States)

    Liu, Shengyu; Tang, Buzhou; Chen, Qingcai; Wang, Xiaolong; Fan, Xiaoming

    2015-01-01

    Drug name recognition (DNR) is a critical step for drug information extraction. Machine learning-based methods have been widely used for DNR with various types of features such as part-of-speech, word shape, and dictionary feature. Features used in current machine learning-based methods are usually singleton features which may be due to explosive features and a large number of noisy features when singleton features are combined into conjunction features. However, singleton features that can only capture one linguistic characteristic of a word are not sufficient to describe the information for DNR when multiple characteristics should be considered. In this study, we explore feature conjunction and feature selection for DNR, which have never been reported. We intuitively select 8 types of singleton features and combine them into conjunction features in two ways. Then, Chi-square, mutual information, and information gain are used to mine effective features. Experimental results show that feature conjunction and feature selection can improve the performance of the DNR system with a moderate number of features and our DNR system significantly outperforms the best system in the DDIExtraction 2013 challenge.

  3. COLOR FEATURE EXTRACTION FOR CBIR

    Directory of Open Access Journals (Sweden)

    Dr. H.B.KEKRE

    2011-12-01

    Full Text Available Content Based Image Retrieval is the application of computer vision techniques to the image retrieval problem of searching for digital images in large databases. The method of CBIR discussed in this paper can filter images based their content and would provide a better indexing and return more accurate results. In this paper we wouldbe discussing: Feature vector generation using color averaging technique, Similarity measures and Performance evaluation using randomly selected 5 query images per class out of which result of one class is discussed. Precision –Recall cross over plot is used as the performance evaluation measure to check the algorithm. As thesystem developed is generic, database consists of images from different classes. The effect due to the size of database and number of different classes is seen on the number of relevancy of the retrievals.

  4. Automatic extraction of planetary image features

    Science.gov (United States)

    LeMoigne-Stewart, Jacqueline J. (Inventor); Troglio, Giulia (Inventor); Benediktsson, Jon A. (Inventor); Serpico, Sebastiano B. (Inventor); Moser, Gabriele (Inventor)

    2013-01-01

    A method for the extraction of Lunar data and/or planetary features is provided. The feature extraction method can include one or more image processing techniques, including, but not limited to, a watershed segmentation and/or the generalized Hough Transform. According to some embodiments, the feature extraction method can include extracting features, such as, small rocks. According to some embodiments, small rocks can be extracted by applying a watershed segmentation algorithm to the Canny gradient. According to some embodiments, applying a watershed segmentation algorithm to the Canny gradient can allow regions that appear as close contours in the gradient to be segmented.

  5. Feature Selection and Effective Classifiers.

    Science.gov (United States)

    Deogun, Jitender S.; Choubey, Suresh K.; Raghavan, Vijay V.; Sever, Hayri

    1998-01-01

    Develops and analyzes four algorithms for feature selection in the context of rough set methodology. Experimental results confirm the expected relationship between the time complexity of these algorithms and the classification accuracy of the resulting upper classifiers. When compared, results of upper classifiers perform better than lower…

  6. Feature selection for portfolio optimization

    DEFF Research Database (Denmark)

    Bjerring, Thomas Trier; Ross, Omri; Weissensteiner, Alex

    2016-01-01

    Most portfolio selection rules based on the sample mean and covariance matrix perform poorly out-of-sample. Moreover, there is a growing body of evidence that such optimization rules are not able to beat simple rules of thumb, such as 1/N. Parameter uncertainty has been identified as one major...... reason for these findings. A strand of literature addresses this problem by improving the parameter estimation and/or by relying on more robust portfolio selection methods. Independent of the chosen portfolio selection rule, we propose using feature selection first in order to reduce the asset menu....... While most of the diversification benefits are preserved, the parameter estimation problem is alleviated. We conduct out-of-sample back-tests to show that in most cases different well-established portfolio selection rules applied on the reduced asset universe are able to improve alpha relative...

  7. Feature selection for portfolio optimization

    DEFF Research Database (Denmark)

    Bjerring, Thomas Trier; Ross, Omri; Weissensteiner, Alex

    2016-01-01

    Most portfolio selection rules based on the sample mean and covariance matrix perform poorly out-of-sample. Moreover, there is a growing body of evidence that such optimization rules are not able to beat simple rules of thumb, such as 1/N. Parameter uncertainty has been identified as one major...... reason for these findings. A strand of literature addresses this problem by improving the parameter estimation and/or by relying on more robust portfolio selection methods. Independent of the chosen portfolio selection rule, we propose using feature selection first in order to reduce the asset menu....... While most of the diversification benefits are preserved, the parameter estimation problem is alleviated. We conduct out-of-sample back-tests to show that in most cases different well-established portfolio selection rules applied on the reduced asset universe are able to improve alpha relative...

  8. ANTHOCYANINS ALIPHATIC ALCOHOLS EXTRACTION FEATURES

    Directory of Open Access Journals (Sweden)

    P. N. Savvin

    2015-01-01

    Full Text Available Anthocyanins red pigments that give color a wide range of fruits, berries and flowers. In the food industry it is widely known as a dye a food additive E163. To extract from natural vegetable raw materials traditionally used ethanol or acidified water, but in same technologies it’s unacceptable. In order to expand the use of anthocyanins as colorants and antioxidants were explored extracting pigments alcohols with different structures of the carbon skeleton, and the position and number of hydroxyl groups. For the isolation anthocyanins raw materials were extracted sequentially twice with t = 60 C for 1.5 hours. The evaluation was performed using extracts of classical spectrophotometric methods and modern express chromaticity. Color black currant extracts depends on the length of the carbon skeleton and position of the hydroxyl group, with the alcohols of normal structure have higher alcohols compared to the isomeric structure of the optical density and index of the red color component. This is due to the different ability to form hydrogen bonds when allocating anthocyanins and other intermolecular interactions. During storage blackcurrant extracts are significant structural changes recoverable pigments, which leads to a significant change in color. In this variation, the stronger the higher the length of the carbon skeleton and branched molecules extractant. Extraction polyols (ethyleneglycol, glycerol are less effective than the corresponding monohydric alcohols. However these extracts saved significantly higher because of their reducing ability at interacting with polyphenolic compounds.

  9. 融合PLS监督特征提取和虚假最近邻点的数据分类特征选择%Feature selection for data classification based on pls supervised feature extraction and false nearest neighbors

    Institute of Scientific and Technical Information of China (English)

    颜克胜; 李太福; 魏正元; 苏盈盈; 姚立忠

    2012-01-01

    The classifier is often led to the problem of low recognition accuracy and time and space overhead, due to the multicollinearity and redundant features and noise in the classification of high dimensional data. A feature selection method based on partial least squares(PLS) and false nearest neighbors(FNN) is proposed. Firstly, the partial least squares method is employed to extract the principal components of high-dimensional data and overcome difficulties encountered with the existing multicollinearity between the original features, and the independent principal components space which carries supervision information could be obtained. Then, the similarity measure based on FNN would be established by calculating the correlation in this space before and after each feature selection, furthermore, gets the original features ranking of interpretation to the dependent variable. Finally, the features which have weak explanatory ability could be removed in turn to construct various classification models, and uses recognition rate of Support Vector Machine(SVM) as a evaluation criterion of models to search out the classification model which not only has the highest recognition rate, but also contains the least number of features, the best feature subset is the just model. A series of experiments from different data models have been conducted. The simulation results show that this method has a good capability to select the best feature subset which is consistent with the nature of classification feature for the data set. Therefore, the research provides a new approach to the feature selection of data classification.%在高维数据分类中,针对多重共线性、冗余特征及噪声易导致分类器识别精度低和时空开销大的问题,提出融合偏最小二乘(Partial Least Squares,PLS)有监督特征提取和虚假最近邻点(False Nearest Neighbors,FNN)的特征选择方法:首先利用偏最小二乘对高维数据提取主元,消除特征之间的多重共

  10. Feature Selection in Scientific Applications

    Energy Technology Data Exchange (ETDEWEB)

    Cantu-Paz, E; Newsam, S; Kamath, C

    2004-02-27

    Numerous applications of data mining to scientific data involve the induction of a classification model. In many cases, the collection of data is not performed with this task in mind, and therefore, the data might contain irrelevant or redundant features that affect negatively the accuracy of the induction algorithms. The size and dimensionality of typical scientific data make it difficult to use any available domain information to identify features that discriminate between the classes of interest. Similarly, exploratory data analysis techniques have limitations on the amount and dimensionality of the data that can be effectively processed. In this paper, we describe applications of efficient feature selection methods to data sets from astronomy, plasma physics, and remote sensing. We use variations of recently proposed filter methods as well as traditional wrapper approaches where practical. We discuss the importance of these applications, the general challenges of feature selection in scientific datasets, the strategies for success that were common among our diverse applications, and the lessons learned in solving these problems.

  11. Efficient sparse kernel feature extraction based on partial least squares.

    Science.gov (United States)

    Dhanjal, Charanpal; Gunn, Steve R; Shawe-Taylor, John

    2009-08-01

    The presence of irrelevant features in training data is a significant obstacle for many machine learning tasks. One approach to this problem is to extract appropriate features and, often, one selects a feature extraction method based on the inference algorithm. Here, we formalize a general framework for feature extraction, based on Partial Least Squares, in which one can select a user-defined criterion to compute projection directions. The framework draws together a number of existing results and provides additional insights into several popular feature extraction methods. Two new sparse kernel feature extraction methods are derived under the framework, called Sparse Maximal Alignment (SMA) and Sparse Maximal Covariance (SMC), respectively. Key advantages of these approaches include simple implementation and a training time which scales linearly in the number of examples. Furthermore, one can project a new test example using only k kernel evaluations, where k is the output dimensionality. Computational results on several real-world data sets show that SMA and SMC extract features which are as predictive as those found using other popular feature extraction methods. Additionally, on large text retrieval and face detection data sets, they produce features which match the performance of the original ones in conjunction with a Support Vector Machine.

  12. Fingerprint Feature Extraction Based on Macroscopic Curvature

    Institute of Scientific and Technical Information of China (English)

    Zhang Xiong; He Gui-ming; Zhang Yun

    2003-01-01

    In the Automatic Fingerprint Identification System (AFIS), extracting the feature of fingerprint is very important. The local curvature of ridges of fingerprint is irregular, so people have the barrier to effectively extract the fingerprint curve features to describe fingerprint. This article proposes a novel algorithm; it embraces information of few nearby fingerprint ridges to extract a new characteristic which can describe the curvature feature of fingerprint. Experimental results show the algorithm is feasible, and the characteristics extracted by it can clearly show the inner macroscopic curve properties of fingerprint. The result also shows that this kind of characteristic is robust to noise and pollution.

  13. Fingerprint Feature Extraction Based on Macroscopic Curvature

    Institute of Scientific and Technical Information of China (English)

    Zhang; Xiong; He; Gui-Ming; 等

    2003-01-01

    In the Automatic Fingerprint Identification System(AFIS), extracting the feature of fingerprint is very important. The local curvature of ridges of fingerprint is irregular, so people have the barrier to effectively extract the fingerprint curve features to describe fingerprint. This article proposes a novel algorithm; it embraces information of few nearby fingerprint ridges to extract a new characterstic which can describe the curvature feature of fingerprint. Experimental results show the algorithm is feasible, and the characteristics extracted by it can clearly show the inner macroscopic curve properties of fingerprint. The result also shows that this kind of characteristic is robust to noise and pollution.

  14. Tongue Image Feature Extraction in TCM

    Institute of Scientific and Technical Information of China (English)

    LI Dong; DU Lian-xiang; LU Fu-ping; DU Jun-ping

    2004-01-01

    In this paper, digital image processing and computer vision techniques are applied to study tongue images for feature extraction with VC++ and Matlab. Extraction and analysis of the tongue surface features are based on shape, color, edge, and texture. The developed software has various functions and good user interface and is easy to use. Feature data for tongue image pattern recognition is provided, which form a sound basis for the future tongue image recognition.

  15. Topographic Feature Extraction for Bengali and Hindi Character Images

    CERN Document Server

    Bag, Soumen; 10.5121/sipij.2011.2215

    2011-01-01

    Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR) etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with respect to views from different directions (e.g. North, South, East, and West). We consider three types of topographic features: closed region, convexity of strokes, and straight line strokes. These features are represented as a shape-based graph which acts as an invariant feature set for discriminating very similar type characters efficiently. We have tested the proposed method on printed and handwritten Bengali and Hindi...

  16. A flow-injection mass spectrometry fingerprinting scaffold for feature selection and quantitation of Cordyceps and Ganoderma extracts in beverage: a predictive artificial neural network modelling strategy

    Science.gov (United States)

    2012-01-01

    Flow-injection mass spectrometry (FI/MS) represents a powerful analytical tool for the quality assessment of herbal formula in dietary supplements. In this study, we described a scaffold (proof-of-concept) adapted from spectroscopy to quantify Cordyceps sinensis and Ganoderma lucidum in a popular Cordyceps sinensis /Ganoderma lucidum -enriched health beverage by utilizing flow-injection/mass spectrometry/artificial neural network (FI/MS/ANN) model fingerprinting method with feature selection capability. Equal proportion of 0.1% formic acid and methanol (v/v) were used to convert extracts of Cordyceps sinensis and Ganoderma lucidum into their respective ions under positive MS polarity condition. No chromatographic separation was performed. The principal m/z values of Cordyceps sinensis and Ganoderma lucidum were identified as: 104.2, 116.2, 120.2, 175.2, 236.3, 248.3, 266.3, 366.6 and 498.6; 439.7, 469.7, 511.7, 551.6, 623.6, 637.7 and 653.6, respectively. ANN models representing Cordyceps sinensis and Ganoderma lucidum were individually trained and validated using three independent sets of matrix-free and matrix-matched calibration curves at concentration levels of 2, 20, 50, 100, 200 and 400 μg mL-1. Five repeat analyses provided a total of 180 spectra for herbal extracts of Cordyceps sinensis and Ganoderma lucidum. Root-mean-square-deviation (RMSE) were highly satisfactory at <4% for both training and validation models. Correlation coefficient (r2) values of between 0.9994 and 0.9997 were reported. Matrix blanks comprised of complex mixture of Lingzhi fermentation solution and collagen. Recovery assessment was performed over two days using six sets of matrix blank (n = 6) spiked at three concentration levels of approximately 83, 166 and 333 mg kg-1. Extraction using acetonitrile provided good overall recovery range of 92-118%. A quantitation limit of 0.2 mg L-1 was reported for both Cordyceps sinensis and Ganoderma lucidum. Intra-day and inter-day RMSE

  17. CBFS: high performance feature selection algorithm based on feature clearness.

    Directory of Open Access Journals (Sweden)

    Minseok Seo

    Full Text Available BACKGROUND: The goal of feature selection is to select useful features and simultaneously exclude garbage features from a given dataset for classification purposes. This is expected to bring reduction of processing time and improvement of classification accuracy. METHODOLOGY: In this study, we devised a new feature selection algorithm (CBFS based on clearness of features. Feature clearness expresses separability among classes in a feature. Highly clear features contribute towards obtaining high classification accuracy. CScore is a measure to score clearness of each feature and is based on clustered samples to centroid of classes in a feature. We also suggest combining CBFS and other algorithms to improve classification accuracy. CONCLUSIONS/SIGNIFICANCE: From the experiment we confirm that CBFS is more excellent than up-to-date feature selection algorithms including FeaLect. CBFS can be applied to microarray gene selection, text categorization, and image classification.

  18. SELECTED FEATURES OF POLISH FARMERS

    Directory of Open Access Journals (Sweden)

    Grzegorz Spychalski

    2013-12-01

    Full Text Available The paper presents results of the research carried out among farm owners in Wielkopolskie voivodeship referring to selected features of social capital. The author identifies and estimates impact of some socio-professional factors on social capital quality and derives statistical conclusion. As a result there is a list of economic policy measures facilitating rural areas development in this aspect. The level of education, civic activity and tendency for collective activity are main conditions of social capital quality in Polish rural areas.

  19. Adaptive feature selection for hyperspectral data analysis

    Science.gov (United States)

    Korycinski, Donna; Crawford, Melba M.; Barnes, J. Wesley

    2004-02-01

    Hyperspectral data can potentially provide greatly improved capability for discrimination between many land cover types, but new methods are required to process these data and extract the required information. Data sets are extremely large, and the data are not well distributed across these high dimensional spaces. The increased number and resolution of spectral bands, many of which are highly correlated, is problematic for supervised statistical classification techniques when the number of training samples is small relative to the dimension of the input vector. Selection of the most relevant subset of features is one means of mitigating these effects. A new algorithm based on the tabu search metaheuristic optimization technique was developed to perform subset feature selection and implemented within a binary hierarchical tree framework. Results obtained using the new approach were compared to those from a greedy common greedy selection technique and to a Fisher discriminant based feature extraction method, both of which were implemented in the same binary hierarchical tree classification scheme. The tabu search based method generally yielded higher classification accuracies with lower variability than these other methods in experiments using hyperspectral data acquired by the EO-1 Hyperion sensor over the Okavango Delta of Botswana.

  20. Discriminative feature selection for visual tracking

    Science.gov (United States)

    Ma, Junkai; Luo, Haibo; Zhou, Wei; Song, Yingchao; Hui, Bin; Chang, Zheng

    2017-06-01

    Visual tracking is an important role in computer vision tasks. The robustness of tracking algorithm is a challenge. Especially in complex scenarios such as clutter background, illumination variation and appearance changes etc. As an important component in tracking algorithm, the appropriateness of feature is closed related to the tracking precision. In this paper, an online discriminative feature selection is proposed to provide the tracker the most discriminative feature. Firstly, a feature pool which contains different information of the image such as gradient, gray value and edge is built. And when every frame is processed during tracking, all of these features will be extracted. Secondly, these features are ranked depend on their discrimination between target and background and the highest scored feature is chosen to represent the candidate image patch. Then, after obtaining the tracking result, the target model will be update to adapt the appearance variation. The experiment show that our method is robust when compared with other state-of-the-art algorithms.

  1. Automated Feature Extraction from Hyperspectral Imagery Project

    Data.gov (United States)

    National Aeronautics and Space Administration — The proposed activities will result in the development of a novel hyperspectral feature-extraction toolkit that will provide a simple, automated, and accurate...

  2. ECG Feature Extraction Techniques - A Survey Approach

    CERN Document Server

    Karpagachelvi, S; Sivakumar, M

    2010-01-01

    ECG Feature Extraction plays a significant role in diagnosing most of the cardiac diseases. One cardiac cycle in an ECG signal consists of the P-QRS-T waves. This feature extraction scheme determines the amplitudes and intervals in the ECG signal for subsequent analysis. The amplitudes and intervals value of P-QRS-T segment determines the functioning of heart of every human. Recently, numerous research and techniques have been developed for analyzing the ECG signal. The proposed schemes were mostly based on Fuzzy Logic Methods, Artificial Neural Networks (ANN), Genetic Algorithm (GA), Support Vector Machines (SVM), and other Signal Analysis techniques. All these techniques and algorithms have their advantages and limitations. This proposed paper discusses various techniques and transformations proposed earlier in literature for extracting feature from an ECG signal. In addition this paper also provides a comparative study of various methods proposed by researchers in extracting the feature from ECG signal.

  3. Multi-scale salient feature extraction on mesh models

    KAUST Repository

    Yang, Yongliang

    2012-01-01

    We present a new method of extracting multi-scale salient features on meshes. It is based on robust estimation of curvature on multiple scales. The coincidence between salient feature and the scale of interest can be established straightforwardly, where detailed feature appears on small scale and feature with more global shape information shows up on large scale. We demonstrate this multi-scale description of features accords with human perception and can be further used for several applications as feature classification and viewpoint selection. Experiments exhibit that our method as a multi-scale analysis tool is very helpful for studying 3D shapes. © 2012 Springer-Verlag.

  4. RESEARCH ON FEATURE POINTS EXTRACTION METHOD FOR BINARY MULTISCALE AND ROTATION INVARIANT LOCAL FEATURE DESCRIPTOR

    Directory of Open Access Journals (Sweden)

    Hongwei Ying

    2014-08-01

    Full Text Available An extreme point of scale space extraction method for binary multiscale and rotation invariant local feature descriptor is studied in this paper in order to obtain a robust and fast method for local image feature descriptor. Classic local feature description algorithms often select neighborhood information of feature points which are extremes of image scale space, obtained by constructing the image pyramid using certain signal transform method. But build the image pyramid always consumes a large amount of computing and storage resources, is not conducive to the actual applications development. This paper presents a dual multiscale FAST algorithm, it does not need to build the image pyramid, but can extract feature points of scale extreme quickly. Feature points extracted by proposed method have the characteristic of multiscale and rotation Invariant and are fit to construct the local feature descriptor.

  5. Rough set-based feature selection method

    Institute of Scientific and Technical Information of China (English)

    ZHAN Yanmei; ZENG Xiangyang; SUN Jincai

    2005-01-01

    A new feature selection method is proposed based on the discern matrix in rough set in this paper. The main idea of this method is that the most effective feature, if used for classification, can distinguish the most number of samples belonging to different classes. Experiments are performed using this method to select relevant features for artificial datasets and real-world datasets. Results show that the selection method proposed can correctly select all the relevant features of artificial datasets and drastically reduce the number of features at the same time. In addition, when this method is used for the selection of classification features of real-world underwater targets,the number of classification features after selection drops to 20% of the original feature set, and the classification accuracy increases about 6% using dataset after feature selection.

  6. Linguistic feature analysis for protein interaction extraction

    Directory of Open Access Journals (Sweden)

    Cornelis Chris

    2009-11-01

    Full Text Available Abstract Background The rapid growth of the amount of publicly available reports on biomedical experimental results has recently caused a boost of text mining approaches for protein interaction extraction. Most approaches rely implicitly or explicitly on linguistic, i.e., lexical and syntactic, data extracted from text. However, only few attempts have been made to evaluate the contribution of the different feature types. In this work, we contribute to this evaluation by studying the relative importance of deep syntactic features, i.e., grammatical relations, shallow syntactic features (part-of-speech information and lexical features. For this purpose, we use a recently proposed approach that uses support vector machines with structured kernels. Results Our results reveal that the contribution of the different feature types varies for the different data sets on which the experiments were conducted. The smaller the training corpus compared to the test data, the more important the role of grammatical relations becomes. Moreover, deep syntactic information based classifiers prove to be more robust on heterogeneous texts where no or only limited common vocabulary is shared. Conclusion Our findings suggest that grammatical relations play an important role in the interaction extraction task. Moreover, the net advantage of adding lexical and shallow syntactic features is small related to the number of added features. This implies that efficient classifiers can be built by using only a small fraction of the features that are typically being used in recent approaches.

  7. Novel Moment Features Extraction for Recognizing Handwritten Arabic Letters

    Directory of Open Access Journals (Sweden)

    Gheith Abandah

    2009-01-01

    Full Text Available Problem statement: Offline recognition of handwritten Arabic text awaits accurate recognition solutions. Most of the Arabic letters have secondary components that are important in recognizing these letters. However these components have large writing variations. We targeted enhancing the feature extraction stage in recognizing handwritten Arabic text. Approach: In this study, we proposed a novel feature extraction approach of handwritten Arabic letters. Pre-segmented letters were first partitioned into main body and secondary components. Then moment features were extracted from the whole letter as well as from the main body and the secondary components. Using multi-objective genetic algorithm, efficient feature subsets were selected. Finally, various feature subsets were evaluated according to their classification error using an SVM classifier. Results: The proposed approach improved the classification error in all cases studied. For example, the improvements of 20-feature subsets of normalized central moments and Zernike moments were 15 and 10%, respectively. Conclusion/Recommendations: Extracting and selecting statistical features from handwritten Arabic letters, their main bodies and their secondary components provided feature subsets that give higher recognition accuracies compared to the subsets of the whole letters alone.

  8. Extraction of Facial Features from Color Images

    Directory of Open Access Journals (Sweden)

    J. Pavlovicova

    2008-09-01

    Full Text Available In this paper, a method for localization and extraction of faces and characteristic facial features such as eyes, mouth and face boundaries from color image data is proposed. This approach exploits color properties of human skin to localize image regions – face candidates. The facial features extraction is performed only on preselected face-candidate regions. Likewise, for eyes and mouth localization color information and local contrast around eyes are used. The ellipse of face boundary is determined using gradient image and Hough transform. Algorithm was tested on image database Feret.

  9. Large datasets: Segmentation, feature extraction, and compression

    Energy Technology Data Exchange (ETDEWEB)

    Downing, D.J.; Fedorov, V.; Lawkins, W.F.; Morris, M.D.; Ostrouchov, G.

    1996-07-01

    Large data sets with more than several mission multivariate observations (tens of megabytes or gigabytes of stored information) are difficult or impossible to analyze with traditional software. The amount of output which must be scanned quickly dilutes the ability of the investigator to confidently identify all the meaningful patterns and trends which may be present. The purpose of this project is to develop both a theoretical foundation and a collection of tools for automated feature extraction that can be easily customized to specific applications. Cluster analysis techniques are applied as a final step in the feature extraction process, which helps make data surveying simple and effective.

  10. Feature Extraction in Radar Target Classification

    Directory of Open Access Journals (Sweden)

    Z. Kus

    1999-09-01

    Full Text Available This paper presents experimental results of extracting features in the Radar Target Classification process using the J frequency band pulse radar. The feature extraction is based on frequency analysis methods, the discrete-time Fourier Transform (DFT and Multiple Signal Characterisation (MUSIC, based on the detection of Doppler effect. The analysis has turned to the preference of DFT with implemented Hanning windowing function. We assumed to classify targets-vehicles into two classes, the wheeled vehicle and tracked vehicle. The results show that it is possible to classify them only while moving. The feature of the class results from a movement of moving parts of the vehicle. However, we have not found any feature to classify the wheeled and tracked vehicles while non-moving, although their engines are on.

  11. Extraction of essential features by quantum density

    Science.gov (United States)

    Wilinski, Artur

    2016-09-01

    In this paper we consider the problem of feature extraction, as an essential and important search of dataset. This problem describe the real ownership of the signals and images. Searches features are often difficult to identify because of data complexity and their redundancy. Here is shown a method of finding an essential features groups, according to the defined issues. To find the hidden attributes we use a special algorithm DQAL with the quantum density for thej-th features from original data, that indicates the important set of attributes. Finally, they have been generated small sets of attributes for subsets with different properties of features. They can be used to the construction of a small set of essential features. All figures were made in Matlab6.

  12. Surrogate-assisted feature extraction for high-throughput phenotyping.

    Science.gov (United States)

    Yu, Sheng; Chakrabortty, Abhishek; Liao, Katherine P; Cai, Tianrun; Ananthakrishnan, Ashwin N; Gainer, Vivian S; Churchill, Susanne E; Szolovits, Peter; Murphy, Shawn N; Kohane, Isaac S; Cai, Tianxi

    2017-04-01

    Phenotyping algorithms are capable of accurately identifying patients with specific phenotypes from within electronic medical records systems. However, developing phenotyping algorithms in a scalable way remains a challenge due to the extensive human resources required. This paper introduces a high-throughput unsupervised feature selection method, which improves the robustness and scalability of electronic medical record phenotyping without compromising its accuracy. The proposed Surrogate-Assisted Feature Extraction (SAFE) method selects candidate features from a pool of comprehensive medical concepts found in publicly available knowledge sources. The target phenotype's International Classification of Diseases, Ninth Revision and natural language processing counts, acting as noisy surrogates to the gold-standard labels, are used to create silver-standard labels. Candidate features highly predictive of the silver-standard labels are selected as the final features. Algorithms were trained to identify patients with coronary artery disease, rheumatoid arthritis, Crohn's disease, and ulcerative colitis using various numbers of labels to compare the performance of features selected by SAFE, a previously published automated feature extraction for phenotyping procedure, and domain experts. The out-of-sample area under the receiver operating characteristic curve and F -score from SAFE algorithms were remarkably higher than those from the other two, especially at small label sizes. SAFE advances high-throughput phenotyping methods by automatically selecting a succinct set of informative features for algorithm training, which in turn reduces overfitting and the needed number of gold-standard labels. SAFE also potentially identifies important features missed by automated feature extraction for phenotyping or experts.

  13. Extracting Product Features from Chinese Product Reviews

    Directory of Open Access Journals (Sweden)

    Yahui Xi

    2013-12-01

    Full Text Available With the great development of e-commerce, the number of product reviews grows rapidly on the e-commerce websites. Review mining has recently received a lot of attention, which aims to discover the valuable information from the massive product reviews. Product feature extraction is one of the basic tasks of product review mining. Its effectiveness can influence significantly the performance of subsequent jobs. Double Propagation is a state-of-the-art technique in product feature extraction. In this paper, we apply the Double Propagation to the product feature exaction from Chinese product reviews and adopt some techniques to improve the precision and recall. First, indirect relations and verb product features are introduced to increase the recall. Second, when ranking candidate product features by using HITS, we expand the number of hubs by means of the dependency relation patterns between product features and opinion words to improve the precision. Finally, the Normalized Pattern Relevance is employed to filter the exacted product features. Experiments on diverse real-life datasets show promising results

  14. Statistical feature extraction based iris recognition system

    Indian Academy of Sciences (India)

    ATUL BANSAL; RAVINDER AGARWAL; R K SHARMA

    2016-05-01

    Iris recognition systems have been proposed by numerous researchers using different feature extraction techniques for accurate and reliable biometric authentication. In this paper, a statistical feature extraction technique based on correlation between adjacent pixels has been proposed and implemented. Hamming distance based metric has been used for matching. Performance of the proposed iris recognition system (IRS) has been measured by recording false acceptance rate (FAR) and false rejection rate (FRR) at differentthresholds in the distance metric. System performance has been evaluated by computing statistical features along two directions, namely, radial direction of circular iris region and angular direction extending from pupil tosclera. Experiments have also been conducted to study the effect of number of statistical parameters on FAR and FRR. Results obtained from the experiments based on different set of statistical features of iris images show thatthere is a significant improvement in equal error rate (EER) when number of statistical parameters for feature extraction is increased from three to six. Further, it has also been found that increasing radial/angular resolution,with normalization in place, improves EER for proposed iris recognition system

  15. Simultaneous Channel and Feature Selection of Fused EEG Features Based on Sparse Group Lasso

    Directory of Open Access Journals (Sweden)

    Jin-Jia Wang

    2015-01-01

    Full Text Available Feature extraction and classification of EEG signals are core parts of brain computer interfaces (BCIs. Due to the high dimension of the EEG feature vector, an effective feature selection algorithm has become an integral part of research studies. In this paper, we present a new method based on a wrapped Sparse Group Lasso for channel and feature selection of fused EEG signals. The high-dimensional fused features are firstly obtained, which include the power spectrum, time-domain statistics, AR model, and the wavelet coefficient features extracted from the preprocessed EEG signals. The wrapped channel and feature selection method is then applied, which uses the logistical regression model with Sparse Group Lasso penalized function. The model is fitted on the training data, and parameter estimation is obtained by modified blockwise coordinate descent and coordinate gradient descent method. The best parameters and feature subset are selected by using a 10-fold cross-validation. Finally, the test data is classified using the trained model. Compared with existing channel and feature selection methods, results show that the proposed method is more suitable, more stable, and faster for high-dimensional feature fusion. It can simultaneously achieve channel and feature selection with a lower error rate. The test accuracy on the data used from international BCI Competition IV reached 84.72%.

  16. Simultaneous channel and feature selection of fused EEG features based on Sparse Group Lasso.

    Science.gov (United States)

    Wang, Jin-Jia; Xue, Fang; Li, Hui

    2015-01-01

    Feature extraction and classification of EEG signals are core parts of brain computer interfaces (BCIs). Due to the high dimension of the EEG feature vector, an effective feature selection algorithm has become an integral part of research studies. In this paper, we present a new method based on a wrapped Sparse Group Lasso for channel and feature selection of fused EEG signals. The high-dimensional fused features are firstly obtained, which include the power spectrum, time-domain statistics, AR model, and the wavelet coefficient features extracted from the preprocessed EEG signals. The wrapped channel and feature selection method is then applied, which uses the logistical regression model with Sparse Group Lasso penalized function. The model is fitted on the training data, and parameter estimation is obtained by modified blockwise coordinate descent and coordinate gradient descent method. The best parameters and feature subset are selected by using a 10-fold cross-validation. Finally, the test data is classified using the trained model. Compared with existing channel and feature selection methods, results show that the proposed method is more suitable, more stable, and faster for high-dimensional feature fusion. It can simultaneously achieve channel and feature selection with a lower error rate. The test accuracy on the data used from international BCI Competition IV reached 84.72%.

  17. A Study on Feature Selection Techniques in Educational Data Mining

    CERN Document Server

    Ramaswami, M

    2009-01-01

    Educational data mining (EDM) is a new growing research area and the essence of data mining concepts are used in the educational field for the purpose of extracting useful information on the behaviors of students in the learning process. In this EDM, feature selection is to be made for the generation of subset of candidate variables. As the feature selection influences the predictive accuracy of any performance model, it is essential to study elaborately the effectiveness of student performance model in connection with feature selection techniques. In this connection, the present study is devoted not only to investigate the most relevant subset features with minimum cardinality for achieving high predictive performance by adopting various filtered feature selection techniques in data mining but also to evaluate the goodness of subsets with different cardinalities and the quality of six filtered feature selection algorithms in terms of F-measure value and Receiver Operating Characteristics (ROC) value, generat...

  18. Vinegar classification based on feature extraction and selection from headspace solid-phase microextraction/gas chromatography volatile analyses: a feasibility study.

    Science.gov (United States)

    Pizarro, C; Esteban-Díez, I; Sáenz-González, C; González-Sáiz, J M

    2008-02-04

    Headspace solid-phase microextraction (HS-SPME) coupled with gas chromatography (GC) and multivariate data analysis were applied to classify different vinegar types (white and red, balsamic, sherry and cider vinegars) on the basis of their volatile composition. The collected chromatographic signals were analysed using the stepwise linear discriminant analysis (SLDA) method, thus simultaneously performing feature selection and classification. Several options, more or less restrictive according to the final number of considered categories, were explored in order to identify the one that afforded highest discrimination ability. The simplicity and effectiveness of the classification methodology proposed in the present study (all the samples were correctly classified and predicted by cross-validation) are promising and encourage the feasibility of using a similar strategy to evaluate the quality and origin of vinegar samples in a reliable, fast, reproducible and cost-efficient way in routine applications. The high quality results obtained were even more remarkable considering the reduced number of discriminant variables finally selected by the stepwise procedure. The use of only 14 peaks enabled differentiation between cider, balsamic, sherry and wine vinegars, whereas only 3 variables were selected to discriminate between red (RW) and white wine (WW) vinegars. The subsequent identification by gas chromatography-mass spectrometry (GC-MS) of the volatile compounds associated with the discriminant peaks selected in the classification process served to interpret their chemical significance.

  19. Fixed kernel regression for voltammogram feature extraction

    Science.gov (United States)

    Acevedo Rodriguez, F. J.; López-Sastre, R. J.; Gil-Jiménez, P.; Ruiz-Reyes, N.; Maldonado Bascón, S.

    2009-12-01

    Cyclic voltammetry is an electroanalytical technique for obtaining information about substances under analysis without the need for complex flow systems. However, classifying the information in voltammograms obtained using this technique is difficult. In this paper, we propose the use of fixed kernel regression as a method for extracting features from these voltammograms, reducing the information to a few coefficients. The proposed approach has been applied to a wine classification problem with accuracy rates of over 98%. Although the method is described here for extracting voltammogram information, it can be used for other types of signals.

  20. Automatic Melody Generation System with Extraction Feature

    Science.gov (United States)

    Ida, Kenichi; Kozuki, Shinichi

    In this paper, we propose the melody generation system with the analysis result of an existing melody. In addition, we introduce the device that takes user's favor in the system. The melody generation is done by pitch's being arranged best on the given rhythm. The best standard is decided by using the feature element extracted from existing music by proposed method. Moreover, user's favor is reflected in the best standard by operating some of the feature element in users. And, GA optimizes the pitch array based on the standard, and achieves the system.

  1. Effects of Feature Extraction and Classification Methods on Cyberbully Detection

    Directory of Open Access Journals (Sweden)

    Esra SARAÇ

    2016-12-01

    Full Text Available Cyberbullying is defined as an aggressive, intentional action against a defenseless person by using the Internet, or other electronic contents. Researchers have found that many of the bullying cases have tragically ended in suicides; hence automatic detection of cyberbullying has become important. In this study we show the effects of feature extraction, feature selection, and classification methods that are used, on the performance of automatic detection of cyberbullying. To perform the experiments FormSpring.me dataset is used and the effects of preprocessing methods; several classifiers like C4.5, Naïve Bayes, kNN, and SVM; and information gain and chi square feature selection methods are investigated. Experimental results indicate that the best classification results are obtained when alphabetic tokenization, no stemming, and no stopwords removal are applied. Using feature selection also improves cyberbully detection performance. When classifiers are compared, C4.5 performs the best for the used dataset.

  2. Feature Selection Criteria for Real Time EKF-SLAM Algorithm

    Directory of Open Access Journals (Sweden)

    Fernando Auat Cheein

    2010-02-01

    Full Text Available This paper presents a seletion procedure for environmet features for the correction stage of a SLAM (Simultaneous Localization and Mapping algorithm based on an Extended Kalman Filter (EKF. This approach decreases the computational time of the correction stage which allows for real and constant-time implementations of the SLAM. The selection procedure consists in chosing the features the SLAM system state covariance is more sensible to. The entire system is implemented on a mobile robot equipped with a range sensor laser. The features extracted from the environment correspond to lines and corners. Experimental results of the real time SLAM algorithm and an analysis of the processing-time consumed by the SLAM with the feature selection procedure proposed are shown. A comparison between the feature selection approach proposed and the classical sequential EKF-SLAM along with an entropy feature selection approach is also performed.

  3. Online Feature Extraction Algorithms for Data Streams

    Science.gov (United States)

    Ozawa, Seiichi

    Along with the development of the network technology and high-performance small devices such as surveillance cameras and smart phones, various kinds of multimodal information (texts, images, sound, etc.) are captured real-time and shared among systems through networks. Such information is given to a system as a stream of data. In a person identification system based on face recognition, for example, image frames of a face are captured by a video camera and given to the system for an identification purpose. Those face images are considered as a stream of data. Therefore, in order to identify a person more accurately under realistic environments, a high-performance feature extraction method for streaming data, which can be autonomously adapted to the change of data distributions, is solicited. In this review paper, we discuss a recent trend on online feature extraction for streaming data. There have been proposed a variety of feature extraction methods for streaming data recently. Due to the space limitation, we here focus on the incremental principal component analysis.

  4. TOPOGRAPHIC FEATURE EXTRACTION FOR BENGALI AND HINDI CHARACTER IMAGES

    Directory of Open Access Journals (Sweden)

    Soumen Bag

    2011-06-01

    Full Text Available Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with respect to views from different directions (e.g. North, South, East, and West. We consider three types of topographic features: closed region, convexity of strokes, and straight line strokes. These features are represented as a shapebased graph which acts as an invariant feature set for discriminating very similar type characters efficiently. We have tested the proposed method on printed and handwritten Bengali and Hindi character images. Initial results demonstrate the efficacy of our approach.

  5. Topographic Feature Extraction for Bengali and Hindi Character Images

    Directory of Open Access Journals (Sweden)

    Soumen Bag

    2011-09-01

    Full Text Available Feature selection and extraction plays an important role in different classification based problems such as face recognition, signature verification, optical character recognition (OCR etc. The performance of OCR highly depends on the proper selection and extraction of feature set. In this paper, we present novel features based on the topography of a character as visible from different viewing directions on a 2D plane. By topography of a character we mean the structural features of the strokes and their spatial relations. In this work we develop topographic features of strokes visible with respect to views from different directions (e.g. North, South, East, and West. We consider three types of topographic features: closed region, convexity of strokes, and straight line strokes. These features are represented as a shapebased graph which acts as an invariant feature set for discriminating very similar type characters efficiently. We have tested the proposed method on printed and handwritten Bengali and Hindi character images. Initial results demonstrate the efficacy of our approach.

  6. FEATURE EXTRACTION FOR EMG BASED PROSTHESES CONTROL

    Directory of Open Access Journals (Sweden)

    R. Aishwarya

    2013-01-01

    Full Text Available The control of prosthetic limb would be more effective if it is based on Surface Electromyogram (SEMG signals from remnant muscles. The analysis of SEMG signals depend on a number of factors, such as amplitude as well as time- and frequency-domain properties. Time series analysis using Auto Regressive (AR model and Mean frequency which is tolerant to white Gaussian noise are used as feature extraction techniques. EMG Histogram is used as another feature vector that was seen to give more distinct classification. The work was done with SEMG dataset obtained from the NINAPRO DATABASE, a resource for bio robotics community. Eight classes of hand movements hand open, hand close, Wrist extension, Wrist flexion, Pointing index, Ulnar deviation, Thumbs up, Thumb opposite to little finger are taken into consideration and feature vectors are extracted. The feature vectors can be given to an artificial neural network for further classification in controlling the prosthetic arm which is not dealt in this paper.

  7. Genetic search feature selection for affective modeling

    DEFF Research Database (Denmark)

    Martínez, Héctor P.; Yannakakis, Georgios N.

    2010-01-01

    Automatic feature selection is a critical step towards the generation of successful computational models of affect. This paper presents a genetic search-based feature selection method which is developed as a global-search algorithm for improving the accuracy of the affective models built...

  8. Genetic search feature selection for affective modeling

    DEFF Research Database (Denmark)

    Martínez, Héctor P.; Yannakakis, Georgios N.

    2010-01-01

    Automatic feature selection is a critical step towards the generation of successful computational models of affect. This paper presents a genetic search-based feature selection method which is developed as a global-search algorithm for improving the accuracy of the affective models built....... The method is tested and compared against sequential forward feature selection and random search in a dataset derived from a game survey experiment which contains bimodal input features (physiological and gameplay) and expressed pairwise preferences of affect. Results suggest that the proposed method...

  9. Embedded Incremental Feature Selection for Reinforcement Learning

    Science.gov (United States)

    2012-05-01

    Classical reinforcement learning techniques become impractical in domains with large complex state spaces. The size of a domain’s state space is...require all the provided features. In this paper we present a feature selection algorithm for reinforcement learning called Incremental Feature

  10. THE IDENTIFICATION OF PILL USING FEATURE EXTRACTION IN IMAGE MINING

    Directory of Open Access Journals (Sweden)

    A. Hema

    2015-02-01

    Full Text Available With the help of image mining techniques, an automatic pill identification system was investigated in this study for matching the images of the pills based on its several features like imprint, color, size and shape. Image mining is an inter-disciplinary task requiring expertise from various fields such as computer vision, image retrieval, image matching and pattern recognition. Image mining is the method in which the unusual patterns are detected so that both hidden and useful data images can only be stored in large database. It involves two different approaches for image matching. This research presents a drug identification, registration, detection and matching, Text, color and shape extraction of the image with image mining concept to identify the legal and illegal pills with more accuracy. Initially, the preprocessing process is carried out using novel interpolation algorithm. The main aim of this interpolation algorithm is to reduce the artifacts, blurring and jagged edges introduced during up-sampling. Then the registration process is proposed with two modules they are, feature extraction and corner detection. In feature extraction the noisy high frequency edges are discarded and relevant high frequency edges are selected. The corner detection approach detects the high frequency pixels in the intersection points. Through the overall performance gets improved. There is a need of segregate the dataset into groups based on the query image’s size, shape, color, text, etc. That process of segregating required information is called as feature extraction. The feature extraction is done using Geometrical Gradient feature transformation. Finally, color and shape feature extraction were performed using color histogram and geometrical gradient vector. Simulation results shows that the proposed techniques provide accurate retrieval results both in terms of time and accuracy when compared to conventional approaches.

  11. Dominant Local Binary Pattern Based Face Feature Selection and Detection

    Directory of Open Access Journals (Sweden)

    Kavitha.T

    2010-04-01

    Full Text Available Face Detection plays a major role in Biometrics.Feature selection is a problem of formidable complexity. Thispaper proposes a novel approach to extract face features forface detection. The LBP features can be extracted faster in asingle scan through the raw image and lie in a lower dimensional space, whilst still retaining facial information efficiently. The LBP features are robust to low-resolution images. The dominant local binary pattern (DLBP is used to extract features accurately. A number of trainable methods are emerging in the empirical practice due to their effectiveness. The proposed method is a trainable system for selecting face features from over-completes dictionaries of imagemeasurements. After the feature selection procedure is completed the SVM classifier is used for face detection. The main advantage of this proposal is that it is trained on a very small training set. The classifier is used to increase the selection accuracy. This is not only advantageous to facilitate the datagathering stage, but, more importantly, to limit the training time. CBCL frontal faces dataset is used for training and validation.

  12. Feature Selection for Image Retrieval based on Genetic Algorithm

    Directory of Open Access Journals (Sweden)

    Preeti Kushwaha

    2016-12-01

    Full Text Available This paper describes the development and implementation of feature selection for content based image retrieval. We are working on CBIR system with new efficient technique. In this system, we use multi feature extraction such as colour, texture and shape. The three techniques are used for feature extraction such as colour moment, gray level co- occurrence matrix and edge histogram descriptor. To reduce curse of dimensionality and find best optimal features from feature set using feature selection based on genetic algorithm. These features are divided into similar image classes using clustering for fast retrieval and improve the execution time. Clustering technique is done by k-means algorithm. The experimental result shows feature selection using GA reduces the time for retrieval and also increases the retrieval precision, thus it gives better and faster results as compared to normal image retrieval system. The result also shows precision and recall of proposed approach compared to previous approach for each image class. The CBIR system is more efficient and better performs using feature selection based on Genetic Algorithm.

  13. Selective Audiovisual Semantic Integration Enabled by Feature-Selective Attention.

    Science.gov (United States)

    Li, Yuanqing; Long, Jinyi; Huang, Biao; Yu, Tianyou; Wu, Wei; Li, Peijun; Fang, Fang; Sun, Pei

    2016-01-13

    An audiovisual object may contain multiple semantic features, such as the gender and emotional features of the speaker. Feature-selective attention and audiovisual semantic integration are two brain functions involved in the recognition of audiovisual objects. Humans often selectively attend to one or several features while ignoring the other features of an audiovisual object. Meanwhile, the human brain integrates semantic information from the visual and auditory modalities. However, how these two brain functions correlate with each other remains to be elucidated. In this functional magnetic resonance imaging (fMRI) study, we explored the neural mechanism by which feature-selective attention modulates audiovisual semantic integration. During the fMRI experiment, the subjects were presented with visual-only, auditory-only, or audiovisual dynamical facial stimuli and performed several feature-selective attention tasks. Our results revealed that a distribution of areas, including heteromodal areas and brain areas encoding attended features, may be involved in audiovisual semantic integration. Through feature-selective attention, the human brain may selectively integrate audiovisual semantic information from attended features by enhancing functional connectivity and thus regulating information flows from heteromodal areas to brain areas encoding the attended features.

  14. Trace Ratio Criterion for Feature Extraction in Classification

    Directory of Open Access Journals (Sweden)

    Guoqi Li

    2014-01-01

    Full Text Available A generalized linear discriminant analysis based on trace ratio criterion algorithm (GLDA-TRA is derived to extract features for classification. With the proposed GLDA-TRA, a set of orthogonal features can be extracted in succession. Each newly extracted feature is the optimal feature that maximizes the trace ratio criterion function in the subspace orthogonal to the space spanned by the previous extracted features.

  15. Feature extraction & image processing for computer vision

    CERN Document Server

    Nixon, Mark

    2012-01-01

    This book is an essential guide to the implementation of image processing and computer vision techniques, with tutorial introductions and sample code in Matlab. Algorithms are presented and fully explained to enable complete understanding of the methods and techniques demonstrated. As one reviewer noted, ""The main strength of the proposed book is the exemplar code of the algorithms."" Fully updated with the latest developments in feature extraction, including expanded tutorials and new techniques, this new edition contains extensive new material on Haar wavelets, Viola-Jones, bilateral filt

  16. Prominent feature selection of microarray data

    Institute of Scientific and Technical Information of China (English)

    Yihui Liu

    2009-01-01

    For wavelet transform, a set of orthogonal wavelet basis aims to detect the localized changing features contained in microarray data. In this research, we investigate the performance of the selected wavelet features based on wavelet detail coefficients at the second level and the third level. The genetic algorithm is performed to optimize wavelet detail coefficients to select the best discriminant features. Exper-iments are carried out on four microarray datasets to evaluate the performance of classification. Experimental results prove that wavelet features optimized from detail coefficients efficiently characterize the differences between normal tissues and cancer tissues.

  17. Stable Feature Selection for Biomarker Discovery

    CERN Document Server

    He, Zengyou

    2010-01-01

    Feature selection techniques have been used as the workhorse in biomarker discovery applications for a long time. Surprisingly, the stability of feature selection with respect to sampling variations has long been under-considered. It is only until recently that this issue has received more and more attention. In this article, we review existing stable feature selection methods for biomarker discovery using a generic hierarchal framework. We have two objectives: (1) providing an overview on this new yet fast growing topic for a convenient reference; (2) categorizing existing methods under an expandable framework for future research and development.

  18. Speech Emotion Feature Selection Method Based on Contribution Analysis Algorithm of Neural Network

    Science.gov (United States)

    Wang, Xiaojia; Mao, Qirong; Zhan, Yongzhao

    2008-11-01

    There are many emotion features. If all these features are employed to recognize emotions, redundant features may be existed. Furthermore, recognition result is unsatisfying and the cost of feature extraction is high. In this paper, a method to select speech emotion features based on contribution analysis algorithm of NN is presented. The emotion features are selected by using contribution analysis algorithm of NN from the 95 extracted features. Cluster analysis is applied to analyze the effectiveness for the features selected, and the time of feature extraction is evaluated. Finally, 24 emotion features selected are used to recognize six speech emotions. The experiments show that this method can improve the recognition rate and the time of feature extraction

  19. Eddy current pulsed phase thermography and feature extraction

    Science.gov (United States)

    He, Yunze; Tian, GuiYun; Pan, Mengchun; Chen, Dixiang

    2013-08-01

    This letter proposed an eddy current pulsed phase thermography technique combing eddy current excitation, infrared imaging, and phase analysis. One steel sample is selected as the material under test to avoid the influence of skin depth, which provides subsurface defects with different depths. The experimental results show that this proposed method can eliminate non-uniform heating and improve defect detectability. Several features are extracted from differential phase spectra and the preliminary linear relationships are built to measure these subsurface defects' depth.

  20. ECG Signal Feature Selection for Emotion Recognition

    Directory of Open Access Journals (Sweden)

    Lichen Xun

    2013-01-01

    Full Text Available This paper aims to study the selection of features based on ECG in emotion recognition. In the process of features selection, we start from existing feature selection algorithm, and pay special attention to some of the intuitive value on ECG waveform as well. Through the use of ANOVA and heuristic search, we picked out the different features to distinguish joy and pleasure these two emotions, then we combine this with pathological analysis of ECG signals by the view of the medical experts to discuss the logic corresponding relation between ECG waveform and emotion distinguish. Through experiment, using the method in this paper we only picked out five features and reached 92% of accuracy rate in the recognition of joy and pleasure.

  1. Features Selection for Skin Micro-Image Symptomatic Recognition

    Institute of Scientific and Technical Information of China (English)

    HU Yue-li; CAO Jia-lin; ZHAO Qian; FENG Xu

    2004-01-01

    Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92 % using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory.

  2. Features Selection for Skin Micro-Image Symptomatic Recognition

    Institute of Scientific and Technical Information of China (English)

    HUYue-li; CAOJia-lin; ZHAOQian; FENGXu

    2004-01-01

    Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92% using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory.

  3. Feature Extraction with Ordered Mean Values for Content Based Image Classification

    Directory of Open Access Journals (Sweden)

    Sudeep Thepade

    2014-01-01

    Full Text Available Categorization of images into meaningful classes by efficient extraction of feature vectors from image datasets has been dependent on feature selection techniques. Traditionally, feature vector extraction has been carried out using different methods of image binarization done with selection of global, local, or mean threshold. This paper has proposed a novel technique for feature extraction based on ordered mean values. The proposed technique was combined with feature extraction using discrete sine transform (DST for better classification results using multitechnique fusion. The novel methodology was compared to the traditional techniques used for feature extraction for content based image classification. Three benchmark datasets, namely, Wang dataset, Oliva and Torralba (OT-Scene dataset, and Caltech dataset, were used for evaluation purpose. Performance measure after evaluation has evidently revealed the superiority of the proposed fusion technique with ordered mean values and discrete sine transform over the popular approaches of single view feature extraction methodologies for classification.

  4. Feature Selection for Audio Surveillance in Urban Environment

    Directory of Open Access Journals (Sweden)

    KIKTOVA Eva

    2014-05-01

    Full Text Available This paper presents the work leading to the acoustic event detection system, which is designed to recognize two types of acoustic events (shot and breaking glass in urban environment. For this purpose, a huge front-end processing was performed for the effective parametric representation of an input sound. MFCC features and features computed during their extraction (MELSPEC and FBANK, then MPEG-7 audio descriptors and other temporal and spectral characteristics were extracted. High dimensional feature sets were created and in the next phase reduced by the mutual information based selection algorithms. Hidden Markov Model based classifier was applied and evaluated by the Viterbi decoding algorithm. Thus very effective feature sets were identified and also the less important features were found.

  5. Classification Using Markov Blanket for Feature Selection

    DEFF Research Database (Denmark)

    Zeng, Yifeng; Luo, Jian

    2009-01-01

    Selecting relevant features is in demand when a large data set is of interest in a classification task. It produces a tractable number of features that are sufficient and possibly improve the classification performance. This paper studies a statistical method of Markov blanket induction algorithm...... induction as a feature selection method. In addition, we point out an important assumption behind the Markov blanket induction algorithm and show its effect on the classification performance....... for filtering features and then applies a classifier using the Markov blanket predictors. The Markov blanket contains a minimal subset of relevant features that yields optimal classification performance. We experimentally demonstrate the improved performance of several classifiers using a Markov blanket...

  6. Extraction of photomultiplier-pulse features

    Energy Technology Data Exchange (ETDEWEB)

    Joerg, Philipp; Baumann, Tobias; Buechele, Maximilian; Fischer, Horst; Gorzellik, Matthias; Grussenmeyer, Tobias; Herrmann, Florian; Kremser, Paul; Kunz, Tobias; Michalski, Christoph; Schopferer, Sebastian; Szameitat, Tobias [Physikalisches Institut der Universitaet Freiburg, Freiburg im Breisgau (Germany)

    2013-07-01

    Experiments in subatomic physics have to handle data rates at several MHz per readout channel to reach statistical significance for the measured quantities. Frequently such experiments have to deal with fast signals which may cover large dynamic ranges. For applications which require amplitude as well as time measurements with highest accuracy transient recorders with very high resolution and deep on-board memory are the first choice. We have built a 16-channel 12- or 14 bit single unit VME64x/VXS sampling ADC module which may sample at rates up to 1GS/s. Fast algorithms have been developed and successfully implemented for the readout of the recoil-proton detector at the COMPASS-II Experiment at CERN. We report on the implementation of the feature extraction algorithms and the performance achieved during a pilot with the COMPASS-II Experiment.

  7. Concrete Slump Classification using GLCM Feature Extraction

    Science.gov (United States)

    Andayani, Relly; Madenda, Syarifudin

    2016-05-01

    Digital image processing technologies have been widely applies in analyzing concrete structure because the accuracy and real time result. The aim of this study is to classify concrete slump by using image processing technique. For this purpose, concrete mix design of 30 MPa compression strength designed with slump of 0-10 mm, 10-30 mm, 30-60 mm, and 60-180 mm were analysed. Image acquired by Nikon Camera D-7000 using high resolution was set up. In the first step RGB converted to greyimage than cropped to 1024 x 1024 pixel. With open-source program, cropped images to be analysed to extract GLCM feature. The result shows for the higher slump contrast getting lower, but higher correlation, energy, and homogeneity.

  8. A New Evolutionary-Incremental Framework for Feature Selection

    Directory of Open Access Journals (Sweden)

    Mohamad-Hoseyn Sigari

    2014-01-01

    Full Text Available Feature selection is an NP-hard problem from the viewpoint of algorithm design and it is one of the main open problems in pattern recognition. In this paper, we propose a new evolutionary-incremental framework for feature selection. The proposed framework can be applied on an ordinary evolutionary algorithm (EA such as genetic algorithm (GA or invasive weed optimization (IWO. This framework proposes some generic modifications on ordinary EAs to be compatible with the variable length of solutions. In this framework, the solutions related to the primary generations have short length. Then, the length of solutions may be increased through generations gradually. In addition, our evolutionary-incremental framework deploys two new operators called addition and deletion operators which change the length of solutions randomly. For evaluation of the proposed framework, we use that for feature selection in the application of face recognition. In this regard, we applied our feature selection method on a robust face recognition algorithm which is based on the extraction of Gabor coefficients. Experimental results show that our proposed evolutionary-incremental framework can select a few number of features from existing thousands features efficiently. Comparison result of the proposed methods with the previous methods shows that our framework is comprehensive, robust, and well-defined to apply on many EAs for feature selection.

  9. Hierarchical Feature Extraction and Selection Method and the Applications in Automatic Target Recognition System%分级特征提取与选择及在自动目标识别系统中的应用

    Institute of Scientific and Technical Information of China (English)

    梅雪; 张继法; 许松松; 巩建鸣

    2012-01-01

    应用于遥感图像、武器制导等的自动目标识别系统中,经常遇到形状相似目标的鉴别问题。为提高其识别的快速性和识别率,提出一种分级的基于形状的目标识别方法。借鉴人类视觉感知方式提取多尺度特征,大尺度下采用全局特征快速粗分类,小尺度下采用局部特征鉴别形状相似目标。然后运用模糊规则对提取的特征进行选择,降低特征维数,加快目标匹配过程。实验结果表明:该方法能快速有效地识别形状相似的目标,特征选择后平均识别率较选择之前提高了6.99/6。%Similar shape object recognition is widely used in automatic target recognition system of remote sensing and weapon guidance. A hierarchical method of shape feature extraction and selection is proposed to increase the recognition efficiency and rate. I.earning from human visual perception, multi-scale features are extracted. C-lobal features are used to make a quick classification,and local features are used to distinguish targets with similar shape. To achieve the feature selection, fuzzy criterion is introduced which improves the matching processing and increases the recognition rate. Experimental results show this method is an effective and general way in recognizing targets with similar shape,and the feature selection improves the recognition rate by 6.9%than before.

  10. Mutual information-based feature selection for radiomics

    Science.gov (United States)

    Oubel, Estanislao; Beaumont, Hubert; Iannessi, Antoine

    2016-03-01

    Background The extraction and analysis of image features (radiomics) is a promising field in the precision medicine era, with applications to prognosis, prediction, and response to treatment quantification. In this work, we present a mutual information - based method for quantifying reproducibility of features, a necessary step for qualification before their inclusion in big data systems. Materials and Methods Ten patients with Non-Small Cell Lung Cancer (NSCLC) lesions were followed over time (7 time points in average) with Computed Tomography (CT). Five observers segmented lesions by using a semi-automatic method and 27 features describing shape and intensity distribution were extracted. Inter-observer reproducibility was assessed by computing the multi-information (MI) of feature changes over time, and the variability of global extrema. Results The highest MI values were obtained for volume-based features (VBF). The lesion mass (M), surface to volume ratio (SVR) and volume (V) presented statistically significant higher values of MI than the rest of features. Within the same VBF group, SVR showed also the lowest variability of extrema. The correlation coefficient (CC) of feature values was unable to make a difference between features. Conclusions MI allowed to discriminate three features (M, SVR, and V) from the rest in a statistically significant manner. This result is consistent with the order obtained when sorting features by increasing values of extrema variability. MI is a promising alternative for selecting features to be considered as surrogate biomarkers in a precision medicine context.

  11. Selecting Optimal Subset of Features for Student Performance Model

    Directory of Open Access Journals (Sweden)

    Hany M. Harb

    2012-09-01

    Full Text Available Educational data mining (EDM is a new growing research area and the essence of data mining concepts are used in the educational field for the purpose of extracting useful information on the student behavior in the learning process. Classification methods like decision trees, rule mining, and Bayesian network, can be applied on the educational data for predicting the student behavior like performance in an examination. This prediction may help in student evaluation. As the feature selection influences the predictive accuracy of any performance model, it is essential to study elaborately the effectiveness of student performance model in connection with feature selection techniques. The main objective of this work is to achieve high predictive performance by adopting various feature selection techniques to increase the predictive accuracy with least number of features. The outcomes show a reduction in computational time and constructional cost in both training and classification phases of the student performance model.

  12. Feature subset selection based on relevance

    Science.gov (United States)

    Wang, Hui; Bell, David; Murtagh, Fionn

    In this paper an axiomatic characterisation of feature subset selection is presented. Two axioms are presented: sufficiency axiom—preservation of learning information, and necessity axiom—minimising encoding length. The sufficiency axiom concerns the existing dataset and is derived based on the following understanding: any selected feature subset should be able to describe the training dataset without losing information, i.e. it is consistent with the training dataset. The necessity axiom concerns the predictability and is derived from Occam's razor, which states that the simplest among different alternatives is preferred for prediction. The two axioms are then restated in terms of relevance in a concise form: maximising both the r( X; Y) and r( Y; X) relevance. Based on the relevance characterisation, four feature subset selection algorithms are presented and analysed: one is exhaustive and the remaining three are heuristic. Experimentation is also presented and the results are encouraging. Comparison is also made with some well-known feature subset selection algorithms, in particular, with the built-in feature selection mechanism in C4.5.

  13. The Importance of Feature Selection in Classification

    Directory of Open Access Journals (Sweden)

    Mrs.K. Moni Sushma Deep

    2014-01-01

    Full Text Available Feature Selection is an important technique for classification for reducing the dimensionality of feature space and it removes redundant, irrelevant, or noisy data. In this paper the feature are selected based on the ranking methods.(1 Information Gain (IG attribute evaluation, (2 Gain Ratio (GR attribute evaluation, (3 Symmetrical Uncertainty (SU attribute evaluation. This paper evaluates the features which are derived from the 3 methods using supervised learning algorithms K-Nearest Neighbor and Naïve Bayes. The measures used for the classifier are True Positive, False Positive, Accuracy and they compared between the algorithm for experimental results. we have taken 2 data sets Pima and Wine from UCI Repository database.

  14. A Hybrid method of face detection based on Feature Extraction using PIFR and Feature Optimization using TLBO

    Directory of Open Access Journals (Sweden)

    Kapil Verma

    2016-01-01

    Full Text Available In this paper we proposed a face detection method based on feature selection and feature optimization. Now in current research trend of biometric security used the process of feature optimization for better improvement of face detection technique. Basically our face consists of three types of feature such as skin color, texture and shape and size of face. The most important feature of face is skin color and texture of face. In this detection technique used texture feature of face image. For the texture extraction of image face used partial feature extraction function, these function is most promising shape feature analysis. For the selection of feature and optimization of feature used multi-objective TLBO. TLBO algorithm is population based searching technique and defines two constraints function for the process of selection and optimization. The proposed algorithm of face detection based on feature selection and feature optimization process. Initially used face image data base and passes through partial feature extractor function and these transform function gives a texture feature of face image. For the evaluation of performance our proposed algorithm implemented in MATLAB 7.8.0 software and face image used provided by Google face image database. For numerical analysis of result used hit and miss ratio. Our empirical evaluation of result shows better prediction result in compression of PIFR method of face detection.

  15. Feature selection for optimized skin tumor recognition using genetic algorithms.

    Science.gov (United States)

    Handels, H; Ross, T; Kreusch, J; Wolff, H H; Pöppl, S J

    1999-07-01

    In this paper, a new approach to computer supported diagnosis of skin tumors in dermatology is presented. High resolution skin surface profiles are analyzed to recognize malignant melanomas and nevocytic nevi (moles), automatically. In the first step, several types of features are extracted by 2D image analysis methods characterizing the structure of skin surface profiles: texture features based on cooccurrence matrices, Fourier features and fractal features. Then, feature selection algorithms are applied to determine suitable feature subsets for the recognition process. Feature selection is described as an optimization problem and several approaches including heuristic strategies, greedy and genetic algorithms are compared. As quality measure for feature subsets, the classification rate of the nearest neighbor classifier computed with the leaving-one-out method is used. Genetic algorithms show the best results. Finally, neural networks with error back-propagation as learning paradigm are trained using the selected feature sets. Different network topologies, learning parameters and pruning algorithms are investigated to optimize the classification performance of the neural classifiers. With the optimized recognition system a classification performance of 97.7% is achieved.

  16. DYNAMIC FEATURE SELECTION FOR WEB USER IDENTIFICATION ON LINGUISTIC AND STYLISTIC FEATURES OF ONLINE TEXTS

    Directory of Open Access Journals (Sweden)

    A. A. Vorobeva

    2017-01-01

    Full Text Available The paper deals with identification and authentication of web users participating in the Internet information processes (based on features of online texts.In digital forensics web user identification based on various linguistic features can be used to discover identity of individuals, criminals or terrorists using the Internet to commit cybercrimes. Internet could be used as a tool in different types of cybercrimes (fraud and identity theft, harassment and anonymous threats, terrorist or extremist statements, distribution of illegal content and information warfare. Linguistic identification of web users is a kind of biometric identification, it can be used to narrow down the suspects, identify a criminal and prosecute him. Feature set includes various linguistic and stylistic features extracted from online texts. We propose dynamic feature selection for each web user identification task. Selection is based on calculating Manhattan distance to k-nearest neighbors (Relief-f algorithm. This approach improves the identification accuracy and minimizes the number of features. Experiments were carried out on several datasets with different level of class imbalance. Experiment results showed that features relevance varies in different set of web users (probable authors of some text; features selection for each set of web users improves identification accuracy by 4% at the average that is approximately 1% higher than with the use of static set of features. The proposed approach is most effective for a small number of training samples (messages per user.

  17. 乳腺癌数据的几何代数特征提取和微分进化特征选择研究%Feature Extraction for Breast Cancer Data Based on Geometric Algebra Theory and Feature Selection Using Differential Evolution

    Institute of Scientific and Technical Information of China (English)

    李静; 洪文学

    2014-01-01

    模式识别问题中特征提取和特征选择是一个重要问题.基于向量的几何代数表示方法,提出了一种新的几何代数片积系数特征提取方法,并对其中存在的维数升高问题进行了研究,提出了改进的微分进化特征选择方法.本文分类器采用线性判别分析,以公开的乳腺癌生物医学数据集进行10折交叉验证(10 CV),得到的分类结果超过了96%,优于原始特征和传统特征提取方法下的分类性能.%The feature extraction and feature selection are the important issues in pattern recognition.Based on the geometric algebra representation of vector,a new feature extraction method using blade coefficient of geometric algebra was proposed in this study.At the same time,an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue.The simple linear discriminant analysis was used as the classifier.The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96 % and proved superior to that of the original features and traditional feature extraction method.

  18. [Electroencephalogram Feature Selection Based on Correlation Coefficient Analysis].

    Science.gov (United States)

    Zhou, Jinzhi; Tang, Xiaofang

    2015-08-01

    In order to improve the accuracy of classification with small amount of motor imagery training data on the development of brain-computer interface (BCD systems, we proposed an analyzing method to automatically select the characteristic parameters based on correlation coefficient analysis. Throughout the five sample data of dataset IV a from 2005 BCI Competition, we utilized short-time Fourier transform (STFT) and correlation coefficient calculation to reduce the number of primitive electroencephalogram dimension, then introduced feature extraction based on common spatial pattern (CSP) and classified by linear discriminant analysis (LDA). Simulation results showed that the average rate of classification accuracy could be improved by using correlation coefficient feature selection method than those without using this algorithm. Comparing with support vector machine (SVM) optimization features algorithm, the correlation coefficient analysis can lead better selection parameters to improve the accuracy of classification.

  19. Feature Selection Strategies for Classifying High Dimensional Astronomical Data Sets

    CERN Document Server

    Donalek, Ciro; Djorgovski, S G; Mahabal, Ashish A; Graham, Matthew J; Fuchs, Thomas J; Turmon, Michael J; Philip, N Sajeeth; Yang, Michael Ting-Chang; Longo, Giuseppe

    2013-01-01

    The amount of collected data in many scientific fields is increasing, all of them requiring a common task: extract knowledge from massive, multi parametric data sets, as rapidly and efficiently possible. This is especially true in astronomy where synoptic sky surveys are enabling new research frontiers in the time domain astronomy and posing several new object classification challenges in multi dimensional spaces; given the high number of parameters available for each object, feature selection is quickly becoming a crucial task in analyzing astronomical data sets. Using data sets extracted from the ongoing Catalina Real-Time Transient Surveys (CRTS) and the Kepler Mission we illustrate a variety of feature selection strategies used to identify the subsets that give the most information and the results achieved applying these techniques to three major astronomical problems.

  20. Using PSO-Based Hierarchical Feature Selection Algorithm

    Directory of Open Access Journals (Sweden)

    Zhiwei Ji

    2014-01-01

    Full Text Available Hepatocellular carcinoma (HCC is one of the most common malignant tumors. Clinical symptoms attributable to HCC are usually absent, thus often miss the best therapeutic opportunities. Traditional Chinese Medicine (TCM plays an active role in diagnosis and treatment of HCC. In this paper, we proposed a particle swarm optimization-based hierarchical feature selection (PSOHFS model to infer potential syndromes for diagnosis of HCC. Firstly, the hierarchical feature representation is developed by a three-layer tree. The clinical symptoms and positive score of patient are leaf nodes and root in the tree, respectively, while each syndrome feature on the middle layer is extracted from a group of symptoms. Secondly, an improved PSO-based algorithm is applied in a new reduced feature space to search an optimal syndrome subset. Based on the result of feature selection, the causal relationships of symptoms and syndromes are inferred via Bayesian networks. In our experiment, 147 symptoms were aggregated into 27 groups and 27 syndrome features were extracted. The proposed approach discovered 24 syndromes which obviously improved the diagnosis accuracy. Finally, the Bayesian approach was applied to represent the causal relationships both at symptom and syndrome levels. The results show that our computational model can facilitate the clinical diagnosis of HCC.

  1. HEURISTICAL FEATURE EXTRACTION FROM LIDAR DATA AND THEIR VISUALIZATION

    OpenAIRE

    Ghosh., S; B. Lohani

    2012-01-01

    Extraction of landscape features from LiDAR data has been studied widely in the past few years. These feature extraction methodologies have been focussed on certain types of features only, namely the bare earth model, buildings principally containing planar roofs, trees and roads. In this paper, we present a methodology to process LiDAR data through DBSCAN, a density based clustering method, which extracts natural and man-made clusters. We then develop heuristics to process these clu...

  2. Applying Feature Extraction for Classification Problems

    Directory of Open Access Journals (Sweden)

    Foon Chi

    2009-03-01

    Full Text Available With the wealth of image data that is now becoming increasingly accessible through the advent of the world wide web and the proliferation of cheap, high quality digital cameras it isbecoming ever more desirable to be able to automatically classify images into appropriate categories such that intelligent agents and other such intelligent software might make better informed decisions regarding them without a need for excessive human intervention.However, as with most Artificial Intelligence (A.I. methods it is seen as necessary to take small steps towards your goal. With this in mind a method is proposed here to represent localised features using disjoint sub-images taken from several datasets of retinal images for their eventual use in an incremental learning system. A tile-based localised adaptive threshold selection method was taken for vessel segmentation based on separate colour components. Arteriole-venous differentiation was made possible by using the composite of these components and high quality fundal images. Performance was evaluated on the DRIVE and STARE datasets achieving average specificity of 0.9379 and sensitivity of 0.5924.

  3. Automatically extracting sheet-metal features from solid model

    Institute of Scientific and Technical Information of China (English)

    刘志坚; 李建军; 王义林; 李材元; 肖祥芷

    2004-01-01

    With the development of modern industry,sheet-metal parts in mass production have been widely applied in mechanical,communication,electronics,and light industries in recent decades; but the advances in sheet-metal part design and manufacturing remain too slow compared with the increasing importance of sheet-metal parts in modern industry. This paper proposes a method for automatically extracting features from an arbitrary solid model of sheet-metal parts; whose characteristics are used for classification and graph-based representation of the sheet-metal features to extract the features embodied in a sheet-metal part. The extracting feature process can be divided for valid checking of the model geometry,feature matching,and feature relationship. Since the extracted features include abundant geometry and engineering information,they will be effective for downstream application such as feature rebuilding and stamping process planning.

  4. Automatically extracting sheet-metal features from solid model

    Institute of Scientific and Technical Information of China (English)

    刘志坚; 李建军; 王义林; 李材元; 肖祥芷

    2004-01-01

    With the development of modern industry, sheet-metal parts in mass production have been widely applied in mechanical, communication, electronics, and light industries in recent decades; but the advances in sheet-metal part design and manufacturing remain too slow compared with the increasing importance of sheet-metal parts in modern industry. This paper proposes a method for automatically extracting features from an arbitrary solid model of sheet-metal parts; whose characteristics are used for classification and graph-based representation of the sheet-metal features to extract the features embodied in a sheet-metal part. The extracting feature process can be divided for valid checking of the model geometry, feature matching, and feature relationship. Since the extracted features include abundant geometry and engineering information, they will be effective for downstream application such as feature rebuilding and stamping process planning.

  5. Coevolution of active vision and feature selection.

    Science.gov (United States)

    Floreano, Dario; Kato, Toshifumi; Marocco, Davide; Sauser, Eric

    2004-03-01

    We show that complex visual tasks, such as position- and size-invariant shape recognition and navigation in the environment, can be tackled with simple architectures generated by a coevolutionary process of active vision and feature selection. Behavioral machines equipped with primitive vision systems and direct pathways between visual and motor neurons are evolved while they freely interact with their environments. We describe the application of this methodology in three sets of experiments, namely, shape discrimination, car driving, and robot navigation. We show that these systems develop sensitivity to a number of oriented, retinotopic, visual-feature-oriented edges, corners, height, and a behavioral repertoire to locate, bring, and keep these features in sensitive regions of the vision system, resembling strategies observed in simple insects.

  6. Feature Extraction by Wavelet Decomposition of Surface

    Directory of Open Access Journals (Sweden)

    Prashant Singh

    2010-07-01

    Full Text Available The paper presents a new approach to surface acoustic wave (SAW chemical sensor array design and data processing for recognition of volatile organic compounds (VOCs based on transient responses. The array is constructed of variable thickness single polymer-coated SAW oscillator sensors. The thickness of polymer coatings are selected such that during the sensing period, different sensors are loaded with varied levels of diffusive inflow of vapour species due to different stages of termination of equilibration process. Using a single polymer for coating the individual sensors with different thickness introduces vapour-specific kinetics variability in transient responses. The transient shapes are analysed by wavelet decomposition based on Daubechies mother wavelets. The set of discrete wavelet transform (DWT approximation coefficients across the array transients is taken to represent the vapour sample in two alternate ways. In one, the sets generated by all the transients are combined into a single set to give a single representation to the vapour. In the other, the set of approximation coefficients at each data point generated by all transients is taken to represent the vapour. The latter results in as many alternate representations as there are approximation coefficients. The alternate representations of a vapour sample are treated as different instances or realisations for further processing. The wavelet analysis is then followed by the principal component analysis (PCA to create new feature space. A comparative analysis of the feature spaces created by both the methods leads to the conclusion that both methods yield complimentary information: the one reveals intrinsic data variables, and the other enhances class separability. The present approach is validated by generating synthetic transient response data based on a prototype polyisobutylene (PIB coated 3-element SAW sensor array exposed to 7 VOC vapours: chloroform, chlorobenzene o

  7. Feature Extraction from Subband Brain Signals and Its Classification

    Science.gov (United States)

    Mukul, Manoj Kumar; Matsuno, Fumitoshi

    This paper considers both the non-stationarity as well as independence/uncorrelated criteria along with the asymmetry ratio over the electroencephalogram (EEG) signals and proposes a hybrid approach of the signal preprocessing methods before the feature extraction. A filter bank approach of the discrete wavelet transform (DWT) is used to exploit the non-stationary characteristics of the EEG signals and it decomposes the raw EEG signals into the subbands of different center frequencies called as rhythm. A post processing of the selected subband by the AMUSE algorithm (a second order statistics based ICA/BSS algorithm) provides the separating matrix for each class of the movement imagery. In the subband domain the orthogonality as well as orthonormality criteria over the whitening matrix and separating matrix do not come respectively. The human brain has an asymmetrical structure. It has been observed that the ratio between the norms of the left and right class separating matrices should be different for better discrimination between these two classes. The alpha/beta band asymmetry ratio between the separating matrices of the left and right classes will provide the condition to select an appropriate multiplier. So we modify the estimated separating matrix by an appropriate multiplier in order to get the required asymmetry and extend the AMUSE algorithm in the subband domain. The desired subband is further subjected to the updated separating matrix to extract subband sub-components from each class. The extracted subband sub-components sources are further subjected to the feature extraction (power spectral density) step followed by the linear discriminant analysis (LDA).

  8. Exploitation of Intra-Spectral Band Correlation for Rapid Feature Selection, and Target Identification in Hyperspectral Imagery

    Science.gov (United States)

    2009-03-01

    entitled “Improved Feature Extraction, Feature Selection, and Identification Techniques that Create a Fast Unsupervised Hyperspectral Target Detection...thesis proposal “Improved Feature Extraction, Feature Selection, and Identification Techniques that Create a Fast Unsupervised Hyperspectral Target...target or non-target classifications . Integration of this type of autonomous target detection algorithm along with hyperspectral imaging sensors

  9. New learning subspace method for image feature extraction

    Institute of Scientific and Technical Information of China (English)

    CAO Jian-hai; LI Long; LU Chang-hou

    2006-01-01

    A new method of Windows Minimum/Maximum Module Learning Subspace Algorithm(WMMLSA) for image feature extraction is presented. The WMMLSM is insensitive to the order of the training samples and can regulate effectively the radical vectors of an image feature subspace through selecting the study samples for subspace iterative learning algorithm,so it can improve the robustness and generalization capacity of a pattern subspace and enhance the recognition rate of a classifier. At the same time,a pattern subspace is built by the PCA method. The classifier based on WMMLSM is successfully applied to recognize the pressed characters on the gray-scale images. The results indicate that the correct recognition rate on WMMLSM is higher than that on Average Learning Subspace Method,and that the training speed and the classification speed are both improved. The new method is more applicable and efficient.

  10. Classification of Textures Using Filter Based Local Feature Extraction

    Directory of Open Access Journals (Sweden)

    Bocekci Veysel Gokhan

    2016-01-01

    Full Text Available In this work local features are used in feature extraction process in image processing for textures. The local binary pattern feature extraction method from textures are introduced. Filtering is also used during the feature extraction process for getting discriminative features. To show the effectiveness of the algorithm before the extraction process, three different noise are added to both train and test images. Wiener filter and median filter are used to remove the noise from images. We evaluate the performance of the method with Naïve Bayesian classifier. We conduct the comparative analysis on benchmark dataset with different filtering and size. Our experiments demonstrate that feature extraction process combine with filtering give promising results on noisy images.

  11. Optimal Features Subset Selection and Classification for Iris Recognition

    Directory of Open Access Journals (Sweden)

    Roy Kaushik

    2008-01-01

    Full Text Available Abstract The selection of the optimal features subset and the classification have become an important issue in the field of iris recognition. We propose a feature selection scheme based on the multiobjectives genetic algorithm (MOGA to improve the recognition accuracy and asymmetrical support vector machine for the classification of iris patterns. We also suggest a segmentation scheme based on the collarette area localization. The deterministic feature sequence is extracted from the iris images using the 1D log-Gabor wavelet technique, and the extracted feature sequence is used to train the support vector machine (SVM. The MOGA is applied to optimize the features sequence and to increase the overall performance based on the matching accuracy of the SVM. The parameters of SVM are optimized to improve the overall generalization performance, and the traditional SVM is modified to an asymmetrical SVM to treat the false accept and false reject cases differently and to handle the unbalanced data of a specific class with respect to the other classes. Our experimental results indicate that the performance of SVM as a classifier is better than the performance of the classifiers based on the feedforward neural network, the k-nearest neighbor, and the Hamming and the Mahalanobis distances. The proposed technique is computationally effective with recognition rates of 99.81% and 96.43% on CASIA and ICE datasets, respectively.

  12. Optimal Features Subset Selection and Classification for Iris Recognition

    Directory of Open Access Journals (Sweden)

    Prabir Bhattacharya

    2008-06-01

    Full Text Available The selection of the optimal features subset and the classification have become an important issue in the field of iris recognition. We propose a feature selection scheme based on the multiobjectives genetic algorithm (MOGA to improve the recognition accuracy and asymmetrical support vector machine for the classification of iris patterns. We also suggest a segmentation scheme based on the collarette area localization. The deterministic feature sequence is extracted from the iris images using the 1D log-Gabor wavelet technique, and the extracted feature sequence is used to train the support vector machine (SVM. The MOGA is applied to optimize the features sequence and to increase the overall performance based on the matching accuracy of the SVM. The parameters of SVM are optimized to improve the overall generalization performance, and the traditional SVM is modified to an asymmetrical SVM to treat the false accept and false reject cases differently and to handle the unbalanced data of a specific class with respect to the other classes. Our experimental results indicate that the performance of SVM as a classifier is better than the performance of the classifiers based on the feedforward neural network, the k-nearest neighbor, and the Hamming and the Mahalanobis distances. The proposed technique is computationally effective with recognition rates of 99.81% and 96.43% on CASIA and ICE datasets, respectively.

  13. Handwritten Character Classification using the Hotspot Feature Extraction Technique

    NARCIS (Netherlands)

    Surinta, Olarik; Schomaker, Lambertus; Wiering, Marco

    2012-01-01

    Feature extraction techniques can be important in character recognition, because they can enhance the efficacy of recognition in comparison to featureless or pixel-based approaches. This study aims to investigate the novel feature extraction technique called the hotspot technique in order to use it

  14. Novel Feature Selection by Differential Evolution Algorithm

    Directory of Open Access Journals (Sweden)

    Ali Ghareaghaji

    2013-11-01

    Full Text Available Iris scan biometrics employs the unique characteristic and features of the human iris in order to verify the identity of in individual. In today's world, where terrorist attacks are on the rise employment of infallible security systems is a must. This makes Iris recognition systems unavoidable in emerging security. Authentication the objective function is minimized using Differential Evolutionary (DE Algorithm where the population vector is encoded using Binary Encoded Decimal to avoid the float number optimization problem. An automatic clustering of the possible values of the Lagrangian multiplier provides a detailed insight of the selected features during the proposed DE based optimization process. The classification accuracy of Support Vector Machine (SVM is used to measure the performance of the selected features. The proposed algorithm outperforms the existing DE based approaches when tested on IRIS, Wine, Wisconsin Breast Cancer, Sonar and Ionosphere datasets. The same algorithm when applied on gait based people identification, using skeleton data points obtained from Microsoft Kinect sensor, exceeds the previously reported accuracies.

  15. A Hybrid Feature Subset Selection using Metrics and Forward Selection

    Directory of Open Access Journals (Sweden)

    K. Fathima Bibi

    2015-04-01

    Full Text Available The aim of this study is to design a Feature Subset Selection Technique that speeds up the Feature Selection (FS process in high dimensional datasets with reduced computational cost and great efficiency. FS has become the focus of much research on decision support system areas for which data with tremendous number of variables are analyzed. Filters and wrappers are proposed techniques for the feature subset selection process. Filters make use of association based approach but wrappers adopt classification algorithms to identify important features. Filter method lacks the ability of minimization of simplification error while wrapper method burden weighty computational resource. To pull through these difficulties, a hybrid approach is proposed combining both filters and wrappers. Filter approach uses a permutation of ranker search methods and a wrapper which improves the learning accurateness and obtains a lessening in the memory requirements and finishing time. The UCI machine learning repository was chosen to experiment the approach. The classification accuracy resulted from our approach proves to be higher.

  16. Analytical Study of Feature Extraction Techniques in Opinion Mining

    Directory of Open Access Journals (Sweden)

    Pravesh Kumar Singh

    2013-07-01

    Full Text Available Although opinion mining is in a nascent stage of de velopment but still the ground is set for dense growth of researches in the field. One of the important activities of opinion mining is to extract opinions of people based on characteristics of the object under study. Feature extraction in opinion mining can be done by various ways like that of clustering, support vector machines etc. This paper is an attempt to appraise the vario us techniques of feature extraction. The first part discusses various techniques and second part m akes a detailed appraisal of the major techniques used for feature extraction.

  17. Selective Extraction of Entangled Textures via Adaptive PDE Transform

    Directory of Open Access Journals (Sweden)

    Yang Wang

    2012-01-01

    Full Text Available Texture and feature extraction is an important research area with a wide range of applications in science and technology. Selective extraction of entangled textures is a challenging task due to spatial entanglement, orientation mixing, and high-frequency overlapping. The partial differential equation (PDE transform is an efficient method for functional mode decomposition. The present work introduces adaptive PDE transform algorithm to appropriately threshold the statistical variance of the local variation of functional modes. The proposed adaptive PDE transform is applied to the selective extraction of entangled textures. Successful separations of human face, clothes, background, natural landscape, text, forest, camouflaged sniper and neuron skeletons have validated the proposed method.

  18. Automated Feature Extraction from Hyperspectral Imagery Project

    Data.gov (United States)

    National Aeronautics and Space Administration — In response to NASA Topic S7.01, Visual Learning Systems, Inc. (VLS) will develop a novel hyperspectral plug-in toolkit for its award winning Feature AnalystREG...

  19. DNA Extraction and Primer Selection

    DEFF Research Database (Denmark)

    Karst, Søren Michael; Nielsen, Per Halkjær; Albertsen, Mads

    Talk regarding pitfalls in DNA extraction and 16S amplicon primer choice when performing community analysis of complex microbial communities. The talk was a part of Workshop 2 "Principles, Potential, and Limitations of Novel Molecular Methods in Water Engineering; from Amplicon Sequencing to -omics...

  20. Feature selection gait-based gender classification under different circumstances

    Science.gov (United States)

    Sabir, Azhin; Al-Jawad, Naseer; Jassim, Sabah

    2014-05-01

    This paper proposes a gender classification based on human gait features and investigates the problem of two variations: clothing (wearing coats) and carrying bag condition as addition to the normal gait sequence. The feature vectors in the proposed system are constructed after applying wavelet transform. Three different sets of feature are proposed in this method. First, Spatio-temporal distance that is dealing with the distance of different parts of the human body (like feet, knees, hand, Human Height and shoulder) during one gait cycle. The second and third feature sets are constructed from approximation and non-approximation coefficient of human body respectively. To extract these two sets of feature we divided the human body into two parts, upper and lower body part, based on the golden ratio proportion. In this paper, we have adopted a statistical method for constructing the feature vector from the above sets. The dimension of the constructed feature vector is reduced based on the Fisher score as a feature selection method to optimize their discriminating significance. Finally k-Nearest Neighbor is applied as a classification method. Experimental results demonstrate that our approach is providing more realistic scenario and relatively better performance compared with the existing approaches.

  1. Feature Selection Method Based on Neighborhood Relationships: Applications in EEG Signal Identification and Chinese Character Recognition

    Directory of Open Access Journals (Sweden)

    Yu-Xiang Zhao

    2016-06-01

    Full Text Available In this study, a new feature selection algorithm, the neighborhood-relationship feature selection (NRFS algorithm, is proposed for identifying rat electroencephalogram signals and recognizing Chinese characters. In these two applications, dependent relationships exist among the feature vectors and their neighboring feature vectors. Therefore, the proposed NRFS algorithm was designed for solving this problem. By applying the NRFS algorithm, unselected feature vectors have a high priority of being added into the feature subset if the neighboring feature vectors have been selected. In addition, selected feature vectors have a high priority of being eliminated if the neighboring feature vectors are not selected. In the experiments conducted in this study, the NRFS algorithm was compared with two feature algorithms. The experimental results indicated that the NRFS algorithm can extract the crucial frequency bands for identifying rat vigilance states and identifying crucial character regions for recognizing Chinese characters.

  2. Feature Selection Method Based on Neighborhood Relationships: Applications in EEG Signal Identification and Chinese Character Recognition

    Science.gov (United States)

    Zhao, Yu-Xiang; Chou, Chien-Hsing

    2016-01-01

    In this study, a new feature selection algorithm, the neighborhood-relationship feature selection (NRFS) algorithm, is proposed for identifying rat electroencephalogram signals and recognizing Chinese characters. In these two applications, dependent relationships exist among the feature vectors and their neighboring feature vectors. Therefore, the proposed NRFS algorithm was designed for solving this problem. By applying the NRFS algorithm, unselected feature vectors have a high priority of being added into the feature subset if the neighboring feature vectors have been selected. In addition, selected feature vectors have a high priority of being eliminated if the neighboring feature vectors are not selected. In the experiments conducted in this study, the NRFS algorithm was compared with two feature algorithms. The experimental results indicated that the NRFS algorithm can extract the crucial frequency bands for identifying rat vigilance states and identifying crucial character regions for recognizing Chinese characters. PMID:27314346

  3. Feature Selection Method Based on Neighborhood Relationships: Applications in EEG Signal Identification and Chinese Character Recognition.

    Science.gov (United States)

    Zhao, Yu-Xiang; Chou, Chien-Hsing

    2016-06-14

    In this study, a new feature selection algorithm, the neighborhood-relationship feature selection (NRFS) algorithm, is proposed for identifying rat electroencephalogram signals and recognizing Chinese characters. In these two applications, dependent relationships exist among the feature vectors and their neighboring feature vectors. Therefore, the proposed NRFS algorithm was designed for solving this problem. By applying the NRFS algorithm, unselected feature vectors have a high priority of being added into the feature subset if the neighboring feature vectors have been selected. In addition, selected feature vectors have a high priority of being eliminated if the neighboring feature vectors are not selected. In the experiments conducted in this study, the NRFS algorithm was compared with two feature algorithms. The experimental results indicated that the NRFS algorithm can extract the crucial frequency bands for identifying rat vigilance states and identifying crucial character regions for recognizing Chinese characters.

  4. Extracting Conceptual Feature Structures from Text

    DEFF Research Database (Denmark)

    Andreasen, Troels; Bulskov, Henrik; Lassen, Tine;

    2011-01-01

    This paper describes an approach to indexing texts by their conceptual content using ontologies along with lexico-syntactic information and semantic role assignment provided by lexical resources. The conceptual content of meaningful chunks of text is transformed into conceptual feature structures...

  5. Combination of heterogeneous EEG feature extraction methods and stacked sequential learning for sleep stage classification.

    Science.gov (United States)

    Herrera, L J; Fernandes, C M; Mora, A M; Migotina, D; Largo, R; Guillen, A; Rosa, A C

    2013-06-01

    This work proposes a methodology for sleep stage classification based on two main approaches: the combination of features extracted from electroencephalogram (EEG) signal by different extraction methods, and the use of stacked sequential learning to incorporate predicted information from nearby sleep stages in the final classifier. The feature extraction methods used in this work include three representative ways of extracting information from EEG signals: Hjorth features, wavelet transformation and symbolic representation. Feature selection was then used to evaluate the relevance of individual features from this set of methods. Stacked sequential learning uses a second-layer classifier to improve the classification by using previous and posterior first-layer predicted stages as additional features providing information to the model. Results show that both approaches enhance the sleep stage classification accuracy rate, thus leading to a closer approximation to the experts' opinion.

  6. [RVM supervised feature extraction and Seyfert spectra classification].

    Science.gov (United States)

    Li, Xiang-Ru; Hu, Zhan-Yi; Zhao, Yong-Heng; Li, Xiao-Ming

    2009-06-01

    With recent technological advances in wide field survey astronomy and implementation of several large-scale astronomical survey proposals (e. g. SDSS, 2dF and LAMOST), celestial spectra are becoming very abundant and rich. Therefore, research on automated classification methods based on celestial spectra has been attracting more and more attention in recent years. Feature extraction is a fundamental problem in automated spectral classification, which not only influences the difficulty and complexity of the problem, but also determines the performance of the designed classifying system. The available methods of feature extraction for spectra classification are usually unsupervised, e. g. principal components analysis (PCA), wavelet transform (WT), artificial neural networks (ANN) and Rough Set theory. These methods extract features not by their capability to classify spectra, but by some kind of power to approximate the original celestial spectra. Therefore, the extracted features by these methods usually are not the best ones for classification. In the present work, the authors pointed out the necessary to investigate supervised feature extraction by analyzing the characteristics of the spectra classification research in available literature and the limitations of unsupervised feature extracting methods. And the authors also studied supervised feature extracting based on relevance vector machine (RVM) and its application in Seyfert spectra classification. RVM is a recently introduced method based on Bayesian methodology, automatic relevance determination (ARD), regularization technique and hierarchical priors structure. By this method, the authors can easily fuse the information in training data, the authors' prior knowledge and belief in the problem, etc. And RVM could effectively extract the features and reduce the data based on classifying capability. Extensive experiments show its superior performance in dimensional reduction and feature extraction for Seyfert

  7. Selective Extraction of Bioproducts by Ionic Liquids

    Institute of Scientific and Technical Information of China (English)

    王键吉; 裴渊超; 赵扬; 张锁江

    2005-01-01

    Imidazolium based room temperature ionic liquids have been used to extract selectively L-tryptophan from fermentation broth. BF4 anion was found to enhance dramatically the partitioning of L-tryptophan into ionic liquid phase from aqueous solutions.

  8. Feature Extraction for Structural Dynamics Model Validation

    Energy Technology Data Exchange (ETDEWEB)

    Farrar, Charles [Los Alamos National Laboratory; Nishio, Mayuko [Yokohama University; Hemez, Francois [Los Alamos National Laboratory; Stull, Chris [Los Alamos National Laboratory; Park, Gyuhae [Chonnam Univesity; Cornwell, Phil [Rose-Hulman Institute of Technology; Figueiredo, Eloi [Universidade Lusófona; Luscher, D. J. [Los Alamos National Laboratory; Worden, Keith [University of Sheffield

    2016-01-13

    As structural dynamics becomes increasingly non-modal, stochastic and nonlinear, finite element model-updating technology must adopt the broader notions of model validation and uncertainty quantification. For example, particular re-sampling procedures must be implemented to propagate uncertainty through a forward calculation, and non-modal features must be defined to analyze nonlinear data sets. The latter topic is the focus of this report, but first, some more general comments regarding the concept of model validation will be discussed.

  9. Heuristical Feature Extraction from LIDAR Data and Their Visualization

    Science.gov (United States)

    Ghosh, S.; Lohani, B.

    2011-09-01

    Extraction of landscape features from LiDAR data has been studied widely in the past few years. These feature extraction methodologies have been focussed on certain types of features only, namely the bare earth model, buildings principally containing planar roofs, trees and roads. In this paper, we present a methodology to process LiDAR data through DBSCAN, a density based clustering method, which extracts natural and man-made clusters. We then develop heuristics to process these clusters and simplify them to be sent to a visualization engine.

  10. Spoken Language Identification Using Hybrid Feature Extraction Methods

    CERN Document Server

    Kumar, Pawan; Mishra, A N; Chandra, Mahesh

    2010-01-01

    This paper introduces and motivates the use of hybrid robust feature extraction technique for spoken language identification (LID) system. The speech recognizers use a parametric form of a signal to get the most important distinguishable features of speech signal for recognition task. In this paper Mel-frequency cepstral coefficients (MFCC), Perceptual linear prediction coefficients (PLP) along with two hybrid features are used for language Identification. Two hybrid features, Bark Frequency Cepstral Coefficients (BFCC) and Revised Perceptual Linear Prediction Coefficients (RPLP) were obtained from combination of MFCC and PLP. Two different classifiers, Vector Quantization (VQ) with Dynamic Time Warping (DTW) and Gaussian Mixture Model (GMM) were used for classification. The experiment shows better identification rate using hybrid feature extraction techniques compared to conventional feature extraction methods.BFCC has shown better performance than MFCC with both classifiers. RPLP along with GMM has shown be...

  11. Unsupervised Feature Selection for Latent Dirichlet Allocation

    Institute of Scientific and Technical Information of China (English)

    Xu Weiran; Du Gang; Chen Guang; Guo Jun; Yang Jie

    2011-01-01

    As a generative model Latent Dirichlet Allocation Model,which lacks optimization of topics' discrimination capability focuses on how to generate data,This paper aims to improve the discrimination capability through unsupervised feature selection.Theoretical analysis shows that the discrimination capability of a topic is limited by the discrimination capability of its representative words.The discrimination capability of a word is approximated by the Information Gain of the word for topics,which is used to distinguish between “general word” and “special word” in LDA topics.Therefore,we add a constraint to the LDA objective function to let the “general words” only happen in “general topics”other than “special topics”.Then a heuristic algorithm is presented to get the solution.Experiments show that this method can not only improve the information gain of topics,but also make the topics easier to understand by human.

  12. Feature extraction for deep neural networks based on decision boundaries

    Science.gov (United States)

    Woo, Seongyoun; Lee, Chulhee

    2017-05-01

    Feature extraction is a process used to reduce data dimensions using various transforms while preserving the discriminant characteristics of the original data. Feature extraction has been an important issue in pattern recognition since it can reduce the computational complexity and provide a simplified classifier. In particular, linear feature extraction has been widely used. This method applies a linear transform to the original data to reduce the data dimensions. The decision boundary feature extraction method (DBFE) retains only informative directions for discriminating among the classes. DBFE has been applied to various parametric and non-parametric classifiers, which include the Gaussian maximum likelihood classifier (GML), the k-nearest neighbor classifier, support vector machines (SVM) and neural networks. In this paper, we apply DBFE to deep neural networks. This algorithm is based on the nonparametric version of DBFE, which was developed for neural networks. Experimental results with the UCI database show improved classification accuracy with reduced dimensionality.

  13. Fingerprint Identification - Feature Extraction, Matching and Database Search

    NARCIS (Netherlands)

    Bazen, Asker Michiel

    2002-01-01

    Presents an overview of state-of-the-art fingerprint recognition technology for identification and verification purposes. Three principal challenges in fingerprint recognition are identified: extracting robust features from low-quality fingerprints, matching elastically deformed fingerprints and eff

  14. A Features Selection for Crops Classification

    Science.gov (United States)

    Zhao, Lei; Chen, Erxue; Li, Zengyuan; Li, Lan; Gu, Xinzhi

    2016-08-01

    Polarization orientation angle (POA) is a major parameter of electromagnetic wave. This angle will be shift due to azimuth slopes, which will affect the radiometric quality of PolSAR data. Under the assumption of reflection symmetrical medium, the shift value of polarization orientation angle (POAs) can be estimated by Circular Polarization Method (CPM). Then, the shift angle can be used to compensate PolSAR data or extract DEM information. However, it is less effective when using high-frequency SAR (L-, C-band) in the forest area. The main reason is that the polarization orientation angle shift of forest area not only influenced by topography, but also affected by the forest canopy. Among them, the influence of the former belongs to the interference information should be removed, but the impact of the latter belongs to the polarization feature information needs to be retained. The ALOS2 PALSAR2 L-band full polarimetric SAR data was used in this study. Base on the Circular Polarization and DEM-based method, we analyzed the variation of shift value of polarization orientation angle and developed the polarization orientation shift estimation and compensation of PolSAR data in forest.

  15. Feature selection with the image grand tour

    Science.gov (United States)

    Marchette, David J.; Solka, Jeffrey L.

    2000-08-01

    The grand tour is a method for visualizing high dimensional data by presenting the user with a set of projections and the projected data. This idea was extended to multispectral images by viewing each pixel as a multidimensional value, and viewing the projections of the grand tour as an image. The user then looks for projections which provide a useful interpretation of the image, for example, separating targets from clutter. We discuss a modification of this which allows the user to select convolution kernels which provide useful discriminant ability, both in an unsupervised manner as in the image grand tour, or in a supervised manner using training data. This approach is extended to other window-based features. For example, one can define a generalization of the median filter as a linear combination of the order statistics within a window. Thus the median filter is that projection containing zeros everywhere except for the middle value, which contains a one. Using the convolution grand tour one can select projections on these order statistics to obtain new nonlinear filters.

  16. Integrated Phoneme Subspace Method for Speech Feature Extraction

    Directory of Open Access Journals (Sweden)

    Park Hyunsin

    2009-01-01

    Full Text Available Speech feature extraction has been a key focus in robust speech recognition research. In this work, we discuss data-driven linear feature transformations applied to feature vectors in the logarithmic mel-frequency filter bank domain. Transformations are based on principal component analysis (PCA, independent component analysis (ICA, and linear discriminant analysis (LDA. Furthermore, this paper introduces a new feature extraction technique that collects the correlation information among phoneme subspaces and reconstructs feature space for representing phonemic information efficiently. The proposed speech feature vector is generated by projecting an observed vector onto an integrated phoneme subspace (IPS based on PCA or ICA. The performance of the new feature was evaluated for isolated word speech recognition. The proposed method provided higher recognition accuracy than conventional methods in clean and reverberant environments.

  17. A harmonic linear dynamical system for prominent ECG feature extraction.

    Science.gov (United States)

    Thi, Ngoc Anh Nguyen; Yang, Hyung-Jeong; Kim, SunHee; Do, Luu Ngoc

    2014-01-01

    Unsupervised mining of electrocardiography (ECG) time series is a crucial task in biomedical applications. To have efficiency of the clustering results, the prominent features extracted from preprocessing analysis on multiple ECG time series need to be investigated. In this paper, a Harmonic Linear Dynamical System is applied to discover vital prominent features via mining the evolving hidden dynamics and correlations in ECG time series. The discovery of the comprehensible and interpretable features of the proposed feature extraction methodology effectively represents the accuracy and the reliability of clustering results. Particularly, the empirical evaluation results of the proposed method demonstrate the improved performance of clustering compared to the previous main stream feature extraction approaches for ECG time series clustering tasks. Furthermore, the experimental results on real-world datasets show scalability with linear computation time to the duration of the time series.

  18. A Harmonic Linear Dynamical System for Prominent ECG Feature Extraction

    Directory of Open Access Journals (Sweden)

    Ngoc Anh Nguyen Thi

    2014-01-01

    Full Text Available Unsupervised mining of electrocardiography (ECG time series is a crucial task in biomedical applications. To have efficiency of the clustering results, the prominent features extracted from preprocessing analysis on multiple ECG time series need to be investigated. In this paper, a Harmonic Linear Dynamical System is applied to discover vital prominent features via mining the evolving hidden dynamics and correlations in ECG time series. The discovery of the comprehensible and interpretable features of the proposed feature extraction methodology effectively represents the accuracy and the reliability of clustering results. Particularly, the empirical evaluation results of the proposed method demonstrate the improved performance of clustering compared to the previous main stream feature extraction approaches for ECG time series clustering tasks. Furthermore, the experimental results on real-world datasets show scalability with linear computation time to the duration of the time series.

  19. Semiautomated landscape feature extraction and modeling

    Science.gov (United States)

    Wasilewski, Anthony A.; Faust, Nickolas L.; Ribarsky, William

    2001-08-01

    We have developed a semi-automated procedure for generating correctly located 3D tree objects form overhead imagery. Cross-platform software partitions arbitrarily large, geocorrected and geolocated imagery into management sub- images. The user manually selected tree areas from one or more of these sub-images. Tree group blobs are then narrowed to lines using a special thinning algorithm which retains the topology of the blobs, and also stores the thickness of the parent blob. Maxima along these thinned tree grous are found, and used as individual tree locations within the tree group. Magnitudes of the local maxima are used to scale the radii of the tree objects. Grossly overlapping trees are culled based on a comparison of tree-tree distance to combined radii. Tree color is randomly selected based on the distribution of sample tree pixels, and height is estimated form tree radius. The final tree objects are then inserted into a terrain database which can be navigated by VGIS, a high-resolution global terrain visualization system developed at Georgia Tech.

  20. Feature Selection for Chemical Sensor Arrays Using Mutual Information

    Science.gov (United States)

    Wang, X. Rosalind; Lizier, Joseph T.; Nowotny, Thomas; Berna, Amalia Z.; Prokopenko, Mikhail; Trowell, Stephen C.

    2014-01-01

    We address the problem of feature selection for classifying a diverse set of chemicals using an array of metal oxide sensors. Our aim is to evaluate a filter approach to feature selection with reference to previous work, which used a wrapper approach on the same data set, and established best features and upper bounds on classification performance. We selected feature sets that exhibit the maximal mutual information with the identity of the chemicals. The selected features closely match those found to perform well in the previous study using a wrapper approach to conduct an exhaustive search of all permitted feature combinations. By comparing the classification performance of support vector machines (using features selected by mutual information) with the performance observed in the previous study, we found that while our approach does not always give the maximum possible classification performance, it always selects features that achieve classification performance approaching the optimum obtained by exhaustive search. We performed further classification using the selected feature set with some common classifiers and found that, for the selected features, Bayesian Networks gave the best performance. Finally, we compared the observed classification performances with the performance of classifiers using randomly selected features. We found that the selected features consistently outperformed randomly selected features for all tested classifiers. The mutual information filter approach is therefore a computationally efficient method for selecting near optimal features for chemical sensor arrays. PMID:24595058

  1. Feature selection for face recognition: a memetic algorithmic approach

    Institute of Scientific and Technical Information of China (English)

    Dinesh KUMAR; Shakti KUMAR; C. S. RAI

    2009-01-01

    The eigenface method that uses principal component analysis (PCA) has been the standard and popular method used in face recognition. This paper presents a PCA-memetic algorithm (PCA-MA) approach for feature selection. PCA has been extended by MAs where the former was used for feature extraction/dimensionality reduction and the latter exploited for feature selection. Simulations were performed over ORL and YaleB face databases using Euclidean norm as the classifier. It was found that as far as the recognition rate is concerned, PCA-MA completely outperforms the eigenface method. We compared the performance of PCA extended with genetic algorithm (PCA-GA) with our proposed PCA-MA method. The results also clearly established the supremacy of the PCA-MA method over the PCA-GA method. We further extended linear discriminant analysis (LDA) and kernel principal component analysis (KPCA) approaches with the MA and observed significant improvement in recognition rate with fewer features. This paper also compares the performance of PCA-MA, LDA-MA and KPCA-MA approaches.

  2. A New Approach of Feature Selection for Text Categorization

    Institute of Scientific and Technical Information of China (English)

    CUI Zifeng; XU Baowen; ZHANG Weifeng; XU Junling

    2006-01-01

    This paper proposes a new approach of feature selection based on the independent measure between features for text categorization.A fundamental hypothesis that occurrence of the terms in documents is independent of each other,widely used in the probabilistic models for text categorization (TC), is discussed.However, the basic hypothesis is incomplete for independence of feature set.From the view of feature selection, a new independent measure between features is designed, by which a feature selection algorithm is given to obtain a feature subset.The selected subset is high in relevance with category and strong in independence between features,satisfies the basic hypothesis at maximum degree.Compared with other traditional feature selection method in TC (which is only taken into the relevance account), the performance of feature subset selected by our method is prior to others with experiments on the benchmark dataset of 20 Newsgroups.

  3. Soft computing based feature selection for environmental sound classification

    NARCIS (Netherlands)

    Shakoor, A.; May, T.M.; Van Schijndel, N.H.

    2010-01-01

    Environmental sound classification has a wide range of applications,like hearing aids, mobile communication devices, portable media players, and auditory protection devices. Sound classification systemstypically extract features from the input sound. Using too many features increases complexity unne

  4. Soft computing based feature selection for environmental sound classification

    NARCIS (Netherlands)

    Shakoor, A.; May, T.M.; Van Schijndel, N.H.

    2010-01-01

    Environmental sound classification has a wide range of applications,like hearing aids, mobile communication devices, portable media players, and auditory protection devices. Sound classification systemstypically extract features from the input sound. Using too many features increases complexity unne

  5. Feature extraction for the analysis of colon status from the endoscopic images

    Directory of Open Access Journals (Sweden)

    Krishnan Shankar M

    2003-04-01

    Full Text Available Abstract Background Extracting features from the colonoscopic images is essential for getting the features, which characterizes the properties of the colon. The features are employed in the computer-assisted diagnosis of colonoscopic images to assist the physician in detecting the colon status. Methods Endoscopic images contain rich texture and color information. Novel schemes are developed to extract new texture features from the texture spectra in the chromatic and achromatic domains, and color features for a selected region of interest from each color component histogram of the colonoscopic images. These features are reduced in size using Principal Component Analysis (PCA and are evaluated using Backpropagation Neural Network (BPNN. Results Features extracted from endoscopic images were tested to classify the colon status as either normal or abnormal. The classification results obtained show the features' capability for classifying the colon's status. The average classification accuracy, which is using hybrid of the texture and color features with PCA (τ = 1%, is 97.72%. It is higher than the average classification accuracy using only texture (96.96%, τ = 1% or color (90.52%, τ = 1% features. Conclusion In conclusion, novel methods for extracting new texture- and color-based features from the colonoscopic images to classify the colon status have been proposed. A new approach using PCA in conjunction with BPNN for evaluating the features has also been proposed. The preliminary test results support the feasibility of the proposed method.

  6. Feature Extraction for Facial Expression Recognition based on Hybrid Face Regions

    Directory of Open Access Journals (Sweden)

    LAJEVARDI, S.M.

    2009-10-01

    Full Text Available Facial expression recognition has numerous applications, including psychological research, improved human computer interaction, and sign language translation. A novel facial expression recognition system based on hybrid face regions (HFR is investigated. The expression recognition system is fully automatic, and consists of the following modules: face detection, facial detection, feature extraction, optimal features selection, and classification. The features are extracted from both whole face image and face regions (eyes and mouth using log Gabor filters. Then, the most discriminate features are selected based on mutual information criteria. The system can automatically recognize six expressions: anger, disgust, fear, happiness, sadness and surprise. The selected features are classified using the Naive Bayesian (NB classifier. The proposed method has been extensively assessed using Cohn-Kanade database and JAFFE database. The experiments have highlighted the efficiency of the proposed HFR method in enhancing the classification rate.

  7. Level Sets and Voronoi based Feature Extraction from any Imagery

    DEFF Research Database (Denmark)

    Sharma, O.; Anton, François; Mioc, Darka

    2012-01-01

    Polygon features are of interest in many GEOProcessing applications like shoreline mapping, boundary delineation, change detection, etc. This paper presents a unique new GPU-based methodology to automate feature extraction combining level sets, or mean shift based segmentation together with Voronoi...

  8. Feature Extraction for Mental Fatigue and Relaxation States Based on Systematic Evaluation Considering Individual Difference

    Science.gov (United States)

    Chen, Lanlan; Sugi, Takenao; Shirakawa, Shuichiro; Zou, Junzhong; Nakamura, Masatoshi

    Feature extraction for mental fatigue and relaxation states is helpful to understand the mechanisms of mental fatigue and search effective relaxation technique in sustained work environments. Experiment data of human states are often affected by external and internal factors, which increase the difficulties to extract common features. The aim of this study is to explore appropriate methods to eliminate individual difference and enhance common features. Mental fatigue and relaxation experiments are executed on 12 subjects. An integrated and evaluation system is proposed, which consists of subjective evaluation (visual analogue scale), calculation performance and neurophysiological signals especially EEG signals. With consideration of individual difference, the common features of multi-estimators testify the effectiveness of relaxation in sustained mental work. Relaxation technique can be practically applied to prevent accumulation of mental fatigue and keep mental health. The proposed feature extraction methods are widely applicable to obtain common features and release the restriction for subjection selection and experiment design.

  9. EEG signal features extraction based on fractal dimension.

    Science.gov (United States)

    Finotello, Francesca; Scarpa, Fabio; Zanon, Mattia

    2015-01-01

    The spread of electroencephalography (EEG) in countless applications has fostered the development of new techniques for extracting synthetic and informative features from EEG signals. However, the definition of an effective feature set depends on the specific problem to be addressed and is currently an active field of research. In this work, we investigated the application of features based on fractal dimension to a problem of sleep identification from EEG data. We demonstrated that features based on fractal dimension, including two novel indices defined in this work, add valuable information to standard EEG features and significantly improve sleep identification performance.

  10. Image feature meaning for automatic key-frame extraction

    Science.gov (United States)

    Di Lecce, Vincenzo; Guerriero, Andrea

    2003-12-01

    Video abstraction and summarization, being request in several applications, has address a number of researches to automatic video analysis techniques. The processes for automatic video analysis are based on the recognition of short sequences of contiguous frames that describe the same scene, shots, and key frames representing the salient content of the shot. Since effective shot boundary detection techniques exist in the literature, in this paper we will focus our attention on key frames extraction techniques to identify the low level visual features of the frames that better represent the shot content. To evaluate the features performance, key frame automatically extracted using these features, are compared to human operator video annotations.

  11. Feature Selection for Wheat Yield Prediction

    Science.gov (United States)

    Ruß, Georg; Kruse, Rudolf

    Carrying out effective and sustainable agriculture has become an important issue in recent years. Agricultural production has to keep up with an everincreasing population by taking advantage of a field’s heterogeneity. Nowadays, modern technology such as the global positioning system (GPS) and a multitude of developed sensors enable farmers to better measure their fields’ heterogeneities. For this small-scale, precise treatment the term precision agriculture has been coined. However, the large amounts of data that are (literally) harvested during the growing season have to be analysed. In particular, the farmer is interested in knowing whether a newly developed heterogeneity sensor is potentially advantageous or not. Since the sensor data are readily available, this issue should be seen from an artificial intelligence perspective. There it can be treated as a feature selection problem. The additional task of yield prediction can be treated as a multi-dimensional regression problem. This article aims to present an approach towards solving these two practically important problems using artificial intelligence and data mining ideas and methodologies.

  12. Feature extraction with LIDAR data and aerial images

    Science.gov (United States)

    Mao, Jianhua; Liu, Yanjing; Cheng, Penggen; Li, Xianhua; Zeng, Qihong; Xia, Jing

    2006-10-01

    Raw LIDAR data is a irregular spacing 3D point cloud including reflections from bare ground, buildings, vegetation and vehicles etc., and the first task of the data analyses of point cloud is feature extraction. However, the interpretability of LIDAR point cloud is often limited due to the fact that no object information is provided, and the complex earth topography and object morphology make it impossible for a single operator to classify all the point cloud precisely 100%. In this paper, a hierarchy method for feature extraction with LIDAR data and aerial images is discussed. The aerial images provide us information of objects figuration and spatial distribution, and hierarchic classification of features makes it easy to apply automatic filters progressively. And the experiment results show that, using this method, it was possible to detect more object information and get a better result of feature extraction than using automatic filters alone.

  13. Distinctive Feature Extraction for Indian Sign Language (ISL) Gesture using Scale Invariant Feature Transform (SIFT)

    Science.gov (United States)

    Patil, Sandeep Baburao; Sinha, G. R.

    2016-07-01

    India, having less awareness towards the deaf and dumb peoples leads to increase the communication gap between deaf and hard hearing community. Sign language is commonly developed for deaf and hard hearing peoples to convey their message by generating the different sign pattern. The scale invariant feature transform was introduced by David Lowe to perform reliable matching between different images of the same object. This paper implements the various phases of scale invariant feature transform to extract the distinctive features from Indian sign language gestures. The experimental result shows the time constraint for each phase and the number of features extracted for 26 ISL gestures.

  14. Distinctive Feature Extraction for Indian Sign Language (ISL) Gesture using Scale Invariant Feature Transform (SIFT)

    Science.gov (United States)

    Patil, Sandeep Baburao; Sinha, G. R.

    2017-02-01

    India, having less awareness towards the deaf and dumb peoples leads to increase the communication gap between deaf and hard hearing community. Sign language is commonly developed for deaf and hard hearing peoples to convey their message by generating the different sign pattern. The scale invariant feature transform was introduced by David Lowe to perform reliable matching between different images of the same object. This paper implements the various phases of scale invariant feature transform to extract the distinctive features from Indian sign language gestures. The experimental result shows the time constraint for each phase and the number of features extracted for 26 ISL gestures.

  15. Feature extraction for magnetic domain images of magneto-optical recording films using gradient feature segmentation

    Science.gov (United States)

    Quanqing, Zhu; Xinsai, Wang; Xuecheng, Zou; Haihua, Li; Xiaofei, Yang

    2002-07-01

    In this paper, we present a method to realize feature extraction on low contrast magnetic domain images of magneto-optical recording films. The method is based on the following three steps: first, Lee-filtering method is adopted to realize pre-filtering and noise reduction; this is followed by gradient feature segmentation, which separates the object area from the background area; finally the common linking method is adopted and the characteristic parameters of magnetic domain are calculated. We describe these steps with particular emphasis on the gradient feature segmentation. The results show that this method has advantages over other traditional ones for feature extraction of low contrast images.

  16. Detecting Lo cal Manifold Structure for Unsup ervised Feature Selection

    Institute of Scientific and Technical Information of China (English)

    FENG Ding-Cheng; CHEN Feng; XU Wen-Li

    2014-01-01

    Unsupervised feature selection is fundamental in statistical pattern recognition, and has drawn persistent attention in the past several decades. Recently, much work has shown that feature selection can be formulated as nonlinear dimensionality reduction with discrete constraints. This line of research emphasizes utilizing the manifold learning techniques, where feature selection and learning can be studied based on the manifold assumption in data distribution. Many existing feature selection methods such as Laplacian score, SPEC (spectrum decomposition of graph Laplacian), TR (trace ratio) criterion, MSFS (multi-cluster feature selection) and EVSC (eigenvalue sensitive criterion) apply the basic properties of graph Laplacian, and select the optimal feature subsets which best preserve the manifold structure defined on the graph Laplacian. In this paper, we propose a new feature selection perspective from locally linear embedding (LLE), which is another popular manifold learning method. The main difficulty of using LLE for feature selection is that its optimization involves quadratic programming and eigenvalue decomposition, both of which are continuous procedures and different from discrete feature selection. We prove that the LLE objective can be decomposed with respect to data dimensionalities in the subset selection problem, which also facilitates constructing better coordinates from data using the principal component analysis (PCA) technique. Based on these results, we propose a novel unsupervised feature selection algorithm, called locally linear selection (LLS), to select a feature subset representing the underlying data manifold. The local relationship among samples is computed from the LLE formulation, which is then used to estimate the contribution of each individual feature to the underlying manifold structure. These contributions, represented as LLS scores, are ranked and selected as the candidate solution to feature selection. We further develop a

  17. Fast SIFT design for real-time visual feature extraction.

    Science.gov (United States)

    Chiu, Liang-Chi; Chang, Tian-Sheuan; Chen, Jiun-Yen; Chang, Nelson Yen-Chung

    2013-08-01

    Visual feature extraction with scale invariant feature transform (SIFT) is widely used for object recognition. However, its real-time implementation suffers from long latency, heavy computation, and high memory storage because of its frame level computation with iterated Gaussian blur operations. Thus, this paper proposes a layer parallel SIFT (LPSIFT) with integral image, and its parallel hardware design with an on-the-fly feature extraction flow for real-time application needs. Compared with the original SIFT algorithm, the proposed approach reduces the computational amount by 90% and memory usage by 95%. The final implementation uses 580-K gate count with 90-nm CMOS technology, and offers 6000 feature points/frame for VGA images at 30 frames/s and ∼ 2000 feature points/frame for 1920 × 1080 images at 30 frames/s at the clock rate of 100 MHz.

  18. Local features for enhancement and minutiae extraction in fingerprints.

    Science.gov (United States)

    Fronthaler, Hartwig; Kollreider, Klaus; Bigun, Josef

    2008-03-01

    Accurate fingerprint recognition presupposes robust feature extraction which is often hampered by noisy input data. We suggest common techniques for both enhancement and minutiae extraction, employing symmetry features. For enhancement, a Laplacian-like image pyramid is used to decompose the original fingerprint into sub-bands corresponding to different spatial scales. In a further step, contextual smoothing is performed on these pyramid levels, where the corresponding filtering directions stem from the frequency-adapted structure tensor (linear symmetry features). For minutiae extraction, parabolic symmetry is added to the local fingerprint model which allows to accurately detect the position and direction of a minutia simultaneously. Our experiments support the view that using the suggested parabolic symmetry features, the extraction of which does not require explicit thinning or other morphological operations, constitute a robust alternative to conventional minutiae extraction. All necessary image processing is done in the spatial domain using 1-D filters only, avoiding block artifacts that reduce the biometric information. We present comparisons to other studies on enhancement in matching tasks employing the open source matcher from NIST, FIS2. Furthermore, we compare the proposed minutiae extraction method with the corresponding method from the NIST package, mindtct. A top five commercial matcher from FVC2006 is used in enhancement quantification as well. The matching error is lowered significantly when plugging in the suggested methods. The FVC2004 fingerprint database, notable for its exceptionally low-quality fingerprints, is used for all experiments.

  19. Surface Electromyography Feature Extraction Based on Wavelet Transform

    Directory of Open Access Journals (Sweden)

    Farzaneh Akhavan Mahdavi

    2012-12-01

    Full Text Available Considering the vast variety of EMG signal applications such as rehabilitation of people suffering from some mobility limitations, scientists have done much research on EMG control system. In this regard, feature extraction of EMG signal has been highly valued as a significant technique to extract the desired information of EMG signal and remove unnecessary parts. In this study, Wavelet Transform (WT has been applied as the main technique to extract Surface EMG (SEMG features because WT is consistent with the nature of EMG as a nonstationary signal. Furthermore, two evaluation criteria, namely, RES index (the ratio of a Euclidean distance to a standard deviation and scatter plot are recruited to investigate the efficiency of wavelet feature extraction. The results illustrated an improvement in class separability of hand movements in feature space. Accordingly, it has been shown that only the SEMG features extracted from first and second level of WT decomposition by second order of Daubechies family (db2 yielded the best class separability.

  20. Combining Multiple Feature Extraction Techniques for Handwritten Devnagari Character Recognition

    CERN Document Server

    Arora, Sandhya; Nasipuri, Mita; Basu, Dipak Kumar; Kundu, Mahantapas

    2010-01-01

    In this paper we present an OCR for Handwritten Devnagari Characters. Basic symbols are recognized by neural classifier. We have used four feature extraction techniques namely, intersection, shadow feature, chain code histogram and straight line fitting features. Shadow features are computed globally for character image while intersection features, chain code histogram features and line fitting features are computed by dividing the character image into different segments. Weighted majority voting technique is used for combining the classification decision obtained from four Multi Layer Perceptron(MLP) based classifier. On experimentation with a dataset of 4900 samples the overall recognition rate observed is 92.80% as we considered top five choices results. This method is compared with other recent methods for Handwritten Devnagari Character Recognition and it has been observed that this approach has better success rate than other methods.

  1. Naive Bayes-Guided Bat Algorithm for Feature Selection

    Directory of Open Access Journals (Sweden)

    Ahmed Majid Taha

    2013-01-01

    Full Text Available When the amount of data and information is said to double in every 20 months or so, feature selection has become highly important and beneficial. Further improvements in feature selection will positively affect a wide array of applications in fields such as pattern recognition, machine learning, or signal processing. Bio-inspired method called Bat Algorithm hybridized with a Naive Bayes classifier has been presented in this work. The performance of the proposed feature selection algorithm was investigated using twelve benchmark datasets from different domains and was compared to three other well-known feature selection algorithms. Discussion focused on four perspectives: number of features, classification accuracy, stability, and feature generalization. The results showed that BANB significantly outperformed other algorithms in selecting lower number of features, hence removing irrelevant, redundant, or noisy features while maintaining the classification accuracy. BANB is also proven to be more stable than other methods and is capable of producing more general feature subsets.

  2. EEG Signal Denoising and Feature Extraction Using Wavelet Transform in Brain Computer Interface

    Institute of Scientific and Technical Information of China (English)

    WU Ting; YAN Guo-zheng; YANG Bang-hua; SUN Hong

    2007-01-01

    Electroencephalogram (EEG) signal preprocessing is one of the most important techniques in brain computer interface (BCI). The target is to increase signal-to-noise ratio and make it more favorable for feature extraction and pattern recognition. Wavelet transform is a method of multi-resolution time-frequency analysis, it can decompose the mixed signals which consist of different frequencies into different frequency band. EEG signal is analyzed and denoised using wavelet transform. Moreover, wavelet transform can be used for EEG feature extraction. The energies of specific sub-bands and corresponding decomposition coefficients which have maximal separability according to the Fisher distance criterion are selected as features. The eigenvector for classification is obtained by combining the effective features from different channels. The performance is evaluated by separability and pattern recognition accuracy using the data set of BCI 2003 Competition, the final classification results have proved the effectiveness of this technology for EEG denoising and feature extraction.

  3. Feature dimensionality reduction for myoelectric pattern recognition: a comparison study of feature selection and feature projection methods.

    Science.gov (United States)

    Liu, Jie

    2014-12-01

    This study investigates the effect of the feature dimensionality reduction strategies on the classification of surface electromyography (EMG) signals toward developing a practical myoelectric control system. Two dimensionality reduction strategies, feature selection and feature projection, were tested on both EMG feature sets, respectively. A feature selection based myoelectric pattern recognition system was introduced to select the features by eliminating the redundant features of EMG recordings instead of directly choosing a subset of EMG channels. The Markov random field (MRF) method and a forward orthogonal search algorithm were employed to evaluate the contribution of each individual feature to the classification, respectively. Our results from 15 healthy subjects indicate that, with a feature selection analysis, independent of the type of feature set, across all subjects high overall accuracies can be achieved in classification of seven different forearm motions with a small number of top ranked original EMG features obtained from the forearm muscles (average overall classification accuracy >95% with 12 selected EMG features). Compared to various feature dimensionality reduction techniques in myoelectric pattern recognition, the proposed filter-based feature selection approach is independent of the type of classification algorithms and features, which can effectively reduce the redundant information not only across different channels, but also cross different features in the same channel. This may enable robust EMG feature dimensionality reduction without needing to change ongoing, practical use of classification algorithms, an important step toward clinical utility.

  4. Efficient Generation and Selection of Combined Features for Improved Classification

    KAUST Repository

    Shono, Ahmad N.

    2014-05-01

    This study contributes a methodology and associated toolkit developed to allow users to experiment with the use of combined features in classification problems. Methods are provided for efficiently generating combined features from an original feature set, for efficiently selecting the most discriminating of these generated combined features, and for efficiently performing a preliminary comparison of the classification results when using the original features exclusively against the results when using the selected combined features. The potential benefit of considering combined features in classification problems is demonstrated by applying the developed methodology and toolkit to three sample data sets where the discovery of combined features containing new discriminating information led to improved classification results.

  5. Feature selection applied to ultrasound carotid images segmentation.

    Science.gov (United States)

    Rosati, Samanta; Molinari, Filippo; Balestra, Gabriella

    2011-01-01

    The automated tracing of the carotid layers on ultrasound images is complicated by noise, different morphology and pathology of the carotid artery. In this study we benchmarked four methods for feature selection on a set of variables extracted from ultrasound carotid images. The main goal was to select those parameters containing the highest amount of information useful to classify the pixels in the carotid regions they belong to. Six different classes of pixels were identified: lumen, lumen-intima interface, intima-media complex, media-adventitia interface, adventitia and adventitia far boundary. The performances of QuickReduct Algorithm (QRA), Entropy-Based Algorithm (EBR), Improved QuickReduct Algorithm (IQRA) and Genetic Algorithm (GA) were compared using Artificial Neural Networks (ANNs). All methods returned subsets with a high dependency degree, even if the average classification accuracy was about 50%. Among all classes, the best results were obtained for the lumen. Overall, the four methods for feature selection assessed in this study return comparable results. Despite the need for accuracy improvement, this study could be useful to build a pre-classifier stage for the optimization of segmentation performance in ultrasound automated carotid segmentation.

  6. Fingerprint Recognition: Enhancement, Feature Extraction and Automatic Evaluation of Algorithms

    OpenAIRE

    Turroni, Francesco

    2012-01-01

    The identification of people by measuring some traits of individual anatomy or physiology has led to a specific research area called biometric recognition. This thesis is focused on improving fingerprint recognition systems considering three important problems: fingerprint enhancement, fingerprint orientation extraction and automatic evaluation of fingerprint algorithms. An effective extraction of salient fingerprint features depends on the quality of the input fingerprint. If the fingerp...

  7. Towards Home-Made Dictionaries for Musical Feature Extraction

    DEFF Research Database (Denmark)

    Harbo, Anders La-Cour

    2003-01-01

    The majority of musical feature extraction applications are based on the Fourier transform in various disguises. This is despite the fact that this transform is subject to a series of restrictions, which admittedly ease the computation and interpretation of transform coefficients, but also imposes...... arguably unnecessary limitations on the ability of the transform to extract and identify features. However, replacing the nicely structured dictionary of the Fourier transform (or indeed other nice transform such as the wavelet transform) with a home-made dictionary is a dangerous task, since even the most...

  8. Moment feature based fast feature extraction algorithm for moving object detection using aerial images.

    Directory of Open Access Journals (Sweden)

    A F M Saifuddin Saif

    Full Text Available Fast and computationally less complex feature extraction for moving object detection using aerial images from unmanned aerial vehicles (UAVs remains as an elusive goal in the field of computer vision research. The types of features used in current studies concerning moving object detection are typically chosen based on improving detection rate rather than on providing fast and computationally less complex feature extraction methods. Because moving object detection using aerial images from UAVs involves motion as seen from a certain altitude, effective and fast feature extraction is a vital issue for optimum detection performance. This research proposes a two-layer bucket approach based on a new feature extraction algorithm referred to as the moment-based feature extraction algorithm (MFEA. Because a moment represents the coherent intensity of pixels and motion estimation is a motion pixel intensity measurement, this research used this relation to develop the proposed algorithm. The experimental results reveal the successful performance of the proposed MFEA algorithm and the proposed methodology.

  9. Automated blood vessel extraction using local features on retinal images

    Science.gov (United States)

    Hatanaka, Yuji; Samo, Kazuki; Tajima, Mikiya; Ogohara, Kazunori; Muramatsu, Chisako; Okumura, Susumu; Fujita, Hiroshi

    2016-03-01

    An automated blood vessel extraction using high-order local autocorrelation (HLAC) on retinal images is presented. Although many blood vessel extraction methods based on contrast have been proposed, a technique based on the relation of neighbor pixels has not been published. HLAC features are shift-invariant; therefore, we applied HLAC features to retinal images. However, HLAC features are weak to turned image, thus a method was improved by the addition of HLAC features to a polar transformed image. The blood vessels were classified using an artificial neural network (ANN) with HLAC features using 105 mask patterns as input. To improve performance, the second ANN (ANN2) was constructed by using the green component of the color retinal image and the four output values of ANN, Gabor filter, double-ring filter and black-top-hat transformation. The retinal images used in this study were obtained from the "Digital Retinal Images for Vessel Extraction" (DRIVE) database. The ANN using HLAC output apparent white values in the blood vessel regions and could also extract blood vessels with low contrast. The outputs were evaluated using the area under the curve (AUC) based on receiver operating characteristics (ROC) analysis. The AUC of ANN2 was 0.960 as a result of our study. The result can be used for the quantitative analysis of the blood vessels.

  10. Shape Adaptive, Robust Iris Feature Extraction from Noisy Iris Images

    Science.gov (United States)

    Ghodrati, Hamed; Dehghani, Mohammad Javad; Danyali, Habibolah

    2013-01-01

    In the current iris recognition systems, noise removing step is only used to detect noisy parts of the iris region and features extracted from there will be excluded in matching step. Whereas depending on the filter structure used in feature extraction, the noisy parts may influence relevant features. To the best of our knowledge, the effect of noise factors on feature extraction has not been considered in the previous works. This paper investigates the effect of shape adaptive wavelet transform and shape adaptive Gabor-wavelet for feature extraction on the iris recognition performance. In addition, an effective noise-removing approach is proposed in this paper. The contribution is to detect eyelashes and reflections by calculating appropriate thresholds by a procedure called statistical decision making. The eyelids are segmented by parabolic Hough transform in normalized iris image to decrease computational burden through omitting rotation term. The iris is localized by an accurate and fast algorithm based on coarse-to-fine strategy. The principle of mask code generation is to assign the noisy bits in an iris code in order to exclude them in matching step is presented in details. An experimental result shows that by using the shape adaptive Gabor-wavelet technique there is an improvement on the accuracy of recognition rate. PMID:24696801

  11. Feature extraction from multiple data sources using genetic programming.

    Energy Technology Data Exchange (ETDEWEB)

    Szymanski, J. J. (John J.); Brumby, Steven P.; Pope, P. A. (Paul A.); Eads, D. R. (Damian R.); Galassi, M. C. (Mark C.); Harvey, N. R. (Neal R.); Perkins, S. J. (Simon J.); Porter, R. B. (Reid B.); Theiler, J. P. (James P.); Young, A. C. (Aaron Cody); Bloch, J. J. (Jeffrey J.); David, N. A. (Nancy A.); Esch-Mosher, D. M. (Diana M.)

    2002-01-01

    Feature extration from imagery is an important and long-standing problem in remote sensing. In this paper, we report on work using genetic programming to perform feature extraction simultaneously from multispectral and digital elevation model (DEM) data. The tool used is the GENetic Imagery Exploitation (GENIE) software, which produces image-processing software that inherently combines spatial and spectral processing. GENIE is particularly useful in exploratory studies of imagery, such as one often does in combining data from multiple sources. The user trains the software by painting the feature of interest with a simple graphical user interface. GENIE then uses genetic programming techniques to produce an image-processing pipeline. Here, we demonstrate evolution of image processing algorithms that extract a range of land-cover features including towns, grasslands, wild fire burn scars, and several types of forest. We use imagery from the DOE/NNSA Multispectral Thermal Imager (MTI) spacecraft, fused with USGS 1:24000 scale DEM data.

  12. Remote Sensing Image Feature Extracting Based Multiple Ant Colonies Cooperation

    Directory of Open Access Journals (Sweden)

    Zhang Zhi-long

    2014-02-01

    Full Text Available This paper presents a novel feature extraction method for remote sensing imagery based on the cooperation of multiple ant colonies. First, multiresolution expression of the input remote sensing imagery is created, and two different ant colonies are spread on different resolution images. The ant colony in the low-resolution image uses phase congruency as the inspiration information, whereas that in the high-resolution image uses gradient magnitude. The two ant colonies cooperate to detect features in the image by sharing the same pheromone matrix. Finally, the image features are extracted on the basis of the pheromone matrix threshold. Because a substantial amount of information in the input image is used as inspiration information of the ant colonies, the proposed method shows higher intelligence and acquires more complete and meaningful image features than those of other simple edge detectors.

  13. Face Feature Extraction for Recognition Using Radon Transform

    Directory of Open Access Journals (Sweden)

    Justice Kwame Appati

    2016-07-01

    Full Text Available Face recognition for some time now has been a challenging exercise especially when it comes to recognizing faces with different pose. This perhaps is due to the use of inappropriate descriptors during the feature extraction stage. In this paper, a thorough examination of the Radon Transform as a face signature descriptor was investigated on one of the standard database. The global features were rather considered by constructing a Gray Level Co-occurrences Matrices (GLCMs. Correlation, Energy, Homogeneity and Contrast are computed from each image to form the feature vector for recognition. We showed that, the transformed face signatures are robust and invariant to the different pose. With the statistical features extracted, face training classes are optimally broken up through the use of Support Vector Machine (SVM whiles recognition rate for test face images are computed based on the L1 norm.

  14. Principal Feature Analysis: A Multivariate Feature Selection Method for fMRI Data

    Directory of Open Access Journals (Sweden)

    Lijun Wang

    2013-01-01

    Full Text Available Brain decoding with functional magnetic resonance imaging (fMRI requires analysis of complex, multivariate data. Multivoxel pattern analysis (MVPA has been widely used in recent years. MVPA treats the activation of multiple voxels from fMRI data as a pattern and decodes brain states using pattern classification methods. Feature selection is a critical procedure of MVPA because it decides which features will be included in the classification analysis of fMRI data, thereby improving the performance of the classifier. Features can be selected by limiting the analysis to specific anatomical regions or by computing univariate (voxel-wise or multivariate statistics. However, these methods either discard some informative features or select features with redundant information. This paper introduces the principal feature analysis as a novel multivariate feature selection method for fMRI data processing. This multivariate approach aims to remove features with redundant information, thereby selecting fewer features, while retaining the most information.

  15. NEW FEATURE SELECTION METHOD IN MACHINE FAULT DIAGNOSIS

    Institute of Scientific and Technical Information of China (English)

    Wang Xinfeng; Qiu Jing; Liu Guanjun

    2005-01-01

    Aiming to deficiency of the filter and wrapper feature selection methods, a new method based on composite method of filter and wrapper method is proposed. First the method filters original features to form a feature subset which can meet classification correctness rate, then applies wrapper feature selection method select optimal feature subset. A successful technique for solving optimization problems is given by genetic algorithm (GA). GA is applied to the problem of optimal feature selection. The composite method saves computing time several times of the wrapper method with holding the classification accuracy in data simulation and experiment on bearing fault feature selection. So this method possesses excellent optimization property, can save more selection time, and has the characteristics of high accuracy and high efficiency.

  16. Discriminative tonal feature extraction method in mandarin speech recognition

    Institute of Scientific and Technical Information of China (English)

    HUANG Hao; ZHU Jie

    2007-01-01

    To utilize the supra-segmental nature of Mandarin tones, this article proposes a feature extraction method for hidden markov model (HMM) based tone modeling. The method uses linear transforms to project F0 (fundamental frequency) features of neighboring syllables as compensations, and adds them to the original F0 features of the current syllable. The transforms are discriminatively trained by using an objective function termed as "minimum tone error", which is a smooth approximation of tone recognition accuracy. Experiments show that the new tonal features achieve 3.82% tone recognition rate improvement, compared with the baseline, using maximum likelihood trained HMM on the normal F0 features. Further experiments show that discriminative HMM training on the new features is 8.78% better than the baseline.

  17. GFF-Ex: a genome feature extraction package

    OpenAIRE

    Rastogi, Achal; Gupta, Dinesh

    2014-01-01

    Background Genomic features of whole genome sequences emerging from various sequencing and annotation projects are represented and stored in several formats. Amongst these formats, the GFF (Generic/General Feature Format) has emerged as a widely accepted, portable and successfully used flat file format for genome annotation storage. With an increasing interest in genome annotation projects and secondary and meta-analysis, there is a need for efficient tools to extract sequences of interests f...

  18. Data Feature Extraction for High-Rate 3-Phase Data

    Energy Technology Data Exchange (ETDEWEB)

    2016-10-18

    This algorithm processes high-rate 3-phase signals to identify the start time of each signal and estimate its envelope as data features. The start time and magnitude of each signal during the steady state is also extracted. The features can be used to detect abnormal signals. This algorithm is developed to analyze Exxeno's 3-phase voltage and current data recorded from refrigeration systems to detect device failure or degradation.

  19. SELECTIVE EXTRACTION OF ISOLATED MITOTIC APPARATUS

    Science.gov (United States)

    Bibring, Thomas; Baxandall, Jane

    1971-01-01

    Mitotic apparatus isolated from sea urchin eggs has been treated with meralluride sodium under conditions otherwise resembling those of its isolation. The treatment causes a selective morphological disappearance of microtubules while extracting a major protein fraction, probably consisting of two closely related proteins, which constitutes about 10% of mitotic apparatus protein. Extraction of other cell particulates under similar conditions yields much less of this protein. The extracted protein closely resembles outer doublet microtubule protein from sea urchin sperm tail in properties considered typical of microtubule proteins: precipitation by calcium ion and vinblastine, electrophoretic mobility in both acid and basic polyacrylamide gels, sedimentation coefficient, molecular weight, and, according to a preliminary determination, amino acid composition. An antiserum against a preparation of sperm tail outer doublet microtubules cross-reacts with the extract from mitotic apparatus. On the basis of these findings it appears that microtubule protein is selectively extracted from isolated mitotic apparatus by treatment with meralluride, and is a typical microtubule protein. PMID:5543404

  20. Neighbourhood search feature selection method for content-based mammogram retrieval.

    Science.gov (United States)

    Chandy, D Abraham; Christinal, A Hepzibah; Theodore, Alwyn John; Selvan, S Easter

    2017-03-01

    Content-based image retrieval plays an increasing role in the clinical process for supporting diagnosis. This paper proposes a neighbourhood search method to select the near-optimal feature subsets for the retrieval of mammograms from the Mammographic Image Analysis Society (MIAS) database. The features based on grey level cooccurrence matrix, Daubechies-4 wavelet, Gabor, Cohen-Daubechies-Feauveau 9/7 wavelet and Zernike moments are extracted from mammograms available in the MIAS database to form the combined or fused feature set for testing various feature selection methods. The performance of feature selection methods is evaluated using precision, storage requirement and retrieval time measures. Using the proposed method, a significant improvement is achieved in mean precision rate and feature dimension. The results show that the proposed method outperforms the state-of-the-art feature selection methods.

  1. A curriculum-based approach for feature selection

    Science.gov (United States)

    Kalavala, Deepthi; Bhagvati, Chakravarthy

    2017-06-01

    Curriculum learning is a learning technique in which a classifier learns from easy samples first and then from increasingly difficult samples. On similar lines, a curriculum based feature selection framework is proposed for identifying most useful features in a dataset. Given a dataset, first, easy and difficult samples are identified. In general, the number of easy samples is assumed larger than difficult samples. Then, feature selection is done in two stages. In the first stage a fast feature selection method which gives feature scores is used. Feature scores are then updated incrementally with the set of difficult samples. The existing feature selection methods are not incremental in nature; entire data needs to be used in feature selection. The use of curriculum learning is expected to decrease the time needed for feature selection with classification accuracy comparable to the existing methods. Curriculum learning also allows incremental refinements in feature selection as new training samples become available. Our experiments on a number of standard datasets demonstrate that feature selection is indeed faster without sacrificing classification accuracy.

  2. Feature-extraction algorithms for the PANDA electromagnetic calorimeter

    NARCIS (Netherlands)

    Kavatsyuk, M.; Guliyev, E.; Lemmens, P. J. J.; Loehner, H.; Poelman, T. P.; Tambave, G.; Yu, B

    2009-01-01

    The feature-extraction algorithms are discussed which have been developed for the digital front-end electronics of the electromagnetic calorimeter of the PANDA detector at the future FAIR facility. Performance parameters have been derived in test measurements with cosmic rays, particle and photon

  3. Feature-extraction algorithms for the PANDA electromagnetic calorimeter

    NARCIS (Netherlands)

    Kavatsyuk, M.; Guliyev, E.; Lemmens, P. J. J.; Loehner, H.; Poelman, T. P.; Tambave, G.; Yu, B

    2009-01-01

    The feature-extraction algorithms are discussed which have been developed for the digital front-end electronics of the electromagnetic calorimeter of the PANDA detector at the future FAIR facility. Performance parameters have been derived in test measurements with cosmic rays, particle and photon be

  4. Sparse kernel orthonormalized PLS for feature extraction in large datasets

    DEFF Research Database (Denmark)

    Arenas-García, Jerónimo; Petersen, Kaare Brandt; Hansen, Lars Kai

    2006-01-01

    In this paper we are presenting a novel multivariate analysis method for large scale problems. Our scheme is based on a novel kernel orthonormalized partial least squares (PLS) variant for feature extraction, imposing sparsity constrains in the solution to improve scalability. The algorithm is te...

  5. Features extraction in anterior and posterior cruciate ligaments analysis.

    Science.gov (United States)

    Zarychta, P

    2015-12-01

    The main aim of this research is finding the feature vectors of the anterior and posterior cruciate ligaments (ACL and PCL). These feature vectors have to clearly define the ligaments structure and make it easier to diagnose them. Extraction of feature vectors is obtained by analysis of both anterior and posterior cruciate ligaments. This procedure is performed after the extraction process of both ligaments. In the first stage in order to reduce the area of analysis a region of interest including cruciate ligaments (CL) is outlined in order to reduce the area of analysis. In this case, the fuzzy C-means algorithm with median modification helping to reduce blurred edges has been implemented. After finding the region of interest (ROI), the fuzzy connectedness procedure is performed. This procedure permits to extract the anterior and posterior cruciate ligament structures. In the last stage, on the basis of the extracted anterior and posterior cruciate ligament structures, 3-dimensional models of the anterior and posterior cruciate ligament are built and the feature vectors created. This methodology has been implemented in MATLAB and tested on clinical T1-weighted magnetic resonance imaging (MRI) slices of the knee joint. The 3D display is based on the Visualization Toolkit (VTK).

  6. [Identification of special quality eggs with NIR spectroscopy technology based on symbol entropy feature extraction method].

    Science.gov (United States)

    Zhao, Yong; Hong, Wen-Xue

    2011-11-01

    Fast, nondestructive and accurate identification of special quality eggs is an urgent problem. The present paper proposed a new feature extraction method based on symbol entropy to identify near infrared spectroscopy of special quality eggs. The authors selected normal eggs, free range eggs, selenium-enriched eggs and zinc-enriched eggs as research objects and measured the near-infrared diffuse reflectance spectra in the range of 12 000-4 000 cm(-1). Raw spectra were symbolically represented with aggregation approximation algorithm and symbolic entropy was extracted as feature vector. An error-correcting output codes multiclass support vector machine classifier was designed to identify the spectrum. Symbolic entropy feature is robust when parameter changed and the highest recognition rate reaches up to 100%. The results show that the identification method of special quality eggs using near-infrared is feasible and the symbol entropy can be used as a new feature extraction method of near-infrared spectra.

  7. METHOD TO EXTRACT BLEND SURFACE FEATURE IN REVERSE ENGINEERING

    Institute of Scientific and Technical Information of China (English)

    Lü Zhen; Ke Yinglin; Sun Qing; Kelvin W; Huang Xiaoping

    2003-01-01

    A new method of extraction of blend surface feature is presented. It contains two steps: segmentation and recovery of parametric representation of the blend. The segmentation separates the points in the blend region from the rest of the input point cloud with the processes of sampling point data, estimation of local surface curvature properties and comparison of maximum curvature values. The recovery of parametric representation generates a set of profile curves by marching throughout the blend and fitting cylinders. Compared with the existing approaches of blend surface feature extraction, the proposed method reduces the requirement of user interaction and is capable of extracting blend surface with either constant radius or variable radius. Application examples are presented to verify the proposed method.

  8. Feature selection with neighborhood entropy-based cooperative game theory.

    Science.gov (United States)

    Zeng, Kai; She, Kun; Niu, Xinzheng

    2014-01-01

    Feature selection plays an important role in machine learning and data mining. In recent years, various feature measurements have been proposed to select significant features from high-dimensional datasets. However, most traditional feature selection methods will ignore some features which have strong classification ability as a group but are weak as individuals. To deal with this problem, we redefine the redundancy, interdependence, and independence of features by using neighborhood entropy. Then the neighborhood entropy-based feature contribution is proposed under the framework of cooperative game. The evaluative criteria of features can be formalized as the product of contribution and other classical feature measures. Finally, the proposed method is tested on several UCI datasets. The results show that neighborhood entropy-based cooperative game theory model (NECGT) yield better performance than classical ones.

  9. SPEECH/MUSIC CLASSIFICATION USING WAVELET BASED FEATURE EXTRACTION TECHNIQUES

    Directory of Open Access Journals (Sweden)

    Thiruvengatanadhan Ramalingam

    2014-01-01

    Full Text Available Audio classification serves as the fundamental step towards the rapid growth in audio data volume. Due to the increasing size of the multimedia sources speech and music classification is one of the most important issues for multimedia information retrieval. In this work a speech/music discrimination system is developed which utilizes the Discrete Wavelet Transform (DWT as the acoustic feature. Multi resolution analysis is the most significant statistical way to extract the features from the input signal and in this study, a method is deployed to model the extracted wavelet feature. Support Vector Machines (SVM are based on the principle of structural risk minimization. SVM is applied to classify audio into their classes namely speech and music, by learning from training data. Then the proposed method extends the application of Gaussian Mixture Models (GMM to estimate the probability density function using maximum likelihood decision methods. The system shows significant results with an accuracy of 94.5%.

  10. Feature extraction from slice data for reverse engineering

    Institute of Scientific and Technical Information of China (English)

    ZHANG Yingjie; LU Shangning

    2007-01-01

    A new approach to feature extraction for slice data points is presented. The reconstruction of objects is performed as follows. First, all contours in each slice are extracted by contour tracing algorithms. Then the data points on the contours are analyzed, and the curve segments of the contours are divided into three categories: straight lines, conic curves and B-spline curves. The curve fitting methods are applied for each curve segment to remove the unwanted points with pre-determined tolerance. Finally, the features, which consist of the object and connection relations among them, are founded by matching the corresponding contours in adjacent slices, and 3D models are reconstructed based on the features. The proposed approach has been implemented in OpenGL, and the feasibility of the proposed method has been verified by several cases.

  11. Advancing Affect Modeling via Preference Learning and Unsupervised Feature Extraction

    DEFF Research Database (Denmark)

    Martínez, Héctor Pérez

    over the other examined methods. The second challenge addressed in this thesis refers to the extraction of relevant information from physiological modalities. Deep learning is proposed as an automatic approach to extract input features for models of affect from physiological signals. Experiments...... difficulties, ordinal reports such as rankings and ratings can yield more reliable affect annotations than alternative tools. This thesis explores preference learning methods to automatically learn computational models from ordinal annotations of affect. In particular, an extensive collection of training...... the complexity of hand-crafting feature extractors that combine information across dissimilar modalities of input. Frequent sequence mining is presented as a method to learn feature extractors that fuse physiological and contextual information. This method is evaluated in a game-based dataset and compared...

  12. Features Extraction for Object Detection Based on Interest Point

    Directory of Open Access Journals (Sweden)

    Amin Mohamed Ahsan

    2013-05-01

    Full Text Available In computer vision, object detection is an essential process for further processes such as object tracking, analyzing and so on. In the same context, extraction features play important role to detect the object correctly. In this paper we present a method to extract local features based on interest point which is used to detect key-points within an image, then, compute histogram of gradient (HOG for the region surround that point. Proposed method used speed-up robust feature (SURF method as interest point detector and exclude the descriptor. The new descriptor is computed by using HOG method. The proposed method got advantages of both mentioned methods. To evaluate the proposed method, we used well-known dataset which is Caltech101. The initial result is encouraging in spite of using a small data for training.

  13. Feature Extraction based Face Recognition, Gender and Age Classification

    Directory of Open Access Journals (Sweden)

    Venugopal K R

    2010-01-01

    Full Text Available The face recognition system with large sets of training sets for personal identification normally attains good accuracy. In this paper, we proposed Feature Extraction based Face Recognition, Gender and Age Classification (FEBFRGAC algorithm with only small training sets and it yields good results even with one image per person. This process involves three stages: Pre-processing, Feature Extraction and Classification. The geometric features of facial images like eyes, nose, mouth etc. are located by using Canny edge operator and face recognition is performed. Based on the texture and shape information gender and age classification is done using Posteriori Class Probability and Artificial Neural Network respectively. It is observed that the face recognition is 100%, the gender and age classification is around 98% and 94% respectively.

  14. An ensemble approach for feature selection of Cyber Attack Dataset

    CERN Document Server

    Singh, Shailendra

    2009-01-01

    Feature selection is an indispensable preprocessing step when mining huge datasets that can significantly improve the overall system performance. Therefore in this paper we focus on a hybrid approach of feature selection. This method falls into two phases. The filter phase select the features with highest information gain and guides the initialization of search process for wrapper phase whose output the final feature subset. The final feature subsets are passed through the Knearest neighbor classifier for classification of attacks. The effectiveness of this algorithm is demonstrated on DARPA KDDCUP99 cyber attack dataset.

  15. Fuzzy - Rough Feature Selection With {\\Pi}- Membership Function For Mammogram Classification

    CERN Document Server

    Thangavel, K

    2012-01-01

    Breast cancer is the second leading cause for death among women and it is diagnosed with the help of mammograms. Oncologists are miserably failed in identifying the micro calcification at the early stage with the help of the mammogram visually. In order to improve the performance of the breast cancer screening, most of the researchers have proposed Computer Aided Diagnosis using image processing. In this study mammograms are preprocessed and features are extracted, then the abnormality is identified through the classification. If all the extracted features are used, most of the cases are misidentified. Hence feature selection procedure is sought. In this paper, Fuzzy-Rough feature selection with {\\pi} membership function is proposed. The selected features are used to classify the abnormalities with help of Ant-Miner and Weka tools. The experimental analysis shows that the proposed method improves the mammograms classification accuracy.

  16. Extracting invariable fault features of rotating machines with multi-ICA networks

    Institute of Scientific and Technical Information of China (English)

    焦卫东; 杨世锡; 吴昭同

    2003-01-01

    This paper proposes novel multi-layer neural networks based on Independent Component Analysis for feature extraction of fault modes. By the use of ICA, invariable features embedded in multi-channel vibration measurements under different operating conditions (rotating speed and/or load) can be captured together.Thus, stable MLP classifiers insensitive to the variation of operation conditions are constructed. The successful results achieved by selected experiments indicate great potential of ICA in health condition monitoring of rotating machines.

  17. Selective electromembrane extraction based on isoelectric point

    DEFF Research Database (Denmark)

    Huang, Chuixiu; Gjelstad, Astrid; Pedersen-Bjergaard, Stig

    2015-01-01

    For the first time, selective isolation of a target peptide based on the isoelectric point (pI) was achieved using a two-step electromembrane extraction (EME) approach with a thin flat membrane-based EME device. In this approach, step #1 was an extraction process, where both the target peptide...... angiotensin II antipeptide (AT2 AP, pI=5.13) and the matrix peptides (pI>5.13) angiotensin II (AT2), neurotensin (NT), angiotensin I (AT1) and leu-enkephalin (L-Enke) were all extracted as net positive species from the sample (pH 3.50), through a supported liquid membrane (SLM) of 1-nonanol diluted with 2......, and the target remained in the acceptor solution. The acceptor solution pH, the SLM composition, the extraction voltage, and the extraction time during the clean-up process (step #2) were important factors influencing the separation performance. An acceptor solution pH of 5.25 for the clean-up process slightly...

  18. Feature extraction and classification algorithms for high dimensional data

    Science.gov (United States)

    Lee, Chulhee; Landgrebe, David

    1993-01-01

    Feature extraction and classification algorithms for high dimensional data are investigated. Developments with regard to sensors for Earth observation are moving in the direction of providing much higher dimensional multispectral imagery than is now possible. In analyzing such high dimensional data, processing time becomes an important factor. With large increases in dimensionality and the number of classes, processing time will increase significantly. To address this problem, a multistage classification scheme is proposed which reduces the processing time substantially by eliminating unlikely classes from further consideration at each stage. Several truncation criteria are developed and the relationship between thresholds and the error caused by the truncation is investigated. Next an approach to feature extraction for classification is proposed based directly on the decision boundaries. It is shown that all the features needed for classification can be extracted from decision boundaries. A characteristic of the proposed method arises by noting that only a portion of the decision boundary is effective in discriminating between classes, and the concept of the effective decision boundary is introduced. The proposed feature extraction algorithm has several desirable properties: it predicts the minimum number of features necessary to achieve the same classification accuracy as in the original space for a given pattern recognition problem; and it finds the necessary feature vectors. The proposed algorithm does not deteriorate under the circumstances of equal means or equal covariances as some previous algorithms do. In addition, the decision boundary feature extraction algorithm can be used both for parametric and non-parametric classifiers. Finally, some problems encountered in analyzing high dimensional data are studied and possible solutions are proposed. First, the increased importance of the second order statistics in analyzing high dimensional data is recognized

  19. Geochemical dynamics in selected Yellowstone hydrothermal features

    Science.gov (United States)

    Druschel, G.; Kamyshny, A.; Findlay, A.; Nuzzio, D.

    2010-12-01

    Yellowstone National Park has a wide diversity of thermal features, and includes springs with a range of pH conditions that significantly impact sulfur speciation. We have utilized a combination of voltammetric and spectroscopic techniques to characterize the intermediate sulfur chemistry of Cinder Pool, Evening Primrose, Ojo Caliente, Frying Pan, Azure, and Dragon thermal springs. These measurements additionally have demonstrated the geochemical dynamics inherent in these systems; significant variability in chemical speciation occur in many of these thermal features due to changes in gas supply rates, fluid discharge rates, and thermal differences that occur on second time scales. The dynamics of the geochemical settings shown may significantly impact how microorganisms interact with the sulfur forms in these systems.

  20. A New Feature Selection Method for Text Clustering

    Institute of Scientific and Technical Information of China (English)

    XU Junling; XU Baowen; ZHANG Weifeng; CUI Zifeng; ZHANG Wei

    2007-01-01

    Feature selection methods have been successfully applied to text categorization but seldom applied to text clustering due to the unavailability of class label information. In this paper, a new feature selection method for text clustering based on expectation maximization and cluster validity is proposed. It uses supervised feature selection method on the intermediate clustering result which is generated during iterative clustering to do feature selection for text clustering; meanwhile, the Davies-Bouldin's index is used to evaluate the intermediate feature subsets indirectly. Then feature subsets are selected according to the curve of the DaviesBouldin's index. Experiment is carried out on several popular datasets and the results show the advantages of the proposed method.

  1. Facial Feature Extraction Using Frequency Map Series in PCNN

    Directory of Open Access Journals (Sweden)

    Rencan Nie

    2016-01-01

    Full Text Available Pulse coupled neural network (PCNN has been widely used in image processing. The 3D binary map series (BMS generated by PCNN effectively describes image feature information such as edges and regional distribution, so BMS can be treated as the basis of extracting 1D oscillation time series (OTS for an image. However, the traditional methods using BMS did not consider the correlation of the binary sequence in BMS and the space structure for every map. By further processing for BMS, a novel facial feature extraction method is proposed. Firstly, consider the correlation among maps in BMS; a method is put forward to transform BMS into frequency map series (FMS, and the method lessens the influence of noncontinuous feature regions in binary images on OTS-BMS. Then, by computing the 2D entropy for every map in FMS, the 3D FMS is transformed into 1D OTS (OTS-FMS, which has good geometry invariance for the facial image, and contains the space structure information of the image. Finally, by analyzing the OTS-FMS, the standard Euclidean distance is used to measure the distances for OTS-FMS. Experimental results verify the effectiveness of OTS-FMS in facial recognition, and it shows better recognition performance than other feature extraction methods.

  2. Facial Feature Extraction Method Based on Coefficients of Variances

    Institute of Scientific and Technical Information of China (English)

    Feng-Xi Song; David Zhang; Cai-Kou Chen; Jing-Yu Yang

    2007-01-01

    Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are two popular feature ex- traction techniques in statistical pattern recognition field. Due to small sample size problem LDA cannot be directly applied to appearance-based face recognition tasks. As a consequence, a lot of LDA-based facial feature extraction techniques are proposed to deal with the problem one after the other. Nullspace Method is one of the most effective methods among them. The Nullspace Method tries to find a set of discriminant vectors which maximize the between-class scatter in the null space of the within-class scatter matrix. The calculation of its discriminant vectors will involve performing singular value decomposition on a high-dimensional matrix. It is generally memory- and time-consuming. Borrowing the key idea in Nullspace method and the concept of coefficient of variance in statistical analysis we present a novel facial feature extraction method, i.e., Discriminant based on Coefficient of Variance (DCV) in this paper. Experimental results performed on the FERET and AR face image databases demonstrate that DCV is a promising technique in comparison with Eigenfaces, Nullspace Method, and other state-of-the-art facial feature extraction methods.

  3. The Hybrid KICA-GDA-LSSVM Method Research on Rolling Bearing Fault Feature Extraction and Classification

    Directory of Open Access Journals (Sweden)

    Jiyong Li

    2015-01-01

    Full Text Available Rolling element bearings are widely used in high-speed rotating machinery; thus proper monitoring and fault diagnosis procedure to avoid major machine failures is necessary. As feature extraction and classification based on vibration signals are important in condition monitoring technique, and superfluous features may degrade the classification performance, it is needed to extract independent features, so LSSVM (least square support vector machine based on hybrid KICA-GDA (kernel independent component analysis-generalized discriminate analysis is presented in this study. A new method named sensitive subband feature set design (SSFD based on wavelet packet is also presented; using proposed variance differential spectrum method, the sensitive subbands are selected. Firstly, independent features are obtained by KICA; the feature redundancy is reduced. Secondly, feature dimension is reduced by GDA. Finally, the projected feature is classified by LSSVM. The whole paper aims to classify the feature vectors extracted from the time series and magnitude of spectral analysis and to discriminate the state of the rolling element bearings by virtue of multiclass LSSVM. Experimental results from two different fault-seeded bearing tests show good performance of the proposed method.

  4. Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features

    Science.gov (United States)

    Shi, Bibo; Grimm, Lars J.; Mazurowski, Maciej A.; Marks, Jeffrey R.; King, Lorraine M.; Maley, Carlo C.; Hwang, E. Shelley; Lo, Joseph Y.

    2017-03-01

    Predicting the risk of occult invasive disease in ductal carcinoma in situ (DCIS) is an important task to help address the overdiagnosis and overtreatment problems associated with breast cancer. In this work, we investigated the feasibility of using computer-extracted mammographic features to predict occult invasive disease in patients with biopsy proven DCIS. We proposed a computer-vision algorithm based approach to extract mammographic features from magnification views of full field digital mammography (FFDM) for patients with DCIS. After an expert breast radiologist provided a region of interest (ROI) mask for the DCIS lesion, the proposed approach is able to segment individual microcalcifications (MCs), detect the boundary of the MC cluster (MCC), and extract 113 mammographic features from MCs and MCC within the ROI. In this study, we extracted mammographic features from 99 patients with DCIS (74 pure DCIS; 25 DCIS plus invasive disease). The predictive power of the mammographic features was demonstrated through binary classifications between pure DCIS and DCIS with invasive disease using linear discriminant analysis (LDA). Before classification, the minimum redundancy Maximum Relevance (mRMR) feature selection method was first applied to choose subsets of useful features. The generalization performance was assessed using Leave-One-Out Cross-Validation and Receiver Operating Characteristic (ROC) curve analysis. Using the computer-extracted mammographic features, the proposed model was able to distinguish DCIS with invasive disease from pure DCIS, with an average classification performance of AUC = 0.61 +/- 0.05. Overall, the proposed computer-extracted mammographic features are promising for predicting occult invasive disease in DCIS.

  5. A Method of Road Extraction from High-resolution Remote Sensing Images Based on Shape Features

    Directory of Open Access Journals (Sweden)

    LEI Xiaoqi

    2016-02-01

    Full Text Available Road extraction from high-resolution remote sensing image is an important and difficult task.Since remote sensing images include complicated information,the methods that extract roads by spectral,texture and linear features have certain limitations.Also,many methods need human-intervention to get the road seeds(semi-automatic extraction,which have the great human-dependence and low efficiency.The road-extraction method,which uses the image segmentation based on principle of local gray consistency and integration shape features,is proposed in this paper.Firstly,the image is segmented,and then the linear and curve roads are obtained by using several object shape features,so the method that just only extract linear roads are rectified.Secondly,the step of road extraction is carried out based on the region growth,the road seeds are automatic selected and the road network is extracted.Finally,the extracted roads are regulated by combining the edge information.In experiments,the images that including the better gray uniform of road and the worse illuminated of road surface were chosen,and the results prove that the method of this study is promising.

  6. Aptamers overview: selection, features and applications.

    Science.gov (United States)

    Hernandez, Luiza I; Machado, Isabel; Schafer, Thomas; Hernandez, Frank J

    2015-01-01

    Apatamer technology has been around for a quarter of a century and the field had matured enough to start seeing real applications, especially in the medical field. Since their discovery, aptamers rapidly emerged as key players in many fields, such as diagnostics, drug discovery, food science, drug delivery and therapeutics. Because of their synthetic nature, aptamers are evolving at an exponential rate gaining from the newest advances in chemistry, nanotechnology, biology and medicine. This review is meant to give an overview of the aptamer field, by including general aspects of aptamer identification and applications as well as highlighting certain features that contribute to their quick deployment in the biomedical field.

  7. Bayesian feature selection to estimate customer survival

    OpenAIRE

    Figini, Silvia; Giudici, Paolo; Brooks, S P

    2006-01-01

    We consider the problem of estimating the lifetime value of customers, when a large number of features are present in the data. In order to measure lifetime value we use survival analysis models to estimate customer tenure. In such a context, a number of classical modelling challenges arise. We will show how our proposed Bayesian methods perform, and compare it with classical churn models on a real case study. More specifically, based on data from a media service company, our aim will be to p...

  8. Application of Texture Characteristics for Urban Feature Extraction from Optical Satellite Images

    Directory of Open Access Journals (Sweden)

    D.Shanmukha Rao

    2014-12-01

    Full Text Available Quest of fool proof methods for extracting various urban features from high resolution satellite imagery with minimal human intervention has resulted in developing texture based algorithms. In view of the fact that the textural properties of images provide valuable information for discrimination purposes, it is appropriate to employ texture based algorithms for feature extraction. The Gray Level Co-occurrence Matrix (GLCM method represents a highly efficient technique of extracting second order statistical texture features. The various urban features can be distinguished based on a set of features viz. energy, entropy, homogeneity etc. that characterize different aspects of the underlying texture. As a preliminary step, notable numbers of regions of interests of the urban feature and contrast locations are identified visually. After calculating Gray Level Co-occurrence matrices of these selected regions, the aforementioned texture features are computed. These features can be used to shape a high-dimensional feature vector to carry out content based retrieval. The insignificant features are eliminated to reduce the dimensionality of the feature vector by executing Principal Components Analysis (PCA. The selection of the discriminating features is also aided by the value of Jeffreys-Matusita (JM distance which serves as a measure of class separability Feature identification is then carried out by computing these chosen feature vectors for every pixel of the entire image and comparing it with their corresponding mean values. This helps in identifying and classifying the pixels corresponding to urban feature being extracted. To reduce the commission errors, various index values viz. Soil Adjusted Vegetation Index (SAVI, Normalized Difference Vegetation Index (NDVI and Normalized Difference Water Index (NDWI are assessed for each pixel. The extracted output is then median filtered to isolate the feature of interest after removing the salt and pepper

  9. FACE RECOGNITION USING FEATURE EXTRACTION AND NEURO-FUZZY TECHNIQUES

    Directory of Open Access Journals (Sweden)

    Ritesh Vyas

    2012-09-01

    Full Text Available Face is a primary focus of attention in social intercourse, playing a major role in conveying identity and emotion. The human ability to recognize faces is remarkable. People can recognize thousands of faces learned throughout their lifetime and identify familiar faces at a glance even after years of separation. This skill is quite robust, despite large changes in the visual stimulus due to viewing conditions, expression, aging, and distractions such as glasses, beards or changes in hair style. In this work, a system is designed to recognize human faces depending on their facial features. Also to reveal the outline of the face, eyes and nose, edge detection technique has been used. Facial features are extracted in the form of distance between important feature points. After normalization, these feature vectors are learned by artificial neural network and used to recognize facial image.

  10. A feature selection method based on multiple kernel learning with expression profiles of different types.

    Science.gov (United States)

    Du, Wei; Cao, Zhongbo; Song, Tianci; Li, Ying; Liang, Yanchun

    2017-01-01

    With the development of high-throughput technology, the researchers can acquire large number of expression data with different types from several public databases. Because most of these data have small number of samples and hundreds or thousands features, how to extract informative features from expression data effectively and robustly using feature selection technique is challenging and crucial. So far, a mass of many feature selection approaches have been proposed and applied to analyse expression data of different types. However, most of these methods only are limited to measure the performances on one single type of expression data by accuracy or error rate of classification. In this article, we propose a hybrid feature selection method based on Multiple Kernel Learning (MKL) and evaluate the performance on expression datasets of different types. Firstly, the relevance between features and classifying samples is measured by using the optimizing function of MKL. In this step, an iterative gradient descent process is used to perform the optimization both on the parameters of Support Vector Machine (SVM) and kernel confidence. Then, a set of relevant features is selected by sorting the optimizing function of each feature. Furthermore, we apply an embedded scheme of forward selection to detect the compact feature subsets from the relevant feature set. We not only compare the classification accuracy with other methods, but also compare the stability, similarity and consistency of different algorithms. The proposed method has a satisfactory capability of feature selection for analysing expression datasets of different types using different performance measurements.

  11. Neural Gen Feature Selection for Supervised Learning Classifier

    Directory of Open Access Journals (Sweden)

    Mohammed Hasan Abdulameer

    2014-04-01

    Full Text Available Face recognition has recently received significant attention, especially during the past few years. Many face recognition techniques were developed such as PSO-SVM and LDA-SVM However, inefficient features in the face recognition may lead to inadequate in the recognition results. Hence, a new face recognition system based on Genetic Algorithm and FFBNN technique is proposed. Our proposed face recognition system initially performs the feature extraction and these optimal features are promoted to the recognition process. In the feature extraction, the optimal features are extracted from the face image database by Genetic Algorithm (GA with FFBNN and the computed optimal features are given to the FFBNN technique to carry out the training and testing process. The optimal features from the feature database are fed to the FFBNN for accomplishing the training process. The well trained FFBNN with the optimal features provide the recognition result. The optimal features in FFBNN by GA efficiently perform the face recognition process. The human face dataset called YALE is utilized to analyze the performance of our proposed GA-FFNN technique and also this GA-FFBNN is compared with standard SVM and PSO-SVM techniques.

  12. Automatic feature extraction in large fusion databases by using deep learning approach

    Energy Technology Data Exchange (ETDEWEB)

    Farias, Gonzalo, E-mail: gonzalo.farias@ucv.cl [Pontificia Universidad Católica de Valparaíso, Valparaíso (Chile); Dormido-Canto, Sebastián [Departamento de Informática y Automática, UNED, Madrid (Spain); Vega, Jesús; Rattá, Giuseppe [Asociación EURATOM/CIEMAT Para Fusión, CIEMAT, Madrid (Spain); Vargas, Héctor; Hermosilla, Gabriel; Alfaro, Luis; Valencia, Agustín [Pontificia Universidad Católica de Valparaíso, Valparaíso (Chile)

    2016-11-15

    Highlights: • Feature extraction is a very critical stage in any machine learning algorithm. • The problem dimensionality can be reduced enormously when selecting suitable attributes. • Despite the importance of feature extraction, the process is commonly done manually by trial and error. • Fortunately, recent advances in deep learning approach have proposed an encouraging way to find a good feature representation automatically. • In this article, deep learning is applied to the TJ-II fusion database to get more robust and accurate classifiers in comparison to previous work. - Abstract: Feature extraction is one of the most important machine learning issues. Finding suitable attributes of datasets can enormously reduce the dimensionality of the input space, and from a computational point of view can help all of the following steps of pattern recognition problems, such as classification or information retrieval. However, the feature extraction step is usually performed manually. Moreover, depending on the type of data, we can face a wide range of methods to extract features. In this sense, the process to select appropriate techniques normally takes a long time. This work describes the use of recent advances in deep learning approach in order to find a good feature representation automatically. The implementation of a special neural network called sparse autoencoder and its application to two classification problems of the TJ-II fusion database is shown in detail. Results have shown that it is possible to get robust classifiers with a high successful rate, in spite of the fact that the feature space is reduced to less than 0.02% from the original one.

  13. Optimized Feature Extraction for Temperature-Modulated Gas Sensors

    Directory of Open Access Journals (Sweden)

    Alexander Vergara

    2009-01-01

    Full Text Available One of the most serious limitations to the practical utilization of solid-state gas sensors is the drift of their signal. Even if drift is rooted in the chemical and physical processes occurring in the sensor, improved signal processing is generally considered as a methodology to increase sensors stability. Several studies evidenced the augmented stability of time variable signals elicited by the modulation of either the gas concentration or the operating temperature. Furthermore, when time-variable signals are used, the extraction of features can be accomplished in shorter time with respect to the time necessary to calculate the usual features defined in steady-state conditions. In this paper, we discuss the stability properties of distinct dynamic features using an array of metal oxide semiconductors gas sensors whose working temperature is modulated with optimized multisinusoidal signals. Experiments were aimed at measuring the dispersion of sensors features in repeated sequences of a limited number of experimental conditions. Results evidenced that the features extracted during the temperature modulation reduce the multidimensional data dispersion among repeated measurements. In particular, the Energy Signal Vector provided an almost constant classification rate along the time with respect to the temperature modulation.

  14. FEATURE SELECTION USING GENETIC ALGORITHMS FOR HANDWRITTEN CHARACTER RECOGNITION

    NARCIS (Netherlands)

    Kim, G.; Kim, S.

    2004-01-01

    A feature selection method using genetic algorithms which are suitable means for selecting appropriate set of features from ones with huge dimension is proposed. SGA (Simple Genetic Algorithm) and its modified methods are applied to improve the recognition speed as well as the recognition accuracy.

  15. An Approach for Optimal Feature Subset Selection using a New Term Weighting Scheme and Mutual Information

    Directory of Open Access Journals (Sweden)

    Shine N Das

    2011-01-01

    Full Text Available With the development of the web, large numbers of documents are available on the Internet and they are growing drastically day by day. Hence automatic text categorization becomes more and more important for dealing with massive data. However the major problem of document categorization is the high dimensionality of feature space.  The measures to decrease the feature dimension under not decreasing recognition effect are called the problems of feature optimum extraction or selection. Dealing with reduced relevant feature set can be more efficient and effective. The objective of feature selection is to find a subset of features that have all characteristics of the full features set. Instead Dependency among features is also important for classification. During past years, various metrics have been proposed to measure the dependency among different features. A popular approach to realize dependency is maximal relevance feature selection: selecting the features with the highest relevance to the target class. A new feature weighting scheme, we proposed have got a tremendous improvements in dimensionality reduction of the feature space. The experimental results clearly show that this integrated method works far better than the others.

  16. High Dimensional Data Clustering Using Fast Cluster Based Feature Selection

    Directory of Open Access Journals (Sweden)

    Karthikeyan.P

    2014-03-01

    Full Text Available Feature selection involves identifying a subset of the most useful features that produces compatible results as the original entire set of features. A feature selection algorithm may be evaluated from both the efficiency and effectiveness points of view. While the efficiency concerns the time required to find a subset of features, the effectiveness is related to the quality of the subset of features. Based on these criteria, a fast clustering-based feature selection algorithm (FAST is proposed and experimentally evaluated in this paper. The FAST algorithm works in two steps. In the first step, features are divided into clusters by using graph-theoretic clustering methods. In the second step, the most representative feature that is strongly related to target classes is selected from each cluster to form a subset of features. Features in different clusters are relatively independent; the clustering-based strategy of FAST has a high probability of producing a subset of useful and independent features. To ensure the efficiency of FAST, we adopt the efficient minimum-spanning tree (MST using the Kruskal‟s Algorithm clustering method. The efficiency and effectiveness of the FAST algorithm are evaluated through an empirical study. Index Terms—

  17. Gradient Algorithm on Stiefel Manifold and Application in Feature Extraction

    Directory of Open Access Journals (Sweden)

    Zhang Jian-jun

    2013-09-01

    Full Text Available To improve the computational efficiency of system feature extraction, reduce the occupied memory space, and simplify the program design, a modified gradient descent method on Stiefel manifold is proposed based on the optimization algorithm of geometry frame on the Riemann manifold. Different geodesic calculation formulas are used for different scenarios. A polynomial is also used to lie close to the geodesic equations. JiuZhaoQin-Horner polynomial algorithm and the strategies of line-searching technique and change of the step size of iteration are also adopted. The gradient descent algorithm on Stiefel manifold applied in Principal Component Analysis (PCA is discussed in detail as an example of system feature extraction. Theoretical analysis and simulation experiments show that the new method can achieve superior performance in both the convergence rate and calculation efficiency while ensuring the unitary column orthogonality. In addition, it is easier to implement by software or hardware.

  18. A Review on Feature Extraction Techniques in Face Recognition

    Directory of Open Access Journals (Sweden)

    Rahimeh Rouhi

    2013-01-01

    Full Text Available Face recognition systems due to their significant application in the security scopes, have been of greatimportance in recent years. The existence of an exact balance between the computing cost, robustness andtheir ability for face recognition is an important characteristic for such systems. Besides, trying to designthe systems performing under different conditions (e.g. illumination, variation of pose, different expressionand etc. is a challenging problem in the feature extraction of the face recognition. As feature extraction isan important step in the face recognition operation, in the present study four techniques of featureextraction in the face recognition were reviewed, subsequently comparable results were presented, andthen the advantages and the disadvantages of these methods were discussed.

  19. Modification of evidence theory based on feature extraction

    Institute of Scientific and Technical Information of China (English)

    DU Feng; SHI Wen-kang; DENG Yong

    2005-01-01

    Although evidence theory has been widely used in information fusion due to its effectiveness of uncertainty reasoning, the classical DS evidence theory involves counter-intuitive behaviors when high conflict information exists. Many modification methods have been developed which can be classified into the following two kinds of ideas, either modifying the combination rules or modifying the evidence sources. In order to make the modification more reasonable and more effective, this paper gives a thorough analysis of some typical existing modification methods firstly, and then extracts the intrinsic feature of the evidence sources by using evidence distance theory. Based on the extracted features, two modified plans of evidence theory according to the corresponding modification ideas have been proposed. The results of numerical examples prove the good performance of the plans when combining evidence sources with high conflict information.

  20. Emotional textile image classification based on cross-domain convolutional sparse autoencoders with feature selection

    Science.gov (United States)

    Li, Zuhe; Fan, Yangyu; Liu, Weihua; Yu, Zeqi; Wang, Fengqin

    2017-01-01

    We aim to apply sparse autoencoder-based unsupervised feature learning to emotional semantic analysis for textile images. To tackle the problem of limited training data, we present a cross-domain feature learning scheme for emotional textile image classification using convolutional autoencoders. We further propose a correlation-analysis-based feature selection method for the weights learned by sparse autoencoders to reduce the number of features extracted from large size images. First, we randomly collect image patches on an unlabeled image dataset in the source domain and learn local features with a sparse autoencoder. We then conduct feature selection according to the correlation between different weight vectors corresponding to the autoencoder's hidden units. We finally adopt a convolutional neural network including a pooling layer to obtain global feature activations of textile images in the target domain and send these global feature vectors into logistic regression models for emotional image classification. The cross-domain unsupervised feature learning method achieves 65% to 78% average accuracy in the cross-validation experiments corresponding to eight emotional categories and performs better than conventional methods. Feature selection can reduce the computational cost of global feature extraction by about 50% while improving classification performance.

  1. Eigenvalue-weighting and feature selection for computer-aided polyp detection in CT colonography

    Science.gov (United States)

    Zhu, Hongbin; Wang, Su; Fan, Yi; Lu, Hongbing; Liang, Zhengrong

    2010-03-01

    With the development of computer-aided polyp detection towards virtual colonoscopy screening, the trade-off between detection sensitivity and specificity has gained increasing attention. An optimum detection, with least number of false positives and highest true positive rate, is desirable and involves interdisciplinary knowledge, such as feature extraction, feature selection as well as machine learning. Toward that goal, various geometrical and textural features, associated with each suspicious polyp candidate, have been individually extracted and stacked together as a feature vector. However, directly inputting these high-dimensional feature vectors into a learning machine, e.g., neural network, for polyp detection may introduce redundant information due to feature correlation and induce the curse of dimensionality. In this paper, we explored an indispensable building block of computer-aided polyp detection, i.e., principal component analysis (PCA)-weighted feature selection for neural network classifier of true and false positives. The major concepts proposed in this paper include (1) the use of PCA to reduce the feature correlation, (2) the scheme of adaptively weighting each principal component (PC) by the associated eigenvalue, and (3) the selection of feature combinations via the genetic algorithm. As such, the eigenvalue is also taken as part of the characterizing feature, and the necessary number of features can be exposed to mitigate the curse of dimensionality. Learned and tested by radial basis neural network, the proposed computer-aided polyp detection has achieved 95% sensitivity at a cost of average 2.99 false positives per polyp.

  2. FEATURES AND GROUND AUTOMATIC EXTRACTION FROM AIRBORNE LIDAR DATA

    OpenAIRE

    D. Costantino; M. G. Angelini

    2012-01-01

    The aim of the research has been the developing and implementing an algorithm for automated extraction of features from LIDAR scenes with varying terrain and coverage types. This applies the moment of third order (Skweness) and fourth order (Kurtosis). While the first has been applied in order to produce an initial filtering and data classification, the second, through the introduction of the weights of the measures, provided the desired results, which is a finer classification and l...

  3. Extracting BI-RADS Features from Portuguese Clinical Texts

    OpenAIRE

    Nassif, Houssam; Cunha, Filipe; Moreira, Inês C.; Cruz-Correia, Ricardo; Sousa, Eliana; Page, David; Burnside, Elizabeth; Dutra, Inês

    2012-01-01

    In this work we build the first BI-RADS parser for Portuguese free texts, modeled after existing approaches to extract BI-RADS features from English medical records. Our concept finder uses a semantic grammar based on the BIRADS lexicon and on iterative transferred expert knowledge. We compare the performance of our algorithm to manual annotation by a specialist in mammography. Our results show that our parser’s performance is comparable to the manual method.

  4. Extracting BI-RADS Features from Portuguese Clinical Texts

    OpenAIRE

    Nassif, Houssam; Cunha, Filipe; Moreira, Inês C; Cruz-Correia, Ricardo; Sousa, Eliana; Page, David; Burnside, Elizabeth; Dutra, Inês

    2012-01-01

    In this work we build the first BI-RADS parser for Portuguese free texts, modeled after existing approaches to extract BI-RADS features from English medical records. Our concept finder uses a semantic grammar based on the BIRADS lexicon and on iterative transferred expert knowledge. We compare the performance of our algorithm to manual annotation by a specialist in mammography. Our results show that our parser’s performance is comparable to the manual method.

  5. Automated Feature Extraction of Foredune Morphology from Terrestrial Lidar Data

    Science.gov (United States)

    Spore, N.; Brodie, K. L.; Swann, C.

    2014-12-01

    Foredune morphology is often described in storm impact prediction models using the elevation of the dune crest and dune toe and compared with maximum runup elevations to categorize the storm impact and predicted responses. However, these parameters do not account for other foredune features that may make them more or less erodible, such as alongshore variations in morphology, vegetation coverage, or compaction. The goal of this work is to identify other descriptive features that can be extracted from terrestrial lidar data that may affect the rate of dune erosion under wave attack. Daily, mobile-terrestrial lidar surveys were conducted during a 6-day nor'easter (Hs = 4 m in 6 m water depth) along 20km of coastline near Duck, North Carolina which encompassed a variety of foredune forms in close proximity to each other. This abstract will focus on the tools developed for the automated extraction of the morphological features from terrestrial lidar data, while the response of the dune will be presented by Brodie and Spore as an accompanying abstract. Raw point cloud data can be dense and is often under-utilized due to time and personnel constraints required for analysis, since many algorithms are not fully automated. In our approach, the point cloud is first projected into a local coordinate system aligned with the coastline, and then bare earth points are interpolated onto a rectilinear 0.5 m grid creating a high resolution digital elevation model. The surface is analyzed by identifying features along each cross-shore transect. Surface curvature is used to identify the position of the dune toe, and then beach and berm morphology is extracted shoreward of the dune toe, and foredune morphology is extracted landward of the dune toe. Changes in, and magnitudes of, cross-shore slope, curvature, and surface roughness are used to describe the foredune face and each cross-shore transect is then classified using its pre-storm morphology for storm-response analysis.

  6. Feature extraction using convolutional neural network for classifying breast density in mammographic images

    Science.gov (United States)

    Thomaz, Ricardo L.; Carneiro, Pedro C.; Patrocinio, Ana C.

    2017-03-01

    Breast cancer is the leading cause of death for women in most countries. The high levels of mortality relate mostly to late diagnosis and to the direct proportionally relationship between breast density and breast cancer development. Therefore, the correct assessment of breast density is important to provide better screening for higher risk patients. However, in modern digital mammography the discrimination among breast densities is highly complex due to increased contrast and visual information for all densities. Thus, a computational system for classifying breast density might be a useful tool for aiding medical staff. Several machine-learning algorithms are already capable of classifying small number of classes with good accuracy. However, machinelearning algorithms main constraint relates to the set of features extracted and used for classification. Although well-known feature extraction techniques might provide a good set of features, it is a complex task to select an initial set during design of a classifier. Thus, we propose feature extraction using a Convolutional Neural Network (CNN) for classifying breast density by a usual machine-learning classifier. We used 307 mammographic images downsampled to 260x200 pixels to train a CNN and extract features from a deep layer. After training, the activation of 8 neurons from a deep fully connected layer are extracted and used as features. Then, these features are feedforward to a single hidden layer neural network that is cross-validated using 10-folds to classify among four classes of breast density. The global accuracy of this method is 98.4%, presenting only 1.6% of misclassification. However, the small set of samples and memory constraints required the reuse of data in both CNN and MLP-NN, therefore overfitting might have influenced the results even though we cross-validated the network. Thus, although we presented a promising method for extracting features and classifying breast density, a greater database is

  7. Evaluation of Feature Selection Approaches for Urdu Text Categorization

    Directory of Open Access Journals (Sweden)

    Tehseen Zia

    2015-05-01

    Full Text Available Efficient feature selection is an important phase of designing an effective text categorization system. Various feature selection methods have been proposed for selecting dissimilar feature sets. It is often essential to evaluate that which method is more effective for a given task and what size of feature set is an effective model selection choice. Aim of this paper is to answer these questions for designing Urdu text categorization system. Five widely used feature selection methods were examined using six well-known classification algorithms: naive Bays (NB, k-nearest neighbor (KNN, support vector machines (SVM with linear, polynomial and radial basis kernels and decision tree (i.e. J48. The study was conducted over two test collections: EMILLE collection and a naive collection. We have observed that three feature selection methods i.e. information gain, Chi statistics, and symmetrical uncertain, have performed uniformly in most of the cases if not all. Moreover, we have found that no single feature selection method is best for all classifiers. While gain ratio out-performed others for naive Bays and J48, information gain has shown top performance for KNN and SVM with polynomial and radial basis kernels. Overall, linear SVM with any of feature selection methods including information gain, Chi statistics or symmetric uncertain methods is turned-out to be first choice across other combinations of classifiers and feature selection methods on moderate size naive collection. On the other hand, naive Bays with any of feature selection method have shown its advantage for a small sized EMILLE corpus.

  8. Features and Ground Automatic Extraction from Airborne LIDAR Data

    Science.gov (United States)

    Costantino, D.; Angelini, M. G.

    2011-09-01

    The aim of the research has been the developing and implementing an algorithm for automated extraction of features from LIDAR scenes with varying terrain and coverage types. This applies the moment of third order (Skweness) and fourth order (Kurtosis). While the first has been applied in order to produce an initial filtering and data classification, the second, through the introduction of the weights of the measures, provided the desired results, which is a finer classification and less noisy. The process has been carried out in Matlab but to reduce processing time, given the large data density, the analysis has been limited at a mobile window. It was, therefore, arranged to produce subscenes in order to covers the entire area. The performance of the algorithm, confirm its robustness and goodness of results. Employment of effective processing strategies to improve the automation is a key to the implementation of this algorithm. The results of this work will serve the increased demand of automation for 3D information extraction using remotely sensed large datasets. After obtaining the geometric features from LiDAR data, we want to complete the research creating an algorithm to vector features and extraction of the DTM.

  9. Automated feature extraction for 3-dimensional point clouds

    Science.gov (United States)

    Magruder, Lori A.; Leigh, Holly W.; Soderlund, Alexander; Clymer, Bradley; Baer, Jessica; Neuenschwander, Amy L.

    2016-05-01

    Light detection and ranging (LIDAR) technology offers the capability to rapidly capture high-resolution, 3-dimensional surface data with centimeter-level accuracy for a large variety of applications. Due to the foliage-penetrating properties of LIDAR systems, these geospatial data sets can detect ground surfaces beneath trees, enabling the production of highfidelity bare earth elevation models. Precise characterization of the ground surface allows for identification of terrain and non-terrain points within the point cloud, and facilitates further discernment between natural and man-made objects based solely on structural aspects and relative neighboring parameterizations. A framework is presented here for automated extraction of natural and man-made features that does not rely on coincident ortho-imagery or point RGB attributes. The TEXAS (Terrain EXtraction And Segmentation) algorithm is used first to generate a bare earth surface from a lidar survey, which is then used to classify points as terrain or non-terrain. Further classifications are assigned at the point level by leveraging local spatial information. Similarly classed points are then clustered together into regions to identify individual features. Descriptions of the spatial attributes of each region are generated, resulting in the identification of individual tree locations, forest extents, building footprints, and 3-dimensional building shapes, among others. Results of the fully-automated feature extraction algorithm are then compared to ground truth to assess completeness and accuracy of the methodology.

  10. Feature Extraction and Pattern Identification for Anemometer Condition Diagnosis

    Directory of Open Access Journals (Sweden)

    Longji Sun

    2012-01-01

    Full Text Available Cup anemometers are commonly used for wind speed measurement in the wind industry. Anemometer malfunctions lead to excessive errors in measurement and directly influence the wind energy development for a proposed wind farm site. This paper is focused on feature extraction and pattern identification to solve the anemometer condition diagnosis problem of the PHM 2011 Data Challenge Competition. Since the accuracy of anemometers can be severely affected by the environmental factors such as icing and the tubular tower itself, in order to distinguish the cause due to anemometer failures from these factors, our methodologies start with eliminating irregular data (outliers under the influence of environmental factors. For paired data, the relation between the relative wind speed difference and the wind direction is extracted as an important feature to reflect normal or abnormal behaviors of paired anemometers. Decisions regarding the condition of paired anemometers are made by comparing the features extracted from training and test data. For shear data, a power law model is fitted using the preprocessed and normalized data, and the sum of the squared residuals (SSR is used to measure the health of an array of anemometers. Decisions are made by comparing the SSRs of training and test data. The performance of our proposed methods is evaluated through the competition website. As a final result, our team ranked the second place overall in both student and professional categories in this competition.

  11. Motion feature extraction scheme for content-based video retrieval

    Science.gov (United States)

    Wu, Chuan; He, Yuwen; Zhao, Li; Zhong, Yuzhuo

    2001-12-01

    This paper proposes the extraction scheme of global motion and object trajectory in a video shot for content-based video retrieval. Motion is the key feature representing temporal information of videos. And it is more objective and consistent compared to other features such as color, texture, etc. Efficient motion feature extraction is an important step for content-based video retrieval. Some approaches have been taken to extract camera motion and motion activity in video sequences. When dealing with the problem of object tracking, algorithms are always proposed on the basis of known object region in the frames. In this paper, a whole picture of the motion information in the video shot has been achieved through analyzing motion of background and foreground respectively and automatically. 6-parameter affine model is utilized as the motion model of background motion, and a fast and robust global motion estimation algorithm is developed to estimate the parameters of the motion model. The object region is obtained by means of global motion compensation between two consecutive frames. Then the center of object region is calculated and tracked to get the object motion trajectory in the video sequence. Global motion and object trajectory are described with MPEG-7 parametric motion and motion trajectory descriptors and valid similar measures are defined for the two descriptors. Experimental results indicate that our proposed scheme is reliable and efficient.

  12. Evolutionary Feature Selection for Big Data Classification: A MapReduce Approach

    Directory of Open Access Journals (Sweden)

    Daniel Peralta

    2015-01-01

    Full Text Available Nowadays, many disciplines have to deal with big datasets that additionally involve a high number of features. Feature selection methods aim at eliminating noisy, redundant, or irrelevant features that may deteriorate the classification performance. However, traditional methods lack enough scalability to cope with datasets of millions of instances and extract successful results in a delimited time. This paper presents a feature selection algorithm based on evolutionary computation that uses the MapReduce paradigm to obtain subsets of features from big datasets. The algorithm decomposes the original dataset in blocks of instances to learn from them in the map phase; then, the reduce phase merges the obtained partial results into a final vector of feature weights, which allows a flexible application of the feature selection procedure using a threshold to determine the selected subset of features. The feature selection method is evaluated by using three well-known classifiers (SVM, Logistic Regression, and Naive Bayes implemented within the Spark framework to address big data problems. In the experiments, datasets up to 67 millions of instances and up to 2000 attributes have been managed, showing that this is a suitable framework to perform evolutionary feature selection, improving both the classification accuracy and its runtime when dealing with big data problems.

  13. Feature extraction through parallel Probabilistic Principal Component Analysis for heart disease diagnosis

    Science.gov (United States)

    Shah, Syed Muhammad Saqlain; Batool, Safeera; Khan, Imran; Ashraf, Muhammad Usman; Abbas, Syed Hussnain; Hussain, Syed Adnan

    2017-09-01

    Automatic diagnosis of human diseases are mostly achieved through decision support systems. The performance of these systems is mainly dependent on the selection of the most relevant features. This becomes harder when the dataset contains missing values for the different features. Probabilistic Principal Component Analysis (PPCA) has reputation to deal with the problem of missing values of attributes. This research presents a methodology which uses the results of medical tests as input, extracts a reduced dimensional feature subset and provides diagnosis of heart disease. The proposed methodology extracts high impact features in new projection by using Probabilistic Principal Component Analysis (PPCA). PPCA extracts projection vectors which contribute in highest covariance and these projection vectors are used to reduce feature dimension. The selection of projection vectors is done through Parallel Analysis (PA). The feature subset with the reduced dimension is provided to radial basis function (RBF) kernel based Support Vector Machines (SVM). The RBF based SVM serves the purpose of classification into two categories i.e., Heart Patient (HP) and Normal Subject (NS). The proposed methodology is evaluated through accuracy, specificity and sensitivity over the three datasets of UCI i.e., Cleveland, Switzerland and Hungarian. The statistical results achieved through the proposed technique are presented in comparison to the existing research showing its impact. The proposed technique achieved an accuracy of 82.18%, 85.82% and 91.30% for Cleveland, Hungarian and Switzerland dataset respectively.

  14. Extracted facial feature of racial closely related faces

    Science.gov (United States)

    Liewchavalit, Chalothorn; Akiba, Masakazu; Kanno, Tsuneo; Nagao, Tomoharu

    2010-02-01

    Human faces contain a lot of demographic information such as identity, gender, age, race and emotion. Human being can perceive these pieces of information and use it as an important clue in social interaction with other people. Race perception is considered the most delicacy and sensitive parts of face perception. There are many research concerning image-base race recognition, but most of them are focus on major race group such as Caucasoid, Negroid and Mongoloid. This paper focuses on how people classify race of the racial closely related group. As a sample of racial closely related group, we choose Japanese and Thai face to represents difference between Northern and Southern Mongoloid. Three psychological experiment was performed to study the strategies of face perception on race classification. As a result of psychological experiment, it can be suggested that race perception is an ability that can be learn. Eyes and eyebrows are the most attention point and eyes is a significant factor in race perception. The Principal Component Analysis (PCA) was performed to extract facial features of sample race group. Extracted race features of texture and shape were used to synthesize faces. As the result, it can be suggested that racial feature is rely on detailed texture rather than shape feature. This research is a indispensable important fundamental research on the race perception which are essential in the establishment of human-like race recognition system.

  15. A Novel Feature Extraction for Robust EMG Pattern Recognition

    CERN Document Server

    Phinyomark, Angkoon; Phukpattaranont, Pornchai

    2009-01-01

    Varieties of noises are major problem in recognition of Electromyography (EMG) signal. Hence, methods to remove noise become most significant in EMG signal analysis. White Gaussian noise (WGN) is used to represent interference in this paper. Generally, WGN is difficult to be removed using typical filtering and solutions to remove WGN are limited. In addition, noise removal is an important step before performing feature extraction, which is used in EMG-based recognition. This research is aimed to present a novel feature that tolerate with WGN. As a result, noise removal algorithm is not needed. Two novel mean and median frequencies (MMNF and MMDF) are presented for robust feature extraction. Sixteen existing features and two novelties are evaluated in a noisy environment. WGN with various signal-to-noise ratios (SNRs), i.e. 20-0 dB, was added to the original EMG signal. The results showed that MMNF performed very well especially in weak EMG signal compared with others. The error of MMNF in weak EMG signal with...

  16. A Transform-Based Feature Extraction Approach for Motor Imagery Tasks Classification

    Science.gov (United States)

    Khorshidtalab, Aida; Mesbah, Mostefa; Salami, Momoh J. E.

    2015-01-01

    In this paper, we present a new motor imagery classification method in the context of electroencephalography (EEG)-based brain–computer interface (BCI). This method uses a signal-dependent orthogonal transform, referred to as linear prediction singular value decomposition (LP-SVD), for feature extraction. The transform defines the mapping as the left singular vectors of the LP coefficient filter impulse response matrix. Using a logistic tree-based model classifier; the extracted features are classified into one of four motor imagery movements. The proposed approach was first benchmarked against two related state-of-the-art feature extraction approaches, namely, discrete cosine transform (DCT) and adaptive autoregressive (AAR)-based methods. By achieving an accuracy of 67.35%, the LP-SVD approach outperformed the other approaches by large margins (25% compared with DCT and 6 % compared with AAR-based methods). To further improve the discriminatory capability of the extracted features and reduce the computational complexity, we enlarged the extracted feature subset by incorporating two extra features, namely, Q- and the Hotelling’s \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{upgreek} \\usepackage{mathrsfs} \\setlength{\\oddsidemargin}{-69pt} \\begin{document} }{}$T^{2}$ \\end{document} statistics of the transformed EEG and introduced a new EEG channel selection method. The performance of the EEG classification based on the expanded feature set and channel selection method was compared with that of a number of the state-of-the-art classification methods previously reported with the BCI IIIa competition data set. Our method came second with an average accuracy of 81.38%. PMID:27170898

  17. Quantification of Cranial Asymmetry in Infants by Facial Feature Extraction

    Institute of Scientific and Technical Information of China (English)

    Chun-Ming Chang; Wei-Cheng Li; Chung-Lin Huang; Pei-Yeh Chang

    2014-01-01

    In this paper, a facial feature extracting method is proposed to transform three-dimension (3D) head images of infants with deformational plagiocephaly for assessment of asymmetry. The features of 3D point clouds of an infant’s cranium can be identified by local feature analysis and a two-phase k-means classification algorithm. The 3D images of infants with asymmetric cranium can then be aligned to the same pose. The mirrored head model obtained from the symmetry plane is compared with the original model for the measurement of asymmetry. Numerical data of the cranial volume can be reviewed by a pediatrician to adjust the treatment plan. The system can also be used to demonstrate the treatment progress.

  18. An image segmentation based method for iris feature extraction

    Institute of Scientific and Technical Information of China (English)

    XU Guang-zhu; ZHANG Zai-feng; MA Yi-de

    2008-01-01

    In this article, the local anomalistic blocks such ascrypts, furrows, and so on in the iris are initially used directly asiris features. A novel image segmentation method based onintersecting cortical model (ICM) neural network was introducedto segment these anomalistic blocks. First, the normalized irisimage was put into ICM neural network after enhancement.Second, the iris features were segmented out perfectly and wereoutput in binary image type by the ICM neural network. Finally,the fourth output pulse image produced by ICM neural networkwas chosen as the iris code for the convenience of real timeprocessing. To estimate the performance of the presentedmethod, an iris recognition platform was produced and theHamming Distance between two iris codes was computed tomeasure the dissimilarity between them. The experimentalresults in CASIA vl.0 and Bath iris image databases show thatthe proposed iris feature extraction algorithm has promisingpotential in iris recognition.

  19. Harnessing Satellite Imageries in Feature Extraction Using Google Earth Pro

    Science.gov (United States)

    Fernandez, Sim Joseph; Milano, Alan

    2016-07-01

    Climate change has been a long-time concern worldwide. Impending flooding, for one, is among its unwanted consequences. The Phil-LiDAR 1 project of the Department of Science and Technology (DOST), Republic of the Philippines, has developed an early warning system in regards to flood hazards. The project utilizes the use of remote sensing technologies in determining the lives in probable dire danger by mapping and attributing building features using LiDAR dataset and satellite imageries. A free mapping software named Google Earth Pro (GEP) is used to load these satellite imageries as base maps. Geotagging of building features has been done so far with the use of handheld Global Positioning System (GPS). Alternatively, mapping and attribution of building features using GEP saves a substantial amount of resources such as manpower, time and budget. Accuracy-wise, geotagging by GEP is dependent on either the satellite imageries or orthophotograph images of half-meter resolution obtained during LiDAR acquisition and not on the GPS of three-meter accuracy. The attributed building features are overlain to the flood hazard map of Phil-LiDAR 1 in order to determine the exposed population. The building features as obtained from satellite imageries may not only be used in flood exposure assessment but may also be used in assessing other hazards and a number of other uses. Several other features may also be extracted from the satellite imageries.

  20. Feature selection using genetic algorithms for fetal heart rate analysis.

    Science.gov (United States)

    Xu, Liang; Redman, Christopher W G; Payne, Stephen J; Georgieva, Antoniya

    2014-07-01

    The fetal heart rate (FHR) is monitored on a paper strip (cardiotocogram) during labour to assess fetal health. If necessary, clinicians can intervene and assist with a prompt delivery of the baby. Data-driven computerized FHR analysis could help clinicians in the decision-making process. However, selecting the best computerized FHR features that relate to labour outcome is a pressing research problem. The objective of this study is to apply genetic algorithms (GA) as a feature selection method to select the best feature subset from 64 FHR features and to integrate these best features to recognize unfavourable FHR patterns. The GA was trained on 404 cases and tested on 106 cases (both balanced datasets) using three classifiers, respectively. Regularization methods and backward selection were used to optimize the GA. Reasonable classification performance is shown on the testing set for the best feature subset (Cohen's kappa values of 0.45 to 0.49 using different classifiers). This is, to our knowledge, the first time that a feature selection method for FHR analysis has been developed on a database of this size. This study indicates that different FHR features, when integrated, can show good performance in predicting labour outcome. It also gives the importance of each feature, which will be a valuable reference point for further studies.

  1. Hadoop neural network for parallel and distributed feature selection.

    Science.gov (United States)

    Hodge, Victoria J; O'Keefe, Simon; Austin, Jim

    2016-06-01

    In this paper, we introduce a theoretical basis for a Hadoop-based neural network for parallel and distributed feature selection in Big Data sets. It is underpinned by an associative memory (binary) neural network which is highly amenable to parallel and distributed processing and fits with the Hadoop paradigm. There are many feature selectors described in the literature which all have various strengths and weaknesses. We present the implementation details of five feature selection algorithms constructed using our artificial neural network framework embedded in Hadoop YARN. Hadoop allows parallel and distributed processing. Each feature selector can be divided into subtasks and the subtasks can then be processed in parallel. Multiple feature selectors can also be processed simultaneously (in parallel) allowing multiple feature selectors to be compared. We identify commonalities among the five features selectors. All can be processed in the framework using a single representation and the overall processing can also be greatly reduced by only processing the common aspects of the feature selectors once and propagating these aspects across all five feature selectors as necessary. This allows the best feature selector and the actual features to select to be identified for large and high dimensional data sets through exploiting the efficiency and flexibility of embedding the binary associative-memory neural network in Hadoop. Copyright © 2015 The Authors. Published by Elsevier Ltd.. All rights reserved.

  2. Feature Selection for Neural Network Based Stock Prediction

    Science.gov (United States)

    Sugunnasil, Prompong; Somhom, Samerkae

    We propose a new methodology of feature selection for stock movement prediction. The methodology is based upon finding those features which minimize the correlation relation function. We first produce all the combination of feature and evaluate each of them by using our evaluate function. We search through the generated set with hill climbing approach. The self-organizing map based stock prediction model is utilized as the prediction method. We conduct the experiment on data sets of the Microsoft Corporation, General Electric Co. and Ford Motor Co. The results show that our feature selection method can improve the efficiency of the neural network based stock prediction.

  3. SAR Data Fusion Imaging Method Oriented to Target Feature Extraction

    Directory of Open Access Journals (Sweden)

    Yang Wei

    2015-02-01

    Full Text Available To deal with the difficulty for target outlines extracting precisely due to neglect of target scattering characteristic variation during the processing of high-resolution space-borne SAR data, a novel fusion imaging method is proposed oriented to target feature extraction. Firstly, several important aspects that affect target feature extraction and SAR image quality are analyzed, including curved orbit, stop-and-go approximation, atmospheric delay, and high-order residual phase error. Furthermore, the corresponding compensation methods are addressed as well. Based on the analysis, the mathematical model of SAR echo combined with target space-time spectrum is established for explaining the space-time-frequency change rule of target scattering characteristic. Moreover, a fusion imaging strategy and method under high-resolution and ultra-large observation angle range conditions are put forward to improve SAR quality by fusion processing in range-doppler and image domain. Finally, simulations based on typical military targets are used to verify the effectiveness of the fusion imaging method.

  4. Selective attention to temporal features on nested time scales.

    Science.gov (United States)

    Henry, Molly J; Herrmann, Björn; Obleser, Jonas

    2015-02-01

    Meaningful auditory stimuli such as speech and music often vary simultaneously along multiple time scales. Thus, listeners must selectively attend to, and selectively ignore, separate but intertwined temporal features. The current study aimed to identify and characterize the neural network specifically involved in this feature-selective attention to time. We used a novel paradigm where listeners judged either the duration or modulation rate of auditory stimuli, and in which the stimulation, working memory demands, response requirements, and task difficulty were held constant. A first analysis identified all brain regions where individual brain activation patterns were correlated with individual behavioral performance patterns, which thus supported temporal judgments generically. A second analysis then isolated those brain regions that specifically regulated selective attention to temporal features: Neural responses in a bilateral fronto-parietal network including insular cortex and basal ganglia decreased with degree of change of the attended temporal feature. Critically, response patterns in these regions were inverted when the task required selectively ignoring this feature. The results demonstrate how the neural analysis of complex acoustic stimuli with multiple temporal features depends on a fronto-parietal network that simultaneously regulates the selective gain for attended and ignored temporal features.

  5. A window-based time series feature extraction method.

    Science.gov (United States)

    Katircioglu-Öztürk, Deniz; Güvenir, H Altay; Ravens, Ursula; Baykal, Nazife

    2017-08-09

    This study proposes a robust similarity score-based time series feature extraction method that is termed as Window-based Time series Feature ExtraCtion (WTC). Specifically, WTC generates domain-interpretable results and involves significantly low computational complexity thereby rendering itself useful for densely sampled and populated time series datasets. In this study, WTC is applied to a proprietary action potential (AP) time series dataset on human cardiomyocytes and three precordial leads from a publicly available electrocardiogram (ECG) dataset. This is followed by comparing WTC in terms of predictive accuracy and computational complexity with shapelet transform and fast shapelet transform (which constitutes an accelerated variant of the shapelet transform). The results indicate that WTC achieves a slightly higher classification performance with significantly lower execution time when compared to its shapelet-based alternatives. With respect to its interpretable features, WTC has a potential to enable medical experts to explore definitive common trends in novel datasets. Copyright © 2017 Elsevier Ltd. All rights reserved.

  6. Entropy Analysis as an Electroencephalogram Feature Extraction Method

    Directory of Open Access Journals (Sweden)

    P. I. Sotnikov

    2014-01-01

    Full Text Available The aim of this study was to evaluate a possibility for using an entropy analysis as an electroencephalogram (EEG feature extraction method in brain-computer interfaces (BCI. The first section of the article describes the proposed algorithm based on the characteristic features calculation using the Shannon entropy analysis. The second section discusses issues of the classifier development for the EEG records. We use a support vector machine (SVM as a classifier. The third section describes the test data. Further, we estimate an efficiency of the considered feature extraction method to compare it with a number of other methods. These methods include: evaluation of signal variance; estimation of spectral power density (PSD; estimation of autoregression model parameters; signal analysis using the continuous wavelet transform; construction of common spatial pattern (CSP filter. As a measure of efficiency we use the probability value of correctly recognized types of imagery movements. At the last stage we evaluate the impact of EEG signal preprocessing methods on the final classification accuracy. Finally, it concludes that the entropy analysis has good prospects in BCI applications.

  7. A multi-approach feature extractions for iris recognition

    Science.gov (United States)

    Sanpachai, H.; Settapong, M.

    2014-04-01

    Biometrics is a promising technique that is used to identify individual traits and characteristics. Iris recognition is one of the most reliable biometric methods. As iris texture and color is fully developed within a year of birth, it remains unchanged throughout a person's life. Contrary to fingerprint, which can be altered due to several aspects including accidental damage, dry or oily skin and dust. Although iris recognition has been studied for more than a decade, there are limited commercial products available due to its arduous requirement such as camera resolution, hardware size, expensive equipment and computational complexity. However, at the present time, technology has overcome these obstacles. Iris recognition can be done through several sequential steps which include pre-processing, features extractions, post-processing, and matching stage. In this paper, we adopted the directional high-low pass filter for feature extraction. A box-counting fractal dimension and Iris code have been proposed as feature representations. Our approach has been tested on CASIA Iris Image database and the results are considered successful.

  8. Data Clustering Analysis Based on Wavelet Feature Extraction

    Institute of Scientific and Technical Information of China (English)

    QIANYuntao; TANGYuanyan

    2003-01-01

    A novel wavelet-based data clustering method is presented in this paper, which includes wavelet feature extraction and cluster growing algorithm. Wavelet transform can provide rich and diversified information for representing the global and local inherent structures of dataset. therefore, it is a very powerful tool for clustering feature extraction. As an unsupervised classification, the target of clustering analysis is dependent on the specific clustering criteria. Several criteria that should be con-sidered for general-purpose clustering algorithm are pro-posed. And the cluster growing algorithm is also con-structed to connect clustering criteria with wavelet fea-tures. Compared with other popular clustering methods,our clustering approach provides multi-resolution cluster-ing results,needs few prior parameters, correctly deals with irregularly shaped clusters, and is insensitive to noises and outliers. As this wavelet-based clustering method isaimed at solving two-dimensional data clustering prob-lem, for high-dimensional datasets, self-organizing mapand U-matrlx method are applied to transform them intotwo-dimensional Euclidean space, so that high-dimensional data clustering analysis,Results on some sim-ulated data and standard test data are reported to illus-trate the power of our method.

  9. Feature-selective attention in healthy old age: a selective decline in selective attention?

    Science.gov (United States)

    Quigley, Cliodhna; Müller, Matthias M

    2014-02-12

    Deficient selection against irrelevant information has been proposed to underlie age-related cognitive decline. We recently reported evidence for maintained early sensory selection when older and younger adults used spatial selective attention to perform a challenging task. Here we explored age-related differences when spatial selection is not possible and feature-selective attention must be deployed. We additionally compared the integrity of feedforward processing by exploiting the well established phenomenon of suppression of visual cortical responses attributable to interstimulus competition. Electroencephalogram was measured while older and younger human adults responded to brief occurrences of coherent motion in an attended stimulus composed of randomly moving, orientation-defined, flickering bars. Attention was directed to horizontal or vertical bars by a pretrial cue, after which two orthogonally oriented, overlapping stimuli or a single stimulus were presented. Horizontal and vertical bars flickered at different frequencies and thereby elicited separable steady-state visual-evoked potentials, which were used to examine the effect of feature-based selection and the competitive influence of a second stimulus on ongoing visual processing. Age differences were found in feature-selective attentional modulation of visual responses: older adults did not show consistent modulation of magnitude or phase. In contrast, the suppressive effect of a second stimulus was robust and comparable in magnitude across age groups, suggesting that bottom-up processing of the current stimuli is essentially unchanged in healthy old age. Thus, it seems that visual processing per se is unchanged, but top-down attentional control is compromised in older adults when space cannot be used to guide selection.

  10. Web News Extraction via Tag Path Feature Fusion Using DS Theory

    Institute of Scientific and Technical Information of China (English)

    Gong-Qing Wu; Lei Li; Li Li; Xindong Wu

    2016-01-01

    Contents, layout styles, and parse structures of web news pages differ greatly from one page to another. In addition, the layout style and the parse structure of a web news page may change from time to time. For these reasons, how to design features with excellent extraction performances for massive and heterogeneous web news pages is a challenging issue. Our extensive case studies indicate that there is potential relevancy between web content layouts and their tag paths. Inspired by the observation, we design a series of tag path extraction features to extract web news. Because each feature has its own strength, we fuse all those features with the DS (Dempster-Shafer) evidence theory, and then design a content extraction method CEDS. Experimental results on both CleanEval datasets and web news pages selected randomly from well-known websites show that the F1-score with CEDS is 8.08%and 3.08%higher than existing popular content extraction methods CETR and CEPR-TPR respectively.

  11. A Novel Feature Cloud Visualization for Depiction of Product Features Extracted from Customer Reviews

    Directory of Open Access Journals (Sweden)

    Tanvir Ahmad

    2013-09-01

    Full Text Available There has been an exponential growth of web content on the World Wide Web and online users contributing to majority of the unstructured data which also contain a good amount of information on many different subjects that may range from products, news, programmes and services. Many a times other users read these reviews and try to find the meaning of the sentences expressed by the reviewers. Since the number and the length of the reviews are so large that most the times the user will read a few reviews and would like to take an informed decision on the subject that is being talked about. Many different methods have been adopted by websites like numerical rating, star rating, percentage rating etc. However, these methods fail to give information on the explicit features of the product and their overall weight when taking the product in totality. In this paper, a framework has been presented which first calculates the weight of the features depending on the user satisfaction or dissatisfaction expressed on individual features and further a feature cloud visualization has been proposed which uses two level of specificity where the first level lists the extracted features and the second level shows the opinions on those features. A font generation function has been applied which calculates the font size depending on the importance of the features vis-a-vis with the opinion expressed on them.

  12. Lazy learner text categorization algorithm based on embedded feature selection

    Institute of Scientific and Technical Information of China (English)

    Yan Peng; Zheng Xuefeng; Zhu Jianyong; Xiao Yunhong

    2009-01-01

    To avoid the curse of dimensionality, text categorization (TC) algorithms based on machine learning (ML) have to use an feature selection (FS) method to reduce the dimensionality of feature space. Although having been widely used, FS process will generally cause information losing and then have much side-effect on the whole performance of TC algorithms. On the basis of the sparsity characteristic of text vectors, a new TC algorithm based on lazy feature selection (LFS) is presented. As a new type of embedded feature selection approach, the LFS method can greatly reduce the dimension of features without any information losing, which can improve both efficiency and performance of algorithms greatly. The experiments show the new algorithm can simultaneously achieve much higher both performance and efficiency than some of other classical TC algorithms.

  13. Features extraction from the electrocatalytic gas sensor responses

    Science.gov (United States)

    Kalinowski, Paweł; Woźniak, Łukasz; Stachowiak, Maria; Jasiński, Grzegorz; Jasiński, Piotr

    2016-11-01

    One of the types of gas sensors used for detection and identification of toxic-air pollutant is an electro-catalytic gas sensor. The electro-catalytic sensors are working in cyclic voltammetry mode, enable detection of various gases. Their response are in the form of I-V curves which contain information about the type and the concentration of measured volatile compound. However, additional analysis is required to provide the efficient recognition of the target gas. Multivariate data analysis and pattern recognition methods are proven to be useful tool for such application, but further investigations on the improvement of the sensor's responses processing are required. In this article the method for extraction of the parameters from the electro-catalytic sensor responses is presented. Extracted features enable the significant reduction of data dimension without the loss of the efficiency of recognition of four volatile air-pollutant, namely nitrogen dioxide, ammonia, hydrogen sulfide and sulfur dioxide.

  14. Opinion mining feature-level using Naive Bayes and feature extraction based analysis dependencies

    Science.gov (United States)

    Sanda, Regi; Baizal, Z. K. Abdurahman; Nhita, Fhira

    2015-12-01

    Development of internet and technology, has major impact and providing new business called e-commerce. Many e-commerce sites that provide convenience in transaction, and consumers can also provide reviews or opinions on products that purchased. These opinions can be used by consumers and producers. Consumers to know the advantages and disadvantages of particular feature of the product. Procuders can analyse own strengths and weaknesses as well as it's competitors products. Many opinions need a method that the reader can know the point of whole opinion. The idea emerged from review summarization that summarizes the overall opinion based on sentiment and features contain. In this study, the domain that become the main focus is about the digital camera. This research consisted of four steps 1) giving the knowledge to the system to recognize the semantic orientation of an opinion 2) indentify the features of product 3) indentify whether the opinion gives a positive or negative 4) summarizing the result. In this research discussed the methods such as Naï;ve Bayes for sentiment classification, and feature extraction algorithm based on Dependencies Analysis, which is one of the tools in Natural Language Processing (NLP) and knowledge based dictionary which is useful for handling implicit features. The end result of research is a summary that contains a bunch of reviews from consumers on the features and sentiment. With proposed method, accuration for sentiment classification giving 81.2 % for positive test data, 80.2 % for negative test data, and accuration for feature extraction reach 90.3 %.

  15. Extract relevant features from DEM for groundwater potential mapping

    Science.gov (United States)

    Liu, T.; Yan, H.; Zhai, L.

    2015-06-01

    Multi-criteria evaluation (MCE) method has been applied much in groundwater potential mapping researches. But when to data scarce areas, it will encounter lots of problems due to limited data. Digital Elevation Model (DEM) is the digital representations of the topography, and has many applications in various fields. Former researches had been approved that much information concerned to groundwater potential mapping (such as geological features, terrain features, hydrology features, etc.) can be extracted from DEM data. This made using DEM data for groundwater potential mapping is feasible. In this research, one of the most widely used and also easy to access data in GIS, DEM data was used to extract information for groundwater potential mapping in batter river basin in Alberta, Canada. First five determining factors for potential ground water mapping were put forward based on previous studies (lineaments and lineament density, drainage networks and its density, topographic wetness index (TWI), relief and convergence Index (CI)). Extraction methods of the five determining factors from DEM were put forward and thematic maps were produced accordingly. Cumulative effects matrix was used for weight assignment, a multi-criteria evaluation process was carried out by ArcGIS software to delineate the potential groundwater map. The final groundwater potential map was divided into five categories, viz., non-potential, poor, moderate, good, and excellent zones. Eventually, the success rate curve was drawn and the area under curve (AUC) was figured out for validation. Validation result showed that the success rate of the model was 79% and approved the method's feasibility. The method afforded a new way for researches on groundwater management in areas suffers from data scarcity, and also broaden the application area of DEM data.

  16. Feature selection for domain knowledge representation through multitask learning

    CSIR Research Space (South Africa)

    Rosman, Benjamin S

    2014-10-01

    Full Text Available -1 Feature selection for domain knowledge representation through multitask learning Benjamin Rosman Mobile Intelligent Autonomous Systems CSIR South Africa BRosman@csir.co.za Representation learning is a difficult and important problem...

  17. Optimized Image Steganalysis through Feature Selection using MBEGA

    CERN Document Server

    Geetha, S

    2010-01-01

    Feature based steganalysis, an emerging branch in information forensics, aims at identifying the presence of a covert communication by employing the statistical features of the cover and stego image as clues/evidences. Due to the large volumes of security audit data as well as complex and dynamic properties of steganogram behaviours, optimizing the performance of steganalysers becomes an important open problem. This paper is focussed at fine tuning the performance of six promising steganalysers in this field, through feature selection. We propose to employ Markov Blanket-Embedded Genetic Algorithm (MBEGA) for stego sensitive feature selection process. In particular, the embedded Markov blanket based memetic operators add or delete features (or genes) from a genetic algorithm (GA) solution so as to quickly improve the solution and fine-tune the search. Empirical results suggest that MBEGA is effective and efficient in eliminating irrelevant and redundant features based on both Markov blanket and predictive pow...

  18. A New Heuristic for Feature Selection by Consistent Biclustering

    CERN Document Server

    Mucherino, Antonio

    2010-01-01

    Given a set of data, biclustering aims at finding simultaneous partitions in biclusters of its samples and of the features which are used for representing the samples. Consistent biclusterings allow to obtain correct classifications of the samples from the known classification of the features, and vice versa, and they are very useful for performing supervised classifications. The problem of finding consistent biclusterings can be seen as a feature selection problem, where the features that are not relevant for classification purposes are removed from the set of data, while the total number of features is maximized in order to preserve information. This feature selection problem can be formulated as a linear fractional 0-1 optimization problem. We propose a reformulation of this problem as a bilevel optimization problem, and we present a heuristic algorithm for an efficient solution of the reformulated problem. Computational experiments show that the presented algorithm is able to find better solutions with re...

  19. Feature Extraction and Analysis of Breast Cancer Specimen

    Science.gov (United States)

    Bhattacharyya, Debnath; Robles, Rosslin John; Kim, Tai-Hoon; Bandyopadhyay, Samir Kumar

    In this paper, we propose a method to identify abnormal growth of cells in breast tissue and suggest further pathological test, if necessary. We compare normal breast tissue with malignant invasive breast tissue by a series of image processing steps. Normal ductal epithelial cells and ductal / lobular invasive carcinogenic cells also consider for comparison here in this paper. In fact, features of cancerous breast tissue (invasive) are extracted and analyses with normal breast tissue. We also suggest the breast cancer recognition technique through image processing and prevention by controlling p53 gene mutation to some greater extent.

  20. Point features extraction: towards slam for an autonomous underwater vehicle

    CSIR Research Space (South Africa)

    Matsebe, O

    2010-07-01

    Full Text Available Page 1 of 11 25th International Conference of CAD/CAM, Robotics & Factories of the Future Conference, 13-16 July 2010, Pretoria, South Africa POINT FEATURES EXTRACTION: TOWARDS SLAM FOR AN AUTONOMOUS UNDERWATER VEHICLE O. Matsebe1,2, M... Page 2 of 11 25th International Conference of CAD/CAM, Robotics & Factories of the Future Conference, 13-16 July 2010, Pretoria, South Africa vehicle is equipped with a Mechanically Scanned Imaging Sonar (Micron DST Sonar) which is able...

  1. Ensemble Feature Extraction Modules for Improved Hindi Speech Recognition System

    Directory of Open Access Journals (Sweden)

    Malay Kumar

    2012-05-01

    Full Text Available Speech is the most natural way of communication between human beings. The field of speech recognition generates intrigues of man - machine conversation and due to its versatile applications; automatic speech recognition systems have been designed. In this paper we are presenting a novel approach for Hindi speech recognition by ensemble feature extraction modules of ASR systems and their outputs have been combined using voting technique ROVER. Experimental results have been shown that proposed system will produce better result than traditional ASR systems.

  2. Modeling Suspicious Email Detection using Enhanced Feature Selection

    OpenAIRE

    2013-01-01

    The paper presents a suspicious email detection model which incorporates enhanced feature selection. In the paper we proposed the use of feature selection strategies along with classification technique for terrorists email detection. The presented model focuses on the evaluation of machine learning algorithms such as decision tree (ID3), logistic regression, Na\\"ive Bayes (NB), and Support Vector Machine (SVM) for detecting emails containing suspicious content. In the literature, various algo...

  3. Reaction Decoder Tool (RDT): extracting features from chemical reactions

    Science.gov (United States)

    Rahman, Syed Asad; Torrance, Gilliean; Baldacci, Lorenzo; Martínez Cuesta, Sergio; Fenninger, Franz; Gopal, Nimish; Choudhary, Saket; May, John W.; Holliday, Gemma L.; Steinbeck, Christoph; Thornton, Janet M.

    2016-01-01

    Summary: Extracting chemical features like Atom–Atom Mapping (AAM), Bond Changes (BCs) and Reaction Centres from biochemical reactions helps us understand the chemical composition of enzymatic reactions. Reaction Decoder is a robust command line tool, which performs this task with high accuracy. It supports standard chemical input/output exchange formats i.e. RXN/SMILES, computes AAM, highlights BCs and creates images of the mapped reaction. This aids in the analysis of metabolic pathways and the ability to perform comparative studies of chemical reactions based on these features. Availability and implementation: This software is implemented in Java, supported on Windows, Linux and Mac OSX, and freely available at https://github.com/asad/ReactionDecoder Contact: asad@ebi.ac.uk or s9asad@gmail.com PMID:27153692

  4. Reaction Decoder Tool (RDT): extracting features from chemical reactions.

    Science.gov (United States)

    Rahman, Syed Asad; Torrance, Gilliean; Baldacci, Lorenzo; Martínez Cuesta, Sergio; Fenninger, Franz; Gopal, Nimish; Choudhary, Saket; May, John W; Holliday, Gemma L; Steinbeck, Christoph; Thornton, Janet M

    2016-07-01

    Extracting chemical features like Atom-Atom Mapping (AAM), Bond Changes (BCs) and Reaction Centres from biochemical reactions helps us understand the chemical composition of enzymatic reactions. Reaction Decoder is a robust command line tool, which performs this task with high accuracy. It supports standard chemical input/output exchange formats i.e. RXN/SMILES, computes AAM, highlights BCs and creates images of the mapped reaction. This aids in the analysis of metabolic pathways and the ability to perform comparative studies of chemical reactions based on these features. This software is implemented in Java, supported on Windows, Linux and Mac OSX, and freely available at https://github.com/asad/ReactionDecoder : asad@ebi.ac.uk or s9asad@gmail.com. © The Author 2016. Published by Oxford University Press.

  5. Graph-driven features extraction from microarray data

    CERN Document Server

    Vert, J P; Vert, Jean-Philippe; Kanehisa, Minoru

    2002-01-01

    Gene function prediction from microarray data is a first step toward better understanding the machinery of the cell from relatively cheap and easy-to-produce data. In this paper we investigate whether the knowledge of many metabolic pathways and their catalyzing enzymes accumulated over the years can help improve the performance of classifiers for this problem. The complex network of known biochemical reactions in the cell results in a representation where genes are nodes of a graph. Formulating the problem as a graph-driven features extraction problem, based on the simple idea that relevant features are likely to exhibit correlation with respect to the topology of the graph, we end up with an algorithm which involves encoding the network and the set of expression profiles into kernel functions, and performing a regularized form of canonical correlation analysis in the corresponding reproducible kernel Hilbert spaces. Function prediction experiments for the genes of the yeast S. Cerevisiae validate this appro...

  6. Texture Feature Extraction and Classification for Iris Diagnosis

    Science.gov (United States)

    Ma, Lin; Li, Naimin

    Appling computer aided techniques in iris image processing, and combining occidental iridology with the traditional Chinese medicine is a challenging research area in digital image processing and artificial intelligence. This paper proposes an iridology model that consists the iris image pre-processing, texture feature analysis and disease classification. To the pre-processing, a 2-step iris localization approach is proposed; a 2-D Gabor filter based texture analysis and a texture fractal dimension estimation method are proposed for pathological feature extraction; and at last support vector machines are constructed to recognize 2 typical diseases such as the alimentary canal disease and the nerve system disease. Experimental results show that the proposed iridology diagnosis model is quite effective and promising for medical diagnosis and health surveillance for both hospital and public use.

  7. Road marking features extraction using the VIAPIX® system

    Science.gov (United States)

    Kaddah, W.; Ouerhani, Y.; Alfalou, A.; Desthieux, M.; Brosseau, C.; Gutierrez, C.

    2016-07-01

    Precise extraction of road marking features is a critical task for autonomous urban driving, augmented driver assistance, and robotics technologies. In this study, we consider an autonomous system allowing us lane detection for marked urban roads and analysis of their features. The task is to relate the georeferencing of road markings from images obtained using the VIAPIX® system. Based on inverse perspective mapping and color segmentation to detect all white objects existing on this road, the present algorithm enables us to examine these images automatically and rapidly and also to get information on road marks, their surface conditions, and their georeferencing. This algorithm allows detecting all road markings and identifying some of them by making use of a phase-only correlation filter (POF). We illustrate this algorithm and its robustness by applying it to a variety of relevant scenarios.

  8. Ensemble feature selection integrating elitist roles and quantum game model

    Institute of Scientific and Technical Information of China (English)

    Weiping Ding; Jiandong Wang; Zhijin Guan; Quan Shi

    2015-01-01

    To accelerate the selection process of feature subsets in the rough set theory (RST), an ensemble elitist roles based quantum game (EERQG) algorithm is proposed for feature selec-tion. Firstly, the multilevel elitist roles based dynamics equilibrium strategy is established, and both immigration and emigration of elitists are able to be self-adaptive to balance between exploration and exploitation for feature selection. Secondly, the utility matrix of trust margins is introduced to the model of multilevel elitist roles to enhance various elitist roles’ performance of searching the optimal feature subsets, and the win-win utility solutions for feature selec-tion can be attained. Meanwhile, a novel ensemble quantum game strategy is designed as an intriguing exhibiting structure to perfect the dynamics equilibrium of multilevel elitist roles. Final y, the en-semble manner of multilevel elitist roles is employed to achieve the global minimal feature subset, which wil greatly improve the fea-sibility and effectiveness. Experiment results show the proposed EERQG algorithm has superiority compared to the existing feature selection algorithms.

  9. Effective Feature Selection for 5G IM Applications Traffic Classification

    Directory of Open Access Journals (Sweden)

    Muhammad Shafiq

    2017-01-01

    Full Text Available Recently, machine learning (ML algorithms have widely been applied in Internet traffic classification. However, due to the inappropriate features selection, ML-based classifiers are prone to misclassify Internet flows as that traffic occupies majority of traffic flows. To address this problem, a novel feature selection metric named weighted mutual information (WMI is proposed. We develop a hybrid feature selection algorithm named WMI_ACC, which filters most of the features with WMI metric. It further uses a wrapper method to select features for ML classifiers with accuracy (ACC metric. We evaluate our approach using five ML classifiers on the two different network environment traces captured. Furthermore, we also apply Wilcoxon pairwise statistical test on the results of our proposed algorithm to find out the robust features from the selected set of features. Experimental results show that our algorithm gives promising results in terms of classification accuracy, recall, and precision. Our proposed algorithm can achieve 99% flow accuracy results, which is very promising.

  10. Using genetic algorithm feature selection in neural classification systems for image pattern recognition

    Directory of Open Access Journals (Sweden)

    Margarita R. Gamarra A.

    2012-09-01

    Full Text Available Pattern recognition performance depends on variations during extraction, selection and classification stages. This paper presents an approach to feature selection by using genetic algorithms with regard to digital image recognition and quality control. Error rate and kappa coefficient were used for evaluating the genetic algorithm approach Neural networks were used for classification, involving the features selected by the genetic algorithms. The neural network approach was compared to a K-nearest neighbor classifier. The proposed approach performed better than the other methods.

  11. Extraction of ABCD rule features from skin lesions images with smartphone.

    Science.gov (United States)

    Rosado, Luís; Castro, Rui; Ferreira, Liliana; Ferreira, Márcia

    2012-01-01

    One of the greatest challenges in dermatology today is the early detection of melanoma since the success rates of curing this type of cancer are very high if detected during the early stages of its development. The main objective of the work presented in this paper is to create a prototype of a patient-oriented system for skin lesion analysis using a smartphone. This work aims at implementing a self-monitoring system that collects, processes, and stores information of skin lesions through the automatic extraction of specific visual features. The selection of the features was based on the ABCD rule, which considers 4 visual criteria considered highly relevant for the detection of malignant melanoma. The algorithms used to extract these features are briefly described and the results achieved using images taken from the smartphone camera are discussed.

  12. Feature selection using feature dissimilarity measure and density-based clustering: Application to biological data

    Indian Academy of Sciences (India)

    Debarka Sengupta; Indranil Aich; Sanghamitra Bandyopadhyay

    2015-10-01

    Reduction of dimensionality has emerged as a routine process in modelling complex biological systems. A large number of feature selection techniques have been reported in the literature to improve model performance in terms of accuracy and speed. In the present article an unsupervised feature selection technique is proposed, using maximum information compression index as the dissimilarity measure and the well-known density-based cluster identification technique DBSCAN for identifying the largest natural group of dissimilar features. The algorithm is fast and less sensitive to the user-supplied parameters. Moreover, the method automatically determines the required number of features and identifies them. We used the proposed method for reducing dimensionality of a number of benchmark data sets of varying sizes. Its performance was also extensively compared with some other well-known feature selection methods.

  13. Multi-task GLOH feature selection for human age estimation

    CERN Document Server

    Liang, Yixiong; Xu, Ying; Xiang, Yao; Zou, Beiji

    2011-01-01

    In this paper, we propose a novel age estimation method based on GLOH feature descriptor and multi-task learning (MTL). The GLOH feature descriptor, one of the state-of-the-art feature descriptor, is used to capture the age-related local and spatial information of face image. As the exacted GLOH features are often redundant, MTL is designed to select the most informative feature bins for age estimation problem, while the corresponding weights are determined by ridge regression. This approach largely reduces the dimensions of feature, which can not only improve performance but also decrease the computational burden. Experiments on the public available FG-NET database show that the proposed method can achieve comparable performance over previous approaches while using much fewer features.

  14. Feature selection and classification methodology for the detection of knee-joint disorders.

    Science.gov (United States)

    Nalband, Saif; Sundar, Aditya; Prince, A Amalin; Agarwal, Anita

    2016-04-01

    Vibroarthographic (VAG) signals emitted from the knee joint disorder provides an early diagnostic tool. The nonstationary and nonlinear nature of VAG signal makes an important aspect for feature extraction. In this work, we investigate VAG signals by proposing a wavelet based decomposition. The VAG signals are decomposed into sub-band signals of different frequencies. Nonlinear features such as recurrence quantification analysis (RQA), approximate entropy (ApEn) and sample entropy (SampEn) are extracted as features of VAG signal. A total of twenty-four features form a vector to characterize a VAG signal. Two feature selection (FS) techniques, apriori algorithm and genetic algorithm (GA) selects six and four features as the most significant features. Least square support vector machines (LS-SVM) and random forest are proposed as classifiers to evaluate the performance of FS techniques. Results indicate that the classification accuracy was more prominent with features selected from FS algorithms. Results convey that LS-SVM using the apriori algorithm gives the highest accuracy of 94.31% with false discovery rate (FDR) of 0.0892. The proposed work also provided better classification accuracy than those reported in the previous studies which gave an accuracy of 88%. This work can enhance the performance of existing technology for accurately distinguishing normal and abnormal VAG signals. And the proposed methodology could provide an effective non-invasive diagnostic tool for knee joint disorders.

  15. Improving Naive Bayes with Online Feature Selection for Quick Adaptation to Evolving Feature Usefulness

    Energy Technology Data Exchange (ETDEWEB)

    Pon, R K; Cardenas, A F; Buttler, D J

    2007-09-19

    The definition of what makes an article interesting varies from user to user and continually evolves even for a single user. As a result, for news recommendation systems, useless document features can not be determined a priori and all features are usually considered for interestingness classification. Consequently, the presence of currently useless features degrades classification performance [1], particularly over the initial set of news articles being classified. The initial set of document is critical for a user when considering which particular news recommendation system to adopt. To address these problems, we introduce an improved version of the naive Bayes classifier with online feature selection. We use correlation to determine the utility of each feature and take advantage of the conditional independence assumption used by naive Bayes for online feature selection and classification. The augmented naive Bayes classifier performs 28% better than the traditional naive Bayes classifier in recommending news articles from the Yahoo! RSS feeds.

  16. The Effect of Feature Selection on Phish Website Detection

    Directory of Open Access Journals (Sweden)

    Hiba Zuhair

    2015-10-01

    Full Text Available Recently, limited anti-phishing campaigns have given phishers more possibilities to bypass through their advanced deceptions. Moreover, failure to devise appropriate classification techniques to effectively identify these deceptions has degraded the detection of phishing websites. Consequently, exploiting as new; few; predictive; and effective features as possible has emerged as a key challenge to keep the detection resilient. Thus, some prior works had been carried out to investigate and apply certain selected methods to develop their own classification techniques. However, no study had generally agreed on which feature selection method that could be employed as the best assistant to enhance the classification performance. Hence, this study empirically examined these methods and their effects on classification performance. Furthermore, it recommends some promoting criteria to assess their outcomes and offers contribution on the problem at hand. Hybrid features, low and high dimensional datasets, different feature selection methods, and classification models were examined in this study. As a result, the findings displayed notably improved detection precision with low latency, as well as noteworthy gains in robustness and prediction susceptibilities. Although selecting an ideal feature subset was a challenging task, the findings retrieved from this study had provided the most advantageous feature subset as possible for robust selection and effective classification in the phishing detection domain.

  17. Extraction of sandy bedforms features through geodesic morphometry

    Science.gov (United States)

    Debese, Nathalie; Jacq, Jean-José; Garlan, Thierry

    2016-09-01

    State-of-art echosounders reveal fine-scale details of mobile sandy bedforms, which are commonly found on continental shelfs. At present, their dynamics are still far from being completely understood. These bedforms are a serious threat to navigation security, anthropic structures and activities, placing emphasis on research breakthroughs. Bedform geometries and their dynamics are closely linked; therefore, one approach is to develop semi-automatic tools aiming at extracting their structural features from bathymetric datasets. Current approaches mimic manual processes or rely on morphological simplification of bedforms. The 1D and 2D approaches cannot address the wide ranges of both types and complexities of bedforms. In contrast, this work attempts to follow a 3D global semi-automatic approach based on a bathymetric TIN. The currently extracted primitives are the salient ridge and valley lines of the sand structures, i.e., waves and mega-ripples. The main difficulty is eliminating the ripples that are found to heavily overprint any observations. To this end, an anisotropic filter that is able to discard these structures while still enhancing the wave ridges is proposed. The second part of the work addresses the semi-automatic interactive extraction and 3D augmented display of the main lines structures. The proposed protocol also allows geoscientists to interactively insert topological constraints.

  18. Protein fold classification with genetic algorithms and feature selection.

    Science.gov (United States)

    Chen, Peng; Liu, Chunmei; Burge, Legand; Mahmood, Mohammad; Southerland, William; Gloster, Clay

    2009-10-01

    Protein fold classification is a key step to predicting protein tertiary structures. This paper proposes a novel approach based on genetic algorithms and feature selection to classifying protein folds. Our dataset is divided into a training dataset and a test dataset. Each individual for the genetic algorithms represents a selection function of the feature vectors of the training dataset. A support vector machine is applied to each individual to evaluate the fitness value (fold classification rate) of each individual. The aim of the genetic algorithms is to search for the best individual that produces the highest fold classification rate. The best individual is then applied to the feature vectors of the test dataset and a support vector machine is built to classify protein folds based on selected features. Our experimental results on Ding and Dubchak's benchmark dataset of 27-class folds show that our approach achieves an accuracy of 71.28%, which outperforms current state-of-the-art protein fold predictors.

  19. GPU Accelerated Automated Feature Extraction From Satellite Images

    Directory of Open Access Journals (Sweden)

    K. Phani Tejaswi

    2013-04-01

    Full Text Available The availability of large volumes of remote sensing data insists on higher degree of automation in featureextraction, making it a need of thehour. Fusingdata from multiple sources, such as panchromatic,hyperspectraland LiDAR sensors, enhances the probability of identifying and extracting features such asbuildings, vegetation or bodies of water by using a combination of spectral and elevation characteristics.Utilizing theaforementioned featuresin remote sensing is impracticable in the absence ofautomation.Whileefforts are underway to reduce human intervention in data processing, this attempt alone may notsuffice. Thehuge quantum of data that needs to be processed entailsaccelerated processing to be enabled.GPUs, which were originally designed to provide efficient visualization,arebeing massively employed forcomputation intensive parallel processing environments. Image processing in general and hence automatedfeatureextraction, is highly computation intensive, where performance improvements have a direct impacton societal needs. In this context, an algorithm has been formulated for automated feature extraction froma panchromatic or multispectral image based on image processing techniques.Two Laplacian of Guassian(LoGmasks were applied on the image individually followed by detection of zero crossing points andextracting the pixels based on their standard deviationwiththe surrounding pixels. The two extractedimages with different LoG masks were combined together which resulted in an image withthe extractedfeatures and edges.Finally the user is at liberty to apply the image smoothing step depending on the noisecontent in the extracted image.The image ispassed through a hybrid median filter toremove the salt andpepper noise from the image.This paper discusses theaforesaidalgorithmforautomated featureextraction, necessity of deployment of GPUs for thesame;system-level challenges and quantifies thebenefits of integrating GPUs in such environment. The

  20. Particle Swarm Optimization Based Feature Enhancement and Feature Selection for Improved Emotion Recognition in Speech and Glottal Signals

    Science.gov (United States)

    Muthusamy, Hariharan; Polat, Kemal; Yaacob, Sazali

    2015-01-01

    In the recent years, many research works have been published using speech related features for speech emotion recognition, however, recent studies show that there is a strong correlation between emotional states and glottal features. In this work, Mel-frequency cepstralcoefficients (MFCCs), linear predictive cepstral coefficients (LPCCs), perceptual linear predictive (PLP) features, gammatone filter outputs, timbral texture features, stationary wavelet transform based timbral texture features and relative wavelet packet energy and entropy features were extracted from the emotional speech (ES) signals and its glottal waveforms(GW). Particle swarm optimization based clustering (PSOC) and wrapper based particle swarm optimization (WPSO) were proposed to enhance the discerning ability of the features and to select the discriminating features respectively. Three different emotional speech databases were utilized to gauge the proposed method. Extreme learning machine (ELM) was employed to classify the different types of emotions. Different experiments were conducted and the results show that the proposed method significantly improves the speech emotion recognition performance compared to previous works published in the literature. PMID:25799141

  1. Spectral and bispectral feature-extraction neural networks for texture classification

    Science.gov (United States)

    Kameyama, Keisuke; Kosugi, Yukio

    1997-10-01

    A neural network model (Kernel Modifying Neural Network: KM Net) specialized for image texture classification, which unifies the filtering kernels for feature extraction and the layered network classifier, will be introduced. The KM Net consists of a layer of convolution kernels that are constrained to be 2D Gabor filters to guarantee efficient spectral feature localization. The KM Net enables an automated feature extraction in multi-channel texture classification through simultaneous modification of the Gabor kernel parameters (central frequency and bandwidth) and the connection weights of the subsequent classifier layers by a backpropagation-based training rule. The capability of the model and its training rule was verified via segmentation of common texture mosaic images. In comparison with the conventional multi-channel filtering method which uses numerous filters to cover the spatial frequency domain, the proposed strategy can greatly reduce the computational cost both in feature extraction and classification. Since the adaptive Gabor filtering scheme is also applicable to band selection in moment spectra of higher orders, the network model was extended for adaptive bispectral filtering for extraction of the phase relation among the frequency components. The ability of this Bispectral KM Net was demonstrated in the discrimination of visually discriminable synthetic textures with identical local power spectral distributions.

  2. Performance Evaluation of Content Based Image Retrieval on Feature Optimization and Selection Using Swarm Intelligence

    Directory of Open Access Journals (Sweden)

    Kirti Jain

    2016-03-01

    Full Text Available The diversity and applicability of swarm intelligence is increasing everyday in the fields of science and engineering. Swarm intelligence gives the features of the dynamic features optimization concept. We have used swarm intelligence for the process of feature optimization and feature selection for content-based image retrieval. The performance of content-based image retrieval faced the problem of precision and recall. The value of precision and recall depends on the retrieval capacity of the image. The basic raw image content has visual features such as color, texture, shape and size. The partial feature extraction technique is based on geometric invariant function. Three swarm intelligence algorithms were used for the optimization of features: ant colony optimization, particle swarm optimization (PSO, and glowworm optimization algorithm. Coral image dataset and MatLab software were used for evaluating performance.

  3. Deep PDF parsing to extract features for detecting embedded malware.

    Energy Technology Data Exchange (ETDEWEB)

    Munson, Miles Arthur; Cross, Jesse S. (Missouri University of Science and Technology, Rolla, MO)

    2011-09-01

    The number of PDF files with embedded malicious code has risen significantly in the past few years. This is due to the portability of the file format, the ways Adobe Reader recovers from corrupt PDF files, the addition of many multimedia and scripting extensions to the file format, and many format properties the malware author may use to disguise the presence of malware. Current research focuses on executable, MS Office, and HTML formats. In this paper, several features and properties of PDF Files are identified. Features are extracted using an instrumented open source PDF viewer. The feature descriptions of benign and malicious PDFs can be used to construct a machine learning model for detecting possible malware in future PDF files. The detection rate of PDF malware by current antivirus software is very low. A PDF file is easy to edit and manipulate because it is a text format, providing a low barrier to malware authors. Analyzing PDF files for malware is nonetheless difficult because of (a) the complexity of the formatting language, (b) the parsing idiosyncrasies in Adobe Reader, and (c) undocumented correction techniques employed in Adobe Reader. In May 2011, Esparza demonstrated that PDF malware could be hidden from 42 of 43 antivirus packages by combining multiple obfuscation techniques [4]. One reason current antivirus software fails is the ease of varying byte sequences in PDF malware, thereby rendering conventional signature-based virus detection useless. The compression and encryption functions produce sequences of bytes that are each functions of multiple input bytes. As a result, padding the malware payload with some whitespace before compression/encryption can change many of the bytes in the final payload. In this study we analyzed a corpus of 2591 benign and 87 malicious PDF files. While this corpus is admittedly small, it allowed us to test a system for collecting indicators of embedded PDF malware. We will call these indicators features throughout

  4. Deep PDF parsing to extract features for detecting embedded malware.

    Energy Technology Data Exchange (ETDEWEB)

    Munson, Miles Arthur; Cross, Jesse S. (Missouri University of Science and Technology, Rolla, MO)

    2011-09-01

    The number of PDF files with embedded malicious code has risen significantly in the past few years. This is due to the portability of the file format, the ways Adobe Reader recovers from corrupt PDF files, the addition of many multimedia and scripting extensions to the file format, and many format properties the malware author may use to disguise the presence of malware. Current research focuses on executable, MS Office, and HTML formats. In this paper, several features and properties of PDF Files are identified. Features are extracted using an instrumented open source PDF viewer. The feature descriptions of benign and malicious PDFs can be used to construct a machine learning model for detecting possible malware in future PDF files. The detection rate of PDF malware by current antivirus software is very low. A PDF file is easy to edit and manipulate because it is a text format, providing a low barrier to malware authors. Analyzing PDF files for malware is nonetheless difficult because of (a) the complexity of the formatting language, (b) the parsing idiosyncrasies in Adobe Reader, and (c) undocumented correction techniques employed in Adobe Reader. In May 2011, Esparza demonstrated that PDF malware could be hidden from 42 of 43 antivirus packages by combining multiple obfuscation techniques [4]. One reason current antivirus software fails is the ease of varying byte sequences in PDF malware, thereby rendering conventional signature-based virus detection useless. The compression and encryption functions produce sequences of bytes that are each functions of multiple input bytes. As a result, padding the malware payload with some whitespace before compression/encryption can change many of the bytes in the final payload. In this study we analyzed a corpus of 2591 benign and 87 malicious PDF files. While this corpus is admittedly small, it allowed us to test a system for collecting indicators of embedded PDF malware. We will call these indicators features throughout

  5. Hardwood species classification with DWT based hybrid texture feature extraction techniques

    Indian Academy of Sciences (India)

    Arvind R Yadav; R S Anand; M L Dewal; Sangeeta Gupta

    2015-12-01

    In this work, discrete wavelet transform (DWT) based hybrid texture feature extraction techniques have been used to categorize the microscopic images of hardwood species into 75 different classes. Initially, the DWT has been employed to decompose the image up to 7 levels using Daubechies (db3) wavelet as decomposition filter. Further, first-order statistics (FOS) and four variants of local binary pattern (LBP) descriptors are used to acquire distinct features of these images at various levels. The linear support vector machine (SVM), radial basis function (RBF) kernel SVM and random forest classifiers have been employed for classification. The classification accuracy obtained with state-of-the-art and DWT based hybrid texture features using various classifiers are compared. The DWT based FOS-uniform local binary pattern (DWTFOSLBPu2) texture features at the 4th level of image decomposition have produced best classification accuracy of 97.67 ± 0.79% and 98.40 ± 064% for grayscale and RGB images, respectively, using linear SVM classifier. Reduction in feature dataset by minimal redundancy maximal relevance (mRMR) feature selection method is achieved and the best classification accuracy of 99.00 ± 0.79% and 99.20 ± 0.42% have been obtained for DWT based FOS-LBP histogram Fourier features (DWTFOSLBP-HF) technique at the 5th and 6th levels of image decomposition for grayscale and RGB images, respectively, using linear SVM classifier. The DWTFOSLBP-HF features selected with mRMR method has also established superiority amongst the DWT based hybrid texture feature extraction techniques for randomly divided database into different proportions of training and test datasets.

  6. Hyperspectral image classification based on NMF Features Selection Method

    Science.gov (United States)

    Abe, Bolanle T.; Jordaan, J. A.

    2013-12-01

    Hyperspectral instruments are capable of collecting hundreds of images corresponding to wavelength channels for the same area on the earth surface. Due to the huge number of features (bands) in hyperspectral imagery, land cover classification procedures are computationally expensive and pose a problem known as the curse of dimensionality. In addition, higher correlation among contiguous bands increases the redundancy within the bands. Hence, dimension reduction of hyperspectral data is very crucial so as to obtain good classification accuracy results. This paper presents a new feature selection technique. Non-negative Matrix Factorization (NMF) algorithm is proposed to obtain reduced relevant features in the input domain of each class label. This aimed to reduce classification error and dimensionality of classification challenges. Indiana pines of the Northwest Indiana dataset is used to evaluate the performance of the proposed method through experiments of features selection and classification. The Waikato Environment for Knowledge Analysis (WEKA) data mining framework is selected as a tool to implement the classification using Support Vector Machines and Neural Network. The selected features subsets are subjected to land cover classification to investigate the performance of the classifiers and how the features size affects classification accuracy. Results obtained shows that performances of the classifiers are significant. The study makes a positive contribution to the problems of hyperspectral imagery by exploring NMF, SVMs and NN to improve classification accuracy. The performances of the classifiers are valuable for decision maker to consider tradeoffs in method accuracy versus method complexity.

  7. Biosensor method and system based on feature vector extraction

    Science.gov (United States)

    Greenbaum, Elias [Knoxville, TN; Rodriguez, Jr., Miguel; Qi, Hairong [Knoxville, TN; Wang, Xiaoling [San Jose, CA

    2012-04-17

    A method of biosensor-based detection of toxins comprises the steps of providing at least one time-dependent control signal generated by a biosensor in a gas or liquid medium, and obtaining a time-dependent biosensor signal from the biosensor in the gas or liquid medium to be monitored or analyzed for the presence of one or more toxins selected from chemical, biological or radiological agents. The time-dependent biosensor signal is processed to obtain a plurality of feature vectors using at least one of amplitude statistics and a time-frequency analysis. At least one parameter relating to toxicity of the gas or liquid medium is then determined from the feature vectors based on reference to the control signal.

  8. Tournament screening cum EBIC for feature selection with high-dimensional feature spaces

    Institute of Scientific and Technical Information of China (English)

    2009-01-01

    The feature selection characterized by relatively small sample size and extremely high-dimensional feature space is common in many areas of contemporary statistics.The high dimensionality of the feature space causes serious diffculties:(i) the sample correlations between features become high even if the features are stochastically independent;(ii) the computation becomes intractable.These diffculties make conventional approaches either inapplicable or ine?cient.The reduction of dimensionality of the feature space followed by low dimensional approaches appears the only feasible way to tackle the problem.Along this line,we develop in this article a tournament screening cum EBIC approach for feature selection with high dimensional feature space.The procedure of tournament screening mimics that of a tournament.It is shown theoretically that the tournament screening has the sure screening property,a necessary property which should be satisfied by any valid screening procedure.It is demonstrated by numerical studies that the tournament screening cum EBIC approach enjoys desirable properties such as having higher positive selection rate and lower false discovery rate than other approaches.

  9. Feature selection versus feature compression in the building of calibration models from FTIR-spectrophotometry datasets.

    Science.gov (United States)

    Vergara, Alexander; Llobet, Eduard

    2012-01-15

    Undoubtedly, FTIR-spectrophotometry has become a standard in chemical industry for monitoring, on-the-fly, the different concentrations of reagents and by-products. However, representing chemical samples by FTIR spectra, which spectra are characterized by hundreds if not thousands of variables, conveys their own set of particular challenges because they necessitate to be analyzed in a high-dimensional feature space, where many of these features are likely to be highly correlated and many others surely affected by noise. Therefore, identifying a subset of features that preserves the classifier/regressor performance seems imperative prior any attempt to build an appropriate pattern recognition method. In this context, we investigate the benefit of utilizing two different dimensionality reduction methods, namely the minimum Redundancy-Maximum Relevance (mRMR) feature selection scheme and a new self-organized map (SOM) based feature compression, coupled to regression methods to quantitatively analyze two-component liquid samples utilizing FTIR spectrophotometry. Since these methods give us the possibility of selecting a small subset of relevant features from FTIR spectra preserving the statistical characteristics of the target variable being analyzed, we claim that expressing the FTIR spectra by these dimensionality-reduced set of features may be beneficial. We demonstrate the utility of these novel feature selection schemes in quantifying the distinct analytes within their binary mixtures utilizing a FTIR-spectrophotometer.

  10. Real-time hypothesis driven feature extraction on parallel processing architectures

    DEFF Research Database (Denmark)

    Granmo, O.-C.; Jensen, Finn Verner

    2002-01-01

    Feature extraction in content-based indexing of media streams is often computational intensive. Typically, a parallel processing architecture is necessary for real-time performance when extracting features brute force. On the other hand, Bayesian network based systems for hypothesis driven feature......, rather than one-by-one. Thereby, the advantages of parallel feature extraction can be combined with the advantages of hypothesis driven feature extraction. The technique is based on a sequential backward feature set search and a correlation based feature set evaluation function. In order to reduce...

  11. Selective processing of multiple features in the human brain: effects of feature type and salience.

    Science.gov (United States)

    McGinnis, E Menton; Keil, Andreas

    2011-02-09

    Identifying targets in a stream of items at a given constant spatial location relies on selection of aspects such as color, shape, or texture. Such attended (target) features of a stimulus elicit a negative-going event-related brain potential (ERP), termed Selection Negativity (SN), which has been used as an index of selective feature processing. In two experiments, participants viewed a series of Gabor patches in which targets were defined as a specific combination of color, orientation, and shape. Distracters were composed of different combinations of color, orientation, and shape of the target stimulus. This design allows comparisons of items with and without specific target features. Consistent with previous ERP research, SN deflections extended between 160-300 ms. Data from the subsequent P3 component (300-450 ms post-stimulus) were also examined, and were regarded as an index of target processing. In Experiment A, predominant effects of target color on SN and P3 amplitudes were found, along with smaller ERP differences in response to variations of orientation and shape. Manipulating color to be less salient while enhancing the saliency of the orientation of the Gabor patch (Experiment B) led to delayed color selection and enhanced orientation selection. Topographical analyses suggested that the location of SN on the scalp reliably varies with the nature of the to-be-attended feature. No interference of non-target features on the SN was observed. These results suggest that target feature selection operates by means of electrocortical facilitation of feature-specific sensory processes, and that selective electrocortical facilitation is more effective when stimulus saliency is heightened.

  12. Selective processing of multiple features in the human brain: effects of feature type and salience.

    Directory of Open Access Journals (Sweden)

    E Menton McGinnis

    Full Text Available Identifying targets in a stream of items at a given constant spatial location relies on selection of aspects such as color, shape, or texture. Such attended (target features of a stimulus elicit a negative-going event-related brain potential (ERP, termed Selection Negativity (SN, which has been used as an index of selective feature processing. In two experiments, participants viewed a series of Gabor patches in which targets were defined as a specific combination of color, orientation, and shape. Distracters were composed of different combinations of color, orientation, and shape of the target stimulus. This design allows comparisons of items with and without specific target features. Consistent with previous ERP research, SN deflections extended between 160-300 ms. Data from the subsequent P3 component (300-450 ms post-stimulus were also examined, and were regarded as an index of target processing. In Experiment A, predominant effects of target color on SN and P3 amplitudes were found, along with smaller ERP differences in response to variations of orientation and shape. Manipulating color to be less salient while enhancing the saliency of the orientation of the Gabor patch (Experiment B led to delayed color selection and enhanced orientation selection. Topographical analyses suggested that the location of SN on the scalp reliably varies with the nature of the to-be-attended feature. No interference of non-target features on the SN was observed. These results suggest that target feature selection operates by means of electrocortical facilitation of feature-specific sensory processes, and that selective electrocortical facilitation is more effective when stimulus saliency is heightened.

  13. A New Feature Selection Algorithm Based on the Mean Impact Variance

    Directory of Open Access Journals (Sweden)

    Weidong Cheng

    2014-01-01

    Full Text Available The selection of fewer or more representative features from multidimensional features is important when the artificial neural network (ANN algorithm is used as a classifier. In this paper, a new feature selection method called the mean impact variance (MIVAR method is proposed to determine the feature that is more suitable for classification. Moreover, this method is constructed on the basis of the training process of the ANN algorithm. To verify the effectiveness of the proposed method, the MIVAR value is used to rank the multidimensional features of the bearing fault diagnosis. In detail, (1 70-dimensional all waveform features are extracted from a rolling bearing vibration signal with four different operating states, (2 the corresponding MIVAR values of all 70-dimensional features are calculated to rank all features, (3 14 groups of 10-dimensional features are separately generated according to the ranking results and the principal component analysis (PCA algorithm and a back propagation (BP network is constructed, and (4 the validity of the ranking result is proven by training this BP network with these seven groups of 10-dimensional features and by comparing the corresponding recognition rates. The results prove that the features with larger MIVAR value can lead to higher recognition rates.

  14. An Improved AAM Method for Extracting Human Facial Features

    Directory of Open Access Journals (Sweden)

    Tao Zhou

    2012-01-01

    Full Text Available Active appearance model is a statistically parametrical model, which is widely used to extract human facial features and recognition. However, intensity values used in original AAM cannot provide enough information for image texture, which will lead to a larger error or a failure fitting of AAM. In order to overcome these defects and improve the fitting performance of AAM model, an improved texture representation is proposed in this paper. Firstly, translation invariant wavelet transform is performed on face images and then image structure is represented using the measure which is obtained by fusing the low-frequency coefficients with edge intensity. Experimental results show that the improved algorithm can increase the accuracy of the AAM fitting and express more information for structures of edge and texture.

  15. Analyzing edge detection techniques for feature extraction in dental radiographs

    Directory of Open Access Journals (Sweden)

    Kanika Lakhani

    2016-09-01

    Full Text Available Several dental problems can be detected using radiographs but the main issue with radiographs is that they are not very prominent. In this paper, two well known edge detection techniques have been implemented for a set of 20 radiographs and number of pixels in each image has been calculated. Further, Gaussian filter has been applied over the images to smoothen the images so as to highlight the defect in the tooth. If the images data are available in the form of pixels for both healthy and decayed tooth, the images can easily be compared using edge detection techniques and the diagnosis is much easier. Further, Laplacian edge detection technique is applied to sharpen the edges of the given image. The aim is to detect discontinuities in dental radiographs when compared to original healthy tooth. Future work includes the feature extraction on the images for the classification of dental problems.

  16. Research on Feature Extraction of Remnant Particles of Aerospace Relays

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    The existence of remnant particles, which significantly reduce the reliability of relays, is a serious problem for aerospace relays.The traditional method for detecting remnant particles-particle impact noise detection (PIND)-can be used merely to detect the existence of the particle; it is not able to provide any information about the particles' material. However, information on the material of the particles is very helpful for analyzing the causes of remnants. By analyzing the output acoustic signals from a PIND tester, this paper proposes three feature extraction methods: unit energy average pulse durative time, shape parameter of signal power spectral density(PSD), and pulse linear predictive coding coefficient sequence. These methods allow identified remnants to be classified into four categories based on their material. Furthermore, we prove the validity of this new method by processing PIND signals from actual tests.

  17. Transmission line icing prediction based on DWT feature extraction

    Science.gov (United States)

    Ma, T. N.; Niu, D. X.; Huang, Y. L.

    2016-08-01

    Transmission line icing prediction is the premise of ensuring the safe operation of the network as well as the very important basis for the prevention of freezing disasters. In order to improve the prediction accuracy of icing, a transmission line icing prediction model based on discrete wavelet transform (DWT) feature extraction was built. In this method, a group of high and low frequency signals were obtained by DWT decomposition, and were fitted and predicted by using partial least squares regression model (PLS) and wavelet least square support vector model (w-LSSVM). Finally, the final result of the icing prediction was obtained by adding the predicted values of the high and low frequency signals. The results showed that the method is effective and feasible in the prediction of transmission line icing.

  18. New feature extraction in gene expression data for tumor classification

    Institute of Scientific and Technical Information of China (English)

    HE Renya; CHENG Qiansheng; WU Lianwen; YUAN Kehong

    2005-01-01

    Using gene expression data to discriminate tumor from the normal ones is a powerful method. However, it is sometimes difficult because the gene expression data are in high dimension and the object number of the data sets is very small. The key technique is to find a new gene expression profiling that can provide understanding and insight into tumor related cellular processes. In this paper, we propose a new feature extraction method based on variance to the center of the class and employ the support vector machine to recognize the gene data either normal or tumor. Two tumor data sets are used to demonstrate the effectiveness of our methods. The results show that the performance has been significantly improved.

  19. Online feature extraction for the PANDA electromagnetic calorimeter

    Energy Technology Data Exchange (ETDEWEB)

    Guliyev, Elmaddin; Tambave, Ganesh; Kavatsyuk, Myroslav; Loehner, Herbert [KVI, University of Groningen (Netherlands); Collaboration: PANDA-Collaboration

    2011-07-01

    Resonances in the charmonium mass region will be studied in antiproton annihilations at FAIR with the multi-purpose PANDA spectrometer providing measurements of electromagnetic signals in a wide dynamic range. The Sampling ADC (SADC) readout of the Electromagnetic Calorimeter (EMC) will allow to realize online hit-detection on the single-channel level and to derive time and energy information. A digital filtering and feature-extraction algorithm was developed and implemented in VHDL code for the online application in a commercial SADC. We discuss the readout scheme, the program logic, the precise signal amplitude detection with phase correction at low sampling frequencies, and the usage of a double moving-window deconvolution filter for the pulse-shape restoration. Such double filtering allows to operate the EMC at much higher rates and to minimize the amount of pile-up events.

  20. PCA Fault Feature Extraction in Complex Electric Power Systems

    Directory of Open Access Journals (Sweden)

    ZHANG, J.

    2010-08-01

    Full Text Available Electric power system is one of the most complex artificial systems in the world. The complexity is determined by its characteristics about constitution, configuration, operation, organization, etc. The fault in electric power system cannot be completely avoided. When electric power system operates from normal state to failure or abnormal, its electric quantities (current, voltage and angles, etc. may change significantly. Our researches indicate that the variable with the biggest coefficient in principal component usually corresponds to the fault. Therefore, utilizing real-time measurements of phasor measurement unit, based on principal components analysis technology, we have extracted successfully the distinct features of fault component. Of course, because of the complexity of different types of faults in electric power system, there still exists enormous problems need a close and intensive study.

  1. Entropy based unsupervised Feature Selection in digital mammogram image using rough set theory.

    Science.gov (United States)

    Velayutham, C; Thangavel, K

    2012-01-01

    Feature Selection (FS) is a process, which attempts to select features, which are more informative. In the supervised FS methods various feature subsets are evaluated using an evaluation function or metric to select only those features, which are related to the decision classes of the data under consideration. However, for many data mining applications, decision class labels are often unknown or incomplete, thus indicating the significance of unsupervised FS. However, in unsupervised learning, decision class labels are not provided. The problem is that not all features are important. Some of the features may be redundant, and others may be irrelevant and noisy. In this paper, a novel unsupervised FS in mammogram image, using rough set-based entropy measures, is proposed. A typical mammogram image processing system generally consists of mammogram image acquisition, pre-processing of image, segmentation, features extracted from the segmented mammogram image. The proposed method is used to select features from data set, the method is compared with the existing rough set-based supervised FS methods and classification performance of both methods are recorded and demonstrates the efficiency of the method.

  2. Informative Feature Selection for Object Recognition via Sparse PCA

    Science.gov (United States)

    2011-04-07

    the BMW database [17] are used for training. For each image pair in SfM, SURF features are deemed informative if the consensus of the corresponding...observe that the first two sparse PVs are sufficient for selecting in- formative features that lie on the foreground objects in the BMW database (as... BMW ) database [17]. The database consists of multiple-view images of 20 landmark buildings on the Berkeley campus. For each building, wide-baseline

  3. FEATURE EXTRACTION OF BONES AND SKIN BASED ON ULTRASONIC SCANNING

    Institute of Scientific and Technical Information of China (English)

    Zheng Shuxian; Zhao Wanhua; Lu Bingheng; Zhao Zhao

    2005-01-01

    In the prosthetic socket design, aimed at the high cost and radiation deficiency caused by CT scanning which is a routine technique to obtain the cross-sectional image of the residual limb, a new ultrasonic scanning method is developed to acquire the bones and skin contours of the residual limb. Using a pig fore-leg as the scanning object, an overlapping algorithm is designed to reconstruct the 2D cross-sectional image, the contours of the bone and skin are extracted using edge detection algorithm and the 3D model of the pig fore-leg is reconstructed by using reverse engineering technology. The results of checking the accuracy of the image by scanning a cylinder work pieces show that the extracted contours of the cylinder are quite close to the standard circumference. So it is feasible to get the contours of bones and skin by ultrasonic scanning. The ultrasonic scanning system featuring no radiation and low cost is a kind of new means of cross section scanning for medical images.

  4. Selecting Features of Single Lead ECG Signal for Automatic Sleep Stages Classification using Correlation-based Feature Subset Selection

    Directory of Open Access Journals (Sweden)

    Ary Noviyanto

    2011-09-01

    Full Text Available Knowing about our sleep quality will help human life to maximize our life performance. ECG signal has potency to determine the sleep stages so that sleep quality can be measured. The data that used in this research is single lead ECG signal from the MIT-BIH Polysomnographic Database. The ECGs features can be derived from RR interval, EDR information and raw ECG signal. Correlation-based Feature Subset Selection (CFS is used to choose the features which are significant to determine the sleep stages. Those features will be evaluated using four different characteristic classifiers (Bayesian network, multilayer perceptron, IB1 and random forest. Performance evaluations by Bayesian network, IB1 and random forest show that CFS performs excellent. It can reduce the number of features significantly with small decreasing accuracy. The best classification result based on this research is a combination of the feature set derived from raw ECG signal and the random forest classifier.

  5. Extraction of Facial Feature Points Using Cumulative Histogram

    CERN Document Server

    Paul, Sushil Kumar; Bouakaz, Saida

    2012-01-01

    This paper proposes a novel adaptive algorithm to extract facial feature points automatically such as eyebrows corners, eyes corners, nostrils, nose tip, and mouth corners in frontal view faces, which is based on cumulative histogram approach by varying different threshold values. At first, the method adopts the Viola-Jones face detector to detect the location of face and also crops the face region in an image. From the concept of the human face structure, the six relevant regions such as right eyebrow, left eyebrow, right eye, left eye, nose, and mouth areas are cropped in a face image. Then the histogram of each cropped relevant region is computed and its cumulative histogram value is employed by varying different threshold values to create a new filtering image in an adaptive way. The connected component of interested area for each relevant filtering image is indicated our respective feature region. A simple linear search algorithm for eyebrows, eyes and mouth filtering images and contour algorithm for nos...

  6. Texture features analysis for coastline extraction in remotely sensed images

    Science.gov (United States)

    De Laurentiis, Raimondo; Dellepiane, Silvana G.; Bo, Giancarlo

    2002-01-01

    The accurate knowledge of the shoreline position is of fundamental importance in several applications such as cartography and ships positioning1. Moreover, the coastline could be seen as a relevant parameter for the monitoring of the coastal zone morphology, as it allows the retrieval of a much more precise digital elevation model of the entire coastal area. The study that has been carried out focuses on the development of a reliable technique for the detection of coastlines in remotely sensed images. An innovative approach which is based on the concepts of fuzzy connectivity and texture features extraction has been developed for the location of the shoreline. The system has been tested on several kind of images as SPOT, LANDSAT and the results obtained are good. Moreover, the algorithm has been tested on a sample of a SAR interferogram. The breakthrough consists in the fact that the coastline detection is seen as an important features in the framework of digital elevation model (DEM) retrieval. In particular, the coast could be seen as a boundary line all data beyond which (the ones representing the sea) are not significant. The processing for the digital elevation model could be refined, just considering the in-land data.

  7. Pomegranate peel and peel extracts: chemistry and food features.

    Science.gov (United States)

    Akhtar, Saeed; Ismail, Tariq; Fraternale, Daniele; Sestili, Piero

    2015-05-01

    The present review focuses on the nutritional, functional and anti-infective properties of pomegranate (Punica granatum L.) peel (PoP) and peel extract (PoPx) and on their applications as food additives, functional food ingredients or biologically active components in nutraceutical preparations. Due to their well-known ethnomedical relevance and chemical features, the biomolecules available in PoP and PoPx have been proposed, for instance, as substitutes of synthetic food additives, as nutraceuticals and chemopreventive agents. However, because of their astringency and anti-nutritional properties, PoP and PoPx are not yet considered as ingredients of choice in food systems. Indeed, considering the prospects related to both their health promoting activity and chemical features, the nutritional and nutraceutical potential of PoP and PoPx seems to be still underestimated. The present review meticulously covers the wide range of actual and possible applications (food preservatives, stabilizers, supplements, prebiotics and quality enhancers) of PoP and PoPx components in various food products. Given the overall properties of PoP and PoPx, further investigations in toxicological and sensory aspects of PoP and PoPx should be encouraged to fully exploit the health promoting and technical/economic potential of these waste materials as food supplements.

  8. How can selection of biologically inspired features improve the performance of a robust object recognition model?

    Directory of Open Access Journals (Sweden)

    Masoud Ghodrati

    Full Text Available Humans can effectively and swiftly recognize objects in complex natural scenes. This outstanding ability has motivated many computational object recognition models. Most of these models try to emulate the behavior of this remarkable system. The human visual system hierarchically recognizes objects in several processing stages. Along these stages a set of features with increasing complexity is extracted by different parts of visual system. Elementary features like bars and edges are processed in earlier levels of visual pathway and as far as one goes upper in this pathway more complex features will be spotted. It is an important interrogation in the field of visual processing to see which features of an object are selected and represented by the visual cortex. To address this issue, we extended a hierarchical model, which is motivated by biology, for different object recognition tasks. In this model, a set of object parts, named patches, extracted in the intermediate stages. These object parts are used for training procedure in the model and have an important role in object recognition. These patches are selected indiscriminately from different positions of an image and this can lead to the extraction of non-discriminating patches which eventually may reduce the performance. In the proposed model we used an evolutionary algorithm approach to select a set of informative patches. Our reported results indicate that these patches are more informative than usual random patches. We demonstrate the strength of the proposed model on a range of object recognition tasks. The proposed model outperforms the original model in diverse object recognition tasks. It can be seen from the experiments that selected features are generally particular parts of target images. Our results suggest that selected features which are parts of target objects provide an efficient set for robust object recognition.

  9. How can selection of biologically inspired features improve the performance of a robust object recognition model?

    Science.gov (United States)

    Ghodrati, Masoud; Khaligh-Razavi, Seyed-Mahdi; Ebrahimpour, Reza; Rajaei, Karim; Pooyan, Mohammad

    2012-01-01

    Humans can effectively and swiftly recognize objects in complex natural scenes. This outstanding ability has motivated many computational object recognition models. Most of these models try to emulate the behavior of this remarkable system. The human visual system hierarchically recognizes objects in several processing stages. Along these stages a set of features with increasing complexity is extracted by different parts of visual system. Elementary features like bars and edges are processed in earlier levels of visual pathway and as far as one goes upper in this pathway more complex features will be spotted. It is an important interrogation in the field of visual processing to see which features of an object are selected and represented by the visual cortex. To address this issue, we extended a hierarchical model, which is motivated by biology, for different object recognition tasks. In this model, a set of object parts, named patches, extracted in the intermediate stages. These object parts are used for training procedure in the model and have an important role in object recognition. These patches are selected indiscriminately from different positions of an image and this can lead to the extraction of non-discriminating patches which eventually may reduce the performance. In the proposed model we used an evolutionary algorithm approach to select a set of informative patches. Our reported results indicate that these patches are more informative than usual random patches. We demonstrate the strength of the proposed model on a range of object recognition tasks. The proposed model outperforms the original model in diverse object recognition tasks. It can be seen from the experiments that selected features are generally particular parts of target images. Our results suggest that selected features which are parts of target objects provide an efficient set for robust object recognition.

  10. An Efficient Method for Automatic Road Extraction Based on Multiple Features from LiDAR Data

    Science.gov (United States)

    Li, Y.; Hu, X.; Guan, H.; Liu, P.

    2016-06-01

    The road extraction in urban areas is difficult task due to the complicated patterns and many contextual objects. LiDAR data directly provides three dimensional (3D) points with less occlusions and smaller shadows. The elevation information and surface roughness are distinguishing features to separate roads. However, LiDAR data has some disadvantages are not beneficial to object extraction, such as the irregular distribution of point clouds and lack of clear edges of roads. For these problems, this paper proposes an automatic road centerlines extraction method which has three major steps: (1) road center point detection based on multiple feature spatial clustering for separating road points from ground points, (2) local principal component analysis with least squares fitting for extracting the primitives of road centerlines, and (3) hierarchical grouping for connecting primitives into complete roads network. Compared with MTH (consist of Mean shift algorithm, Tensor voting, and Hough transform) proposed in our previous article, this method greatly reduced the computational cost. To evaluate the proposed method, the Vaihingen data set, a benchmark testing data provided by ISPRS for "Urban Classification and 3D Building Reconstruction" project, was selected. The experimental results show that our method achieve the same performance by less time in road extraction using LiDAR data.

  11. Spatial selection of features within perceived and remembered objects

    Directory of Open Access Journals (Sweden)

    Duncan E Astle

    2009-04-01

    Full Text Available Our representation of the visual world can be modulated by spatially specific attentional biases that depend flexibly on task goals. We compared searching for task-relevant features in perceived versus remembered objects. When searching perceptual input, selected task-relevant and suppressed task-irrelevant features elicited contrasting spatiotopic ERP effects, despite them being perceptually identical. This was also true when participants searched a memory array, suggesting that memory had retained the spatial organisation of the original perceptual input and that this representation could be modulated in a spatially specific fashion. However, task-relevant selection and task-irrelevant suppression effects were of the opposite polarity when searching remembered compared to perceived objects. We suggest that this surprising result stems from the nature of feature- and object-based representations when stored in visual short-term memory. When stored, features are integrated into objects, meaning that the spatially specific selection mechanisms must operate upon objects rather than specific feature-level representations.

  12. Technical Evaluation Report 27: Educational Wikis: Features and selection criteria

    Directory of Open Access Journals (Sweden)

    Jim Rudolph

    2004-04-01

    Full Text Available This report discusses the educational uses of the ‘wiki,’ an increasingly popular approach to online community development. Wikis are defined and compared with ‘blogging’ methods; characteristics of major wiki engines are described; and wiki features and selection criteria are examined.

  13. Variance Ranklets : Orientation-selective rank features for contrast modulations

    NARCIS (Netherlands)

    Azzopardi, George; Smeraldi, Fabrizio

    2009-01-01

    We introduce a novel type of orientation–selective rank features that are sensitive to contrast modulations (second–order stimuli). Variance Ranklets are designed in close analogy with the standard Ranklets, but use the Siegel–Tukey statistics for dispersion instead of the Wilcoxon statistics. Their

  14. Emotion of Physiological Signals Classification Based on TS Feature Selection

    Institute of Scientific and Technical Information of China (English)

    Wang Yujing; Mo Jianlin

    2015-01-01

    This paper propose a method of TS-MLP about emotion recognition of physiological signal.It can recognize emotion successfully by Tabu search which selects features of emotion’s physiological signals and multilayer perceptron that is used to classify emotion.Simulation shows that it has achieved good emotion classification performance.

  15. Biometric hashing for handwriting: entropy-based feature selection and semantic fusion

    Science.gov (United States)

    Scheidat, Tobias; Vielhauer, Claus

    2008-02-01

    Some biometric algorithms lack of the problem of using a great number of features, which were extracted from the raw data. This often results in feature vectors of high dimensionality and thus high computational complexity. However, in many cases subsets of features do not contribute or with only little impact to the correct classification of biometric algorithms. The process of choosing more discriminative features from a given set is commonly referred to as feature selection. In this paper we present a study on feature selection for an existing biometric hash generation algorithm for the handwriting modality, which is based on the strategy of entropy analysis of single components of biometric hash vectors, in order to identify and suppress elements carrying little information. To evaluate the impact of our feature selection scheme to the authentication performance of our biometric algorithm, we present an experimental study based on data of 86 users. Besides discussing common biometric error rates such as Equal Error Rates, we suggest a novel measurement to determine the reproduction rate probability for biometric hashes. Our experiments show that, while the feature set size may be significantly reduced by 45% using our scheme, there are marginal changes both in the results of a verification process as well as in the reproducibility of biometric hashes. Since multi-biometrics is a recent topic, we additionally carry out a first study on a pair wise multi-semantic fusion based on reduced hashes and analyze it by the introduced reproducibility measure.

  16. Auditory-model based robust feature selection for speech recognition.

    Science.gov (United States)

    Koniaris, Christos; Kuropatwinski, Marcin; Kleijn, W Bastiaan

    2010-02-01

    It is shown that robust dimension-reduction of a feature set for speech recognition can be based on a model of the human auditory system. Whereas conventional methods optimize classification performance, the proposed method exploits knowledge implicit in the auditory periphery, inheriting its robustness. Features are selected to maximize the similarity of the Euclidean geometry of the feature domain and the perceptual domain. Recognition experiments using mel-frequency cepstral coefficients (MFCCs) confirm the effectiveness of the approach, which does not require labeled training data. For noisy data the method outperforms commonly used discriminant-analysis based dimension-reduction methods that rely on labeling. The results indicate that selecting MFCCs in their natural order results in subsets with good performance.

  17. Review and Evaluation of Feature Selection Algorithms in Synthetic Problems

    CERN Document Server

    Belanche, L A

    2011-01-01

    The main purpose of Feature Subset Selection is to find a reduced subset of attributes from a data set described by a feature set. The task of a feature selection algorithm (FSA) is to provide with a computational solution motivated by a certain definition of relevance or by a reliable evaluation measure. In this paper several fundamental algorithms are studied to assess their performance in a controlled experimental scenario. A measure to evaluate FSAs is devised that computes the degree of matching between the output given by a FSA and the known optimal solutions. An extensive experimental study on synthetic problems is carried out to assess the behaviour of the algorithms in terms of solution accuracy and size as a function of the relevance, irrelevance, redundancy and size of the data samples. The controlled experimental conditions facilitate the derivation of better-supported and meaningful conclusions.

  18. Feature selection for high-dimensional integrated data

    KAUST Repository

    Zheng, Charles

    2012-04-26

    Motivated by the problem of identifying correlations between genes or features of two related biological systems, we propose a model of feature selection in which only a subset of the predictors Xt are dependent on the multidimensional variate Y, and the remainder of the predictors constitute a “noise set” Xu independent of Y. Using Monte Carlo simulations, we investigated the relative performance of two methods: thresholding and singular-value decomposition, in combination with stochastic optimization to determine “empirical bounds” on the small-sample accuracy of an asymptotic approximation. We demonstrate utility of the thresholding and SVD feature selection methods to with respect to a recent infant intestinal gene expression and metagenomics dataset.

  19. Feature Selection based on Machine Learning in MRIs for Hippocampal Segmentation

    CERN Document Server

    Tangaro, Sabina; Brescia, Massimo; Cavuoti, Stefano; Chincarini, Andrea; Errico, Rosangela; Inglese, Paolo; Longo, Giuseppe; Maglietta, Rosalia; Tateo, Andrea; Riccio, Giuseppe; Bellotti, Roberto

    2015-01-01

    Neurodegenerative diseases are frequently associated with structural changes in the brain. Magnetic Resonance Imaging (MRI) scans can show these variations and therefore be used as a supportive feature for a number of neurodegenerative diseases. The hippocampus has been known to be a biomarker for Alzheimer disease and other neurological and psychiatric diseases. However, it requires accurate, robust and reproducible delineation of hippocampal structures. Fully automatic methods are usually the voxel based approach, for each voxel a number of local features were calculated. In this paper we compared four different techniques for feature selection from a set of 315 features extracted for each voxel: (i) filter method based on the Kolmogorov-Smirnov test; two wrapper methods, respectively, (ii) Sequential Forward Selection and (iii) Sequential Backward Elimination; and (iv) embedded method based on the Random Forest Classifier on a set of 10 T1-weighted brain MRIs and tested on an independent set of 25 subjects...

  20. Application of Fisher Score and mRMR Techniques for Feature Selection in Compressed Medical Images

    Directory of Open Access Journals (Sweden)

    Vamsidhar Enireddy

    2015-12-01

    Full Text Available In nowadays there is a large increase in the digital medical images and different medical imaging equipments are available for diagnoses, medical professionals are increasingly relying on computer aided techniques for both indexing these images and retrieving similar images from large repositories. To develop systems which are computationally less intensive without compromising on the accuracy from the high dimensional feature space is always challenging. In this paper an investigation is made on the retrieval of compressed medical images. Images are compressed using the visually lossless compression technique. Shape and texture features are extracted and best features are selected using the fisher technique and mRMR. Using these selected features RNN with BPTT was utilized for classification of the compressed images.

  1. Comparison of Genetic Algorithm, Particle Swarm Optimization and Biogeography-based Optimization for Feature Selection to Classify Clusters of Microcalcifications

    Science.gov (United States)

    Khehra, Baljit Singh; Pharwaha, Amar Partap Singh

    2016-06-01

    Ductal carcinoma in situ (DCIS) is one type of breast cancer. Clusters of microcalcifications (MCCs) are symptoms of DCIS that are recognized by mammography. Selection of robust features vector is the process of selecting an optimal subset of features from a large number of available features in a given problem domain after the feature extraction and before any classification scheme. Feature selection reduces the feature space that improves the performance of classifier and decreases the computational burden imposed by using many features on classifier. Selection of an optimal subset of features from a large number of available features in a given problem domain is a difficult search problem. For n features, the total numbers of possible subsets of features are 2n. Thus, selection of an optimal subset of features problem belongs to the category of NP-hard problems. In this paper, an attempt is made to find the optimal subset of MCCs features from all possible subsets of features using genetic algorithm (GA), particle swarm optimization (PSO) and biogeography-based optimization (BBO). For simulation, a total of 380 benign and malignant MCCs samples have been selected from mammogram images of DDSM database. A total of 50 features extracted from benign and malignant MCCs samples are used in this study. In these algorithms, fitness function is correct classification rate of classifier. Support vector machine is used as a classifier. From experimental results, it is also observed that the performance of PSO-based and BBO-based algorithms to select an optimal subset of features for classifying MCCs as benign or malignant is better as compared to GA-based algorithm.

  2. Research on Heuristic Feature Extraction and Classification of EEG Signal Based on BCI Data Set

    Directory of Open Access Journals (Sweden)

    Lijuan Duan

    2013-01-01

    Full Text Available In this study, an EEG signal classification framework was proposed. The framework contained three feature extraction methods refer to optimization strategy. Firstly, we selected optimal electrodes based on the single electrode classification performance and combined all the optimal electrodes’ data as the feature. Then, we discussed the contribution of each time span of EEG signals for each electrode and joined all the optimal time spans’ data together to be used for classifying. In addition, we further selected useful information from original data based on genetic algorithm. Finally, the performances were evaluated by Bayes and SVM classifiers on BCI 2003 Competition data set Ia. And the accuracy of genetic algorithm has reached 91.81%. The experimental results show that our methods offer the better performance for reliable classification of the EEG signal.

  3. Modeling neuron selectivity over simple midlevel features for image classification.

    Science.gov (United States)

    Shu Kong; Zhuolin Jiang; Qiang Yang

    2015-08-01

    We now know that good mid-level features can greatly enhance the performance of image classification, but how to efficiently learn the image features is still an open question. In this paper, we present an efficient unsupervised midlevel feature learning approach (MidFea), which only involves simple operations, such as k-means clustering, convolution, pooling, vector quantization, and random projection. We show this simple feature can also achieve good performance in traditional classification task. To further boost the performance, we model the neuron selectivity (NS) principle by building an additional layer over the midlevel features prior to the classifier. The NS-layer learns category-specific neurons in a supervised manner with both bottom-up inference and top-down analysis, and thus supports fast inference for a query image. Through extensive experiments, we demonstrate that this higher level NS-layer notably improves the classification accuracy with our simple MidFea, achieving comparable performances for face recognition, gender classification, age estimation, and object categorization. In particular, our approach runs faster in inference by an order of magnitude than sparse coding-based feature learning methods. As a conclusion, we argue that not only do carefully learned features (MidFea) bring improved performance, but also a sophisticated mechanism (NS-layer) at higher level boosts the performance further.

  4. AN EFFICIENT APPROACH FOR EXTRACTION OF LINEAR FEATURES FROM HIGH RESOLUTION INDIAN SATELLITE IMAGERIES

    Directory of Open Access Journals (Sweden)

    DK Bhattacharyya

    2010-07-01

    Full Text Available This paper presents an Object oriented feature extraction approach in order to classify the linear features like drainage, roads etc. from high resolution Indian satellite imageries. It starts with the multiresolution segmentations of image objects for optimal separation and representation of image regions or objects. Fuzzy membership functions were defined for a selected set of image object parameters such as mean, ratio, shape index, area etc. for representation of required image objects. Experiment was carried out for both panchromatic (CARTOSAT-I and multispectral (IRSP6 LISS IV Indiansatellite imageries. Experimental results show that the extractionof linear features can be achieved in a satisfactory level throughproper segmentation and appropriate definition & representationof key parameters of image objects.

  5. iPcc: a novel feature extraction method for accurate disease class discovery and prediction.

    Science.gov (United States)

    Ren, Xianwen; Wang, Yong; Zhang, Xiang-Sun; Jin, Qi

    2013-08-01

    Gene expression profiling has gradually become a routine procedure for disease diagnosis and classification. In the past decade, many computational methods have been proposed, resulting in great improvements on various levels, including feature selection and algorithms for classification and clustering. In this study, we present iPcc, a novel method from the feature extraction perspective to further propel gene expression profiling technologies from bench to bedside. We define 'correlation feature space' for samples based on the gene expression profiles by iterative employment of Pearson's correlation coefficient. Numerical experiments on both simulated and real gene expression data sets demonstrate that iPcc can greatly highlight the latent patterns underlying noisy gene expression data and thus greatly improve the robustness and accuracy of the algorithms currently available for disease diagnosis and classification based on gene expression profiles.

  6. Automatic layout feature extraction for lithography hotspot detection based on deep neural network

    Science.gov (United States)

    Matsunawa, Tetsuaki; Nojima, Shigeki; Kotani, Toshiya

    2016-03-01

    Lithography hotspot detection in the physical verification phase is one of the most important techniques in today's optical lithography based manufacturing process. Although lithography simulation based hotspot detection is widely used, it is also known to be time-consuming. To detect hotspots in a short runtime, several machine learning based methods have been proposed. However, it is difficult to realize highly accurate detection without an increase in false alarms because an appropriate layout feature is undefined. This paper proposes a new method to automatically extract a proper layout feature from a given layout for improvement in detection performance of machine learning based methods. Experimental results show that using a deep neural network can achieve better performance than other frameworks using manually selected layout features and detection algorithms, such as conventional logistic regression or artificial neural network.

  7. Research into a Feature Selection Method for Hyperspectral Imagery Using PSO and SVM

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    Classification and recognition of hyperspectral remote sensing images is not the same as that of conventional multi-spectral remote sensing images.We propose, a novel feature selection and classification method for hyperspectral images by combining the global optimization ability of particle swarm optimization (PSO) algorithm and the superior classification performance of a support vector machine (SVM).Global optimal search performance of PSO is improved by using a chaotic optimization search technique.Granularity based grid search strategy is used to optimize the SVM model parameters.Parameter optimization and classification of the SVM are addressed using the training date corresponding to the feature subset.A false classification rate is adopted as a fitness function.Tests of feature selection and classification are carried out on a hyperspectral data set.Classification performances are also compared among different feature extraction methods commonly used today.Results indicate that this hybrid method has a higher classification accuracy and can effectively extract optimal bands.A feasible approach is provided for feature selection and classification of hyperspectral image data.

  8. Economic indicators selection for crime rates forecasting using cooperative feature selection

    Science.gov (United States)

    Alwee, Razana; Shamsuddin, Siti Mariyam Hj; Salleh Sallehuddin, Roselina

    2013-04-01

    Features selection in multivariate forecasting model is very important to ensure that the model is accurate. The purpose of this study is to apply the Cooperative Feature Selection method for features selection. The features are economic indicators that will be used in crime rate forecasting model. The Cooperative Feature Selection combines grey relational analysis and artificial neural network to establish a cooperative model that can rank and select the significant economic indicators. Grey relational analysis is used to select the best data series to represent each economic indicator and is also used to rank the economic indicators according to its importance to the crime rate. After that, the artificial neural network is used to select the significant economic indicators for forecasting the crime rates. In this study, we used economic indicators of unemployment rate, consumer price index, gross domestic product and consumer sentiment index, as well as data rates of property crime and violent crime for the United States. Levenberg-Marquardt neural network is used in this study. From our experiments, we found that consumer price index is an important economic indicator that has a significant influence on the violent crime rate. While for property crime rate, the gross domestic product, unemployment rate and consumer price index are the influential economic indicators. The Cooperative Feature Selection is also found to produce smaller errors as compared to Multiple Linear Regression in forecasting property and violent crime rates.

  9. Feature extraction and models for speech: An overview

    Science.gov (United States)

    Schroeder, Manfred

    2002-11-01

    Modeling of speech has a long history, beginning with Count von Kempelens 1770 mechanical speaking machine. Even then human vowel production was seen as resulting from a source (the vocal chords) driving a physically separate resonator (the vocal tract). Homer Dudley's 1928 frequency-channel vocoder and many of its descendants are based on the same successful source-filter paradigm. For linguistic studies as well as practical applications in speech recognition, compression, and synthesis (see M. R. Schroeder, Computer Speech), the extant models require the (often difficult) extraction of numerous parameters such as the fundamental and formant frequencies and various linguistic distinctive features. Some of these difficulties were obviated by the introduction of linear predictive coding (LPC) in 1967 in which the filter part is an all-pole filter, reflecting the fact that for non-nasalized vowels the vocal tract is well approximated by an all-pole transfer function. In the now ubiquitous code-excited linear prediction (CELP), the source-part is replaced by a code book which (together with a perceptual error criterion) permits speech compression to very low bit rates at high speech quality for the Internet and cell phones.

  10. An Improved Particle Swarm Optimization for Feature Selection

    Institute of Scientific and Technical Information of China (English)

    Yuanning Liu; Gang Wang; Huiling Chen; Hao Dong; Xiaodong Zhu; Sujing Wang

    2011-01-01

    Particle Swarm Optimization (PSO) is a popular and bionic algorithm based on the social behavior associated with bird flocking for optimization problems. To maintain the diversity of swarms, a few studies of multi-swarm strategy have been reported. However, the competition among swarms, reservation or destruction of a swarm, has not been considered further. In this paper, we formulate four rules by introducing the mechanism for survival of the fittest, which simulates the competition among the swarms. Based on the mechanism, we design a modified Multi-Swarm PSO (MSPSO) to solve discrete problems,which consists of a number of sub-swarms and a multi-swarm scheduler that can monitor and control each sub-swarm using the rules. To further settle the feature selection problems, we propose an Improved Feature Selection (IFS) method by integrating MSPSO, Support Vector Machines (SVM) with F-score method. The IFS method aims to achieve higher generalization capability through performing kernel parameter optimization and feature selection simultaneously. The performance of the proposed method is compared with that of the standard PSO based, Genetic Algorithm (GA) based and the grid search based methods on 10 benchmark datasets, taken from UCI machine learning and StatLog databases. The numerical results and statistical analysis show that the proposed IFS method performs significantly better than the other three methods in terms of prediction accuracy with smaller subset of features.

  11. Electrocardiogram Based Identification using a New Effective Intelligent Selection of Fused Features

    Science.gov (United States)

    Abbaspour, Hamidreza; Razavi, Seyyed Mohammad; Mehrshad, Nasser

    2015-01-01

    Over the years, the feasibility of using Electrocardiogram (ECG) signal for human identification issue has been investigated, and some methods have been suggested. In this research, a new effective intelligent feature selection method from ECG signals has been proposed. This method is developed in such a way that it is able to select important features that are necessary for identification using analysis of the ECG signals. For this purpose, after ECG signal preprocessing, its characterizing features were extracted and then compressed using the cosine transform. The more effective features in the identification, among the characterizing features, are selected using a combination of the genetic algorithm and artificial neural networks. The proposed method was tested on three public ECG databases, namely, MIT-BIH Arrhythmias Database, MITBIH Normal Sinus Rhythm Database and The European ST-T Database, in order to evaluate the proposed subject identification method on normal ECG signals as well as ECG signals with arrhythmias. Identification rates of 99.89% and 99.84% and 99.99% are obtained for these databases respectively. The proposed algorithm exhibits remarkable identification accuracies not only with normal ECG signals, but also in the presence of various arrhythmias. Simulation results showed that the proposed method despite the low number of selected features has a high performance in identification task. PMID:25709939

  12. Making Trillion Correlations Feasible in Feature Grouping and Selection.

    Science.gov (United States)

    Zhai, Yiteng; Ong, Yew-Soon; Tsang, Ivor W

    2016-12-01

    Today, modern databases with "Big Dimensionality" are experiencing a growing trend. Existing approaches that require the calculations of pairwise feature correlations in their algorithmic designs have scored miserably on such databases, since computing the full correlation matrix (i.e., square of dimensionality in size) is computationally very intensive (i.e., million features would translate to trillion correlations). This poses a notable challenge that has received much lesser attention in the field of machine learning and data mining research. Thus, this paper presents a study to fill in this gap. Our findings on several established databases with big dimensionality across a wide spectrum of domains have indicated that an extremely small portion of the feature pairs contributes significantly to the underlying interactions and there exists feature groups that are highly correlated. Inspired by the intriguing observations, we introduce a novel learning approach that exploits the presence of sparse correlations for the efficient identifications of informative and correlated feature groups from big dimensional data that translates to a reduction in complexity from O(m(2)n) to O(mlogm + Ka mn), where Ka strategy, designed to filter out the large number of non-contributing correlations that could otherwise confuse the classifier while identifying the correlated and informative feature groups, forms one of the highlights of our approach. We also demonstrated the proposed method on one-class learning, where notable speedup can be observed when solving one-class problem on big dimensional data. Further, to identify robust informative features with minimal sampling bias, our feature selection strategy embeds the V-fold cross validation in the learning model, so as to seek for features that exhibit stable or consistent performance accuracy on multiple data folds. Extensive empirical studies on both synthetic and several real-world datasets comprising up to 30 million

  13. Improved method for the feature extraction of laser scanner using genetic clustering

    Institute of Scientific and Technical Information of China (English)

    Yu Jinxia; Cai Zixing; Duan Zhuohua

    2008-01-01

    Feature extraction of range images provided by ranging sensor is a key issue of pattern recognition. To automatically extract the environmental feature sensed by a 2D ranging sensor laser scanner, an improved method based on genetic clustering VGA-clustering is presented. By integrating the spatial neighbouring information of range data into fuzzy clustering algorithm, a weighted fuzzy clustering algorithm (WFCA) instead of standard clustering algorithm is introduced to realize feature extraction of laser scanner. Aimed at the unknown clustering number in advance, several validation index functions are used to estimate the validity of different clustering al-gorithms and one validation index is selected as the fitness function of genetic algorithm so as to determine the accurate clustering number automatically. At the same time, an improved genetic algorithm IVGA on the basis of VGA is proposed to solve the local optimum of clustering algorithm, which is implemented by increasing the population diversity and improving the genetic operators of elitist rule to enhance the local search capacity and to quicken the convergence speed. By the comparison with other algorithms, the effectiveness of the algorithm introduced is demonstrated.

  14. Dermoscopic diagnosis of melanoma in a 4D space constructed by active contour extracted features.

    Science.gov (United States)

    Mete, Mutlu; Sirakov, Nikolay Metodiev

    2012-10-01

    Dermoscopy, also known as epiluminescence microscopy, is a major imaging technique used in the assessment of melanoma and other diseases of skin. In this study we propose a computer aided method and tools for fast and automated diagnosis of malignant skin lesions using non-linear classifiers. The method consists of three main stages: (1) skin lesion features extraction from images; (2) features measurement and digitization; and (3) skin lesion binary diagnosis (classification), using the extracted features. A shrinking active contour (S-ACES) extracts color regions boundaries, the number of colors, and lesion's boundary, which is used to calculate the abrupt boundary. Quantification methods for measurements of asymmetry and abrupt endings in skin lesions are elaborated to approach the second stage of the method. The total dermoscopy score (TDS) formula of the ABCD rule is modeled as linear support vector machines (SVM). Further a polynomial SVM classifier is developed. To validate the proposed framework a dataset of 64 lesion images were selected from a collection with a ground truth. The lesions were classified as benign or malignant by the TDS based model and the SVM polynomial classifier. Comparing the results, we showed that the latter model has a better f-measure then the TDS-based model (linear classifier) in the classification of skin lesions into two groups, malignant and benign. Copyright © 2012 Elsevier Ltd. All rights reserved.

  15. Comparative Study on Feature Selection and Fusion Schemes for Emotion Recognition from Speech

    Directory of Open Access Journals (Sweden)

    Santiago Planet

    2012-09-01

    Full Text Available The automatic analysis of speech to detect affective states may improve the way users interact with electronic devices. However, the analysis only at the acoustic level could be not enough to determine the emotion of a user in a realistic scenario. In this paper we analyzed the spontaneous speech recordings of the FAU Aibo Corpus at the acoustic and linguistic levels to extract two sets of features. The acoustic set was reduced by a greedy procedure selecting the most relevant features to optimize the learning stage. We compared two versions of this greedy selection algorithm by performing the search of the relevant features forwards and backwards. We experimented with three classification approaches: Naïve-Bayes, a support vector machine and a logistic model tree, and two fusion schemes: decision-level fusion, merging the hard-decisions of the acoustic and linguistic classifiers by means of a decision tree; and feature-level fusion, concatenating both sets of features before the learning stage. Despite the low performance achieved by the linguistic data, a dramatic improvement was achieved after its combination with the acoustic information, improving the results achieved by this second modality on its own. The results achieved by the classifiers using the parameters merged at feature level outperformed the classification results of the decision-level fusion scheme, despite the simplicity of the scheme. Moreover, the extremely reduced set of acoustic features obtained by the greedy forward search selection algorithm improved the results provided by the full set.

  16. A feature extraction technique based on character geometry for character recognition

    CERN Document Server

    Gaurav, Dinesh Dileep

    2012-01-01

    This paper describes a geometry based technique for feature extraction applicable to segmentation-based word recognition systems. The proposed system extracts the geometric features of the character contour. This features are based on the basic line types that forms the character skeleton. The system gives a feature vector as its output. The feature vectors so generated from a training set, were then used to train a pattern recognition engine based on Neural Networks so that the system can be benchmarked.

  17. A NOVEL SHAPE BASED FEATURE EXTRACTION TECHNIQUE FOR DIAGNOSIS OF LUNG DISEASES USING EVOLUTIONARY APPROACH

    Directory of Open Access Journals (Sweden)

    C. Bhuvaneswari

    2014-07-01

    Full Text Available Lung diseases are one of the most common diseases that affect the human community worldwide. When the diseases are not diagnosed they may lead to serious problems and may even lead to transience. As an outcome to assist the medical community this study helps in detecting some of the lung diseases specifically bronchitis, pneumonia and normal lung images. In this paper, to detect the lung diseases feature extraction is done by the proposed shape based methods, feature selection through the genetics algorithm and the images are classified by the classifier such as MLP-NN, KNN, Bayes Net classifiers and their performances are listed and compared. The shape features are extracted and selected from the input CT images using the image processing techniques and fed to the classifier for categorization. A total of 300 lung CT images were used, out of which 240 are used for training and 60 images were used for testing. Experimental results show that MLP-NN has an accuracy of 86.75 % KNN Classifier has an accuracy of 85.2 % and Bayes net has an accuracy of 83.4% of classification accuracy. The sensitivity, specificity, F-measures, PPV values for the various classifiers are also computed. This concludes that the MLP-NN outperforms all other classifiers.

  18. Extracting Feature Model Changes from the Linux Kernel Using FMDiff

    NARCIS (Netherlands)

    Dintzner, N.J.R.; Van Deursen, A.; Pinzger, M.

    2014-01-01

    The Linux kernel feature model has been studied as an example of large scale evolving feature model and yet details of its evolution are not known. We present here a classification of feature changes occurring on the Linux kernel feature model, as well as a tool, FMDiff, designed to automatically ex

  19. Extracting Feature Model Changes from the Linux Kernel Using FMDiff

    NARCIS (Netherlands)

    Dintzner, N.J.R.; Van Deursen, A.; Pinzger, M.

    2014-01-01

    The Linux kernel feature model has been studied as an example of large scale evolving feature model and yet details of its evolution are not known. We present here a classification of feature changes occurring on the Linux kernel feature model, as well as a tool, FMDiff, designed to automatically

  20. Effects of LiDAR Derived DEM Resolution on Hydrographic Feature Extraction

    Science.gov (United States)

    Yang, P.; Ames, D. P.; Glenn, N. F.; Anderson, D.

    2010-12-01

    This paper examines the effect of LiDAR-derived digital elevation model (DEM) resolution on digitally extracted stream networks with respect to known stream channel locations. Two study sites, Reynolds Creek Experimental Watershed (RCEW) and Dry Creek Experimental Watershed (DCEW), which represent terrain characteristics for lower and intermediate elevation mountainous watersheds in the Intermountain West, were selected as study areas for this research. DEMs reflecting bare earth ground were created from the LiDAR observations at a series of raster cell sizes (from 1 m to 60 m) using spatial interpolation techniques. The effect of DEM resolution on resulting hydrographic feature (specifically stream channel) derivation was studied. Stream length, watershed area, and sinuosity were explored at each of the raster cell sizes. Also, variation from known channel location as estimated by root mean square error (RMSE) between surveyed channel location and extracted channel was computed for each of the DEMs and extracted stream networks. As expected, the results indicate that the DEM based hydrographic extraction process provides more detailed hydrographic features at a finer resolution. RMSE between the known channel location and modeled locations generally increased with larger cell size DEM with a greater effect in the larger RCEW. Sensitivity analyses on sinuosity demonstrated that the resulting shape of streams obtained from LiDAR data matched best with the reference data at an intermediate cell size instead of highest resolution, which is at a range of cell size from 5 to 10 m likely due to original point spacing, terrain characteristics, and LiDAR noise influence. More importantly, the absolute sinuosity deviation displayed a smallest value at the cell size of 10 m in both experimental watersheds, which suggests that optimal cell size for LiDAR-derived DEMs used for hydrographic feature extraction is 10 m.

  1. Feature selection and survival modeling in The Cancer Genome Atlas

    Directory of Open Access Journals (Sweden)

    Kim H

    2013-09-01

    Full Text Available Hyunsoo Kim,1 Markus Bredel2 1Department of Pathology, The University of Alabama at Birmingham, Birmingham, AL, USA; 2Department of Radiation Oncology, and Comprehensive Cancer Center, The University of Alabama at Birmingham, Birmingham, AL, USA Purpose: Personalized medicine is predicated on the concept of identifying subgroups of a common disease for better treatment. Identifying biomarkers that predict disease subtypes has been a major focus of biomedical science. In the era of genome-wide profiling, there is controversy as to the optimal number of genes as an input of a feature selection algorithm for survival modeling. Patients and methods: The expression profiles and outcomes of 544 patients were retrieved from The Cancer Genome Atlas. We compared four different survival prediction methods: (1 1-nearest neighbor (1-NN survival prediction method; (2 random patient selection method and a Cox-based regression method with nested cross-validation; (3 least absolute shrinkage and selection operator (LASSO optimization using whole-genome gene expression profiles; or (4 gene expression profiles of cancer pathway genes. Results: The 1-NN method performed better than the random patient selection method in terms of survival predictions, although it does not include a feature selection step. The Cox-based regression method with LASSO optimization using whole-genome gene expression data demonstrated higher survival prediction power than the 1-NN method, but was outperformed by the same method when using gene expression profiles of cancer pathway genes alone. Conclusion: The 1-NN survival prediction method may require more patients for better performance, even when omitting censored data. Using preexisting biological knowledge for survival prediction is reasonable as a means to understand the biological system of a cancer, unless the analysis goal is to identify completely unknown genes relevant to cancer biology. Keywords: brain, feature selection

  2. A fuzzy based feature selection from independent component subspace for machine learning classification of microarray data

    Directory of Open Access Journals (Sweden)

    Rabia Aziz

    2016-06-01

    Full Text Available Feature (gene selection and classification of microarray data are the two most interesting machine learning challenges. In the present work two existing feature selection/extraction algorithms, namely independent component analysis (ICA and fuzzy backward feature elimination (FBFE are used which is a new combination of selection/extraction. The main objective of this paper is to select the independent components of the DNA microarray data using FBFE to improve the performance of support vector machine (SVM and Naïve Bayes (NB classifier, while making the computational expenses affordable. To show the validity of the proposed method, it is applied to reduce the number of genes for five DNA microarray datasets namely; colon cancer, acute leukemia, prostate cancer, lung cancer II, and high-grade glioma. Now these datasets are then classified using SVM and NB classifiers. Experimental results on these five microarray datasets demonstrate that gene selected by proposed approach, effectively improve the performance of SVM and NB classifiers in terms of classification accuracy. We compare our proposed method with principal component analysis (PCA as a standard extraction algorithm and find that the proposed method can obtain better classification accuracy, using SVM and NB classifiers with a smaller number of selected genes than the PCA. The curve between the average error rate and number of genes with each dataset represents the selection of required number of genes for the highest accuracy with our proposed method for both the classifiers. ROC shows best subset of genes for both the classifier of different datasets with propose method.

  3. Feature Selection for Generator Excitation Neurocontroller Development Using Filter Technique

    Directory of Open Access Journals (Sweden)

    Abdul Ghani Abro

    2011-09-01

    Full Text Available Essentially, motive behind using control system is to generate suitable control signal for yielding desired response of a physical process. Control of synchronous generator has always remained very critical in power system operation and control. For certain well known reasons power generators are normally operated well below their steady state stability limit. This raises demand for efficient and fast controllers. Artificial intelligence has been reported to give revolutionary outcomes in the field of control engineering. Artificial Neural Network (ANN, a branch of artificial intelligence has been used for nonlinear and adaptive control, utilizing its inherent observability. The overall performance of neurocontroller is dependent upon input features too. Selecting optimum features to train a neurocontroller optimally is very critical. Both quality and size of data are of equal importance for better performance. In this work filter technique is employed to select independent factors for ANN training.

  4. EEG artifact elimination by extraction of ICA-component features using image processing algorithms.

    Science.gov (United States)

    Radüntz, T; Scouten, J; Hochmuth, O; Meffert, B

    2015-03-30

    Artifact rejection is a central issue when dealing with electroencephalogram recordings. Although independent component analysis (ICA) separates data in linearly independent components (IC), the classification of these components as artifact or EEG signal still requires visual inspection by experts. In this paper, we achieve automated artifact elimination using linear discriminant analysis (LDA) for classification of feature vectors extracted from ICA components via image processing algorithms. We compare the performance of this automated classifier to visual classification by experts and identify range filtering as a feature extraction method with great potential for automated IC artifact recognition (accuracy rate 88%). We obtain almost the same level of recognition performance for geometric features and local binary pattern (LBP) features. Compared to the existing automated solutions the proposed method has two main advantages: First, it does not depend on direct recording of artifact signals, which then, e.g. have to be subtracted from the contaminated EEG. Second, it is not limited to a specific number or type of artifact. In summary, the present method is an automatic, reliable, real-time capable and practical tool that reduces the time intensive manual selection of ICs for artifact removal. The results are very promising despite the relatively small channel resolution of 25 electrodes.

  5. Acute Exercise Modulates Feature-selective Responses in Human Cortex.

    Science.gov (United States)

    Bullock, Tom; Elliott, James C; Serences, John T; Giesbrecht, Barry

    2017-04-01

    An organism's current behavioral state influences ongoing brain activity. Nonhuman mammalian and invertebrate brains exhibit large increases in the gain of feature-selective neural responses in sensory cortex during locomotion, suggesting that the visual system becomes more sensitive when actively exploring the environment. This raises the possibility that human vision is also more sensitive during active movement. To investigate this possibility, we used an inverted encoding model technique to estimate feature-selective neural response profiles from EEG data acquired from participants performing an orientation discrimination task. Participants (n = 18) fixated at the center of a flickering (15 Hz) circular grating presented at one of nine different orientations and monitored for a brief shift in orientation that occurred on every trial. Participants completed the task while seated on a stationary exercise bike at rest and during low- and high-intensity cycling. We found evidence for inverted-U effects; such that the peak of the reconstructed feature-selective tuning profiles was highest during low-intensity exercise compared with those estimated during rest and high-intensity exercise. When modeled, these effects were driven by changes in the gain of the tuning curve and in the profile bandwidth during low-intensity exercise relative to rest. Thus, despite profound differences in visual pathways across species, these data show that sensitivity in human visual cortex is also enhanced during locomotive behavior. Our results reveal the nature of exercise-induced gain on feature-selective coding in human sensory cortex and provide valuable evidence linking the neural mechanisms of behavior state across species.

  6. Feature Selection in Detection of Adverse Drug Reactions from the Health Improvement Network (THIN Database

    Directory of Open Access Journals (Sweden)

    Yihui Liu

    2015-02-01

    Full Text Available Adverse drug reaction (ADR is widely concerned for public health issue. ADRs are one of most common causes to withdraw some drugs from market. Prescription event monitoring (PEM is an important approach to detect the adverse drug reactions. The main problem to deal with this method is how to automatically extract the medical events or side effects from high-throughput medical events, which are collected from day to day clinical practice. In this study we propose a novel concept of feature matrix to detect the ADRs. Feature matrix, which is extracted from big medical data from The Health Improvement Network (THIN database, is created to characterize the medical events for the patients who take drugs. Feature matrix builds the foundation for the irregular and big medical data. Then feature selection methods are performed on feature matrix to detect the significant features. Finally the ADRs can be located based on the significant features. The experiments are carried out on three drugs: Atorvastatin, Alendronate, and Metoclopramide. Major side effects for each drug are detected and better performance is achieved compared to other computerized methods. The detected ADRs are based on computerized methods, further investigation is needed.

  7. HYBRID FEATURE SELECTION ALGORITHM FOR INTRUSION DETECTION SYSTEM

    Directory of Open Access Journals (Sweden)

    Seyed Reza Hasani

    2014-01-01

    Full Text Available Network security is a serious global concern. Usefulness Intrusion Detection Systems (IDS are increasing incredibly in Information Security research using Soft computing techniques. In the previous researches having irrelevant and redundant features are recognized causes of increasing the processing speed of evaluating the known intrusive patterns. In addition, an efficient feature selection method eliminates dimension of data and reduce redundancy and ambiguity caused by none important attributes. Therefore, feature selection methods are well-known methods to overcome this problem. There are various approaches being utilized in intrusion detections, they are able to perform their method and relatively they are achieved with some improvements. This work is based on the enhancement of the highest Detection Rate (DR algorithm which is Linear Genetic Programming (LGP reducing the False Alarm Rate (FAR incorporates with Bees Algorithm. Finally, Support Vector Machine (SVM is one of the best candidate solutions to settle IDSs problems. In this study four sample dataset containing 4000 random records are excluded randomly from this dataset for training and testing purposes. Experimental results show that the LGP_BA method improves the accuracy and efficiency compared with the previous related research and the feature subcategory offered by LGP_BA gives a superior representation of data.

  8. Online Feature Selection of Class Imbalance via PA Algorithm

    Institute of Scientific and Technical Information of China (English)

    Chao Han; Yun-Kun Tan; Jin-Hui Zhu; Yong Guo; Jian Chen; Qing-Yao Wu

    2016-01-01

    Imbalance classification techniques have been frequently applied in many machine learning application domains where the number of the majority (or positive) class of a dataset is much larger than that of the minority (or negative) class. Meanwhile, feature selection (FS) is one of the key techniques for the high-dimensional classification task in a manner which greatly improves the classification performance and the computational efficiency. However, most studies of feature selection and imbalance classification are restricted to off-line batch learning, which is not well adapted to some practical scenarios. In this paper, we aim to solve high-dimensional imbalanced classification problem accurately and efficiently with only a small number of active features in an online fashion, and we propose two novel online learning algorithms for this purpose. In our approach, a classifier which involves only a small and fixed number of features is constructed to classify a sequence of imbalanced data received in an online manner. We formulate the construction of such online learner into an optimization problem and use an iterative approach to solve the problem based on the passive-aggressive (PA) algorithm as well as a truncated gradient (TG) method. We evaluate the performance of the proposed algorithms based on several real-world datasets, and our experimental results have demonstrated the effectiveness of the proposed algorithms in comparison with the baselines.

  9. Use of genetic algorithm for the selection of EEG features

    Science.gov (United States)

    Asvestas, P.; Korda, A.; Kostopoulos, S.; Karanasiou, I.; Ouzounoglou, A.; Sidiropoulos, K.; Ventouras, E.; Matsopoulos, G.

    2015-09-01

    Genetic Algorithm (GA) is a popular optimization technique that can detect the global optimum of a multivariable function containing several local optima. GA has been widely used in the field of biomedical informatics, especially in the context of designing decision support systems that classify biomedical signals or images into classes of interest. The aim of this paper is to present a methodology, based on GA, for the selection of the optimal subset of features that can be used for the efficient classification of Event Related Potentials (ERPs), which are recorded during the observation of correct or incorrect actions. In our experiment, ERP recordings were acquired from sixteen (16) healthy volunteers who observed correct or incorrect actions of other subjects. The brain electrical activity was recorded at 47 locations on the scalp. The GA was formulated as a combinatorial optimizer for the selection of the combination of electrodes that maximizes the performance of the Fuzzy C Means (FCM) classification algorithm. In particular, during the evolution of the GA, for each candidate combination of electrodes, the well-known (Σ, Φ, Ω) features were calculated and were evaluated by means of the FCM method. The proposed methodology provided a combination of 8 electrodes, with classification accuracy 93.8%. Thus, GA can be the basis for the selection of features that discriminate ERP recordings of observations of correct or incorrect actions.

  10. Processing of Feature Selectivity in Cortical Networks with Specific Connectivity.

    Directory of Open Access Journals (Sweden)

    Sadra Sadeh

    Full Text Available Although non-specific at the onset of eye opening, networks in rodent visual cortex attain a non-random structure after eye opening, with a specific bias for connections between neurons of similar preferred orientations. As orientation selectivity is already present at eye opening, it remains unclear how this specificity in network wiring contributes to feature selectivity. Using large-scale inhibition-dominated spiking networks as a model, we show that feature-specific connectivity leads to a linear amplification of feedforward tuning, consistent with recent electrophysiological single-neuron recordings in rodent neocortex. Our results show that optimal amplification is achieved at an intermediate regime of specific connectivity. In this configuration a moderate increase of pairwise correlations is observed, consistent with recent experimental findings. Furthermore, we observed that feature-specific connectivity leads to the emergence of orientation-selective reverberating activity, and entails pattern completion in network responses. Our theoretical analysis provides a mechanistic understanding of subnetworks' responses to visual stimuli, and casts light on the regime of operation of sensory cortices in the presence of specific connectivity.

  11. A new breast cancer risk analysis approach using features extracted from multiple sub-regions on bilateral mammograms

    Science.gov (United States)

    Sun, Wenqing; Tseng, Tzu-Liang B.; Zheng, Bin; Zhang, Jianying; Qian, Wei

    2015-03-01

    A novel breast cancer risk analysis approach is proposed for enhancing performance of computerized breast cancer risk analysis using bilateral mammograms. Based on the intensity of breast area, five different sub-regions were acquired from one mammogram, and bilateral features were extracted from every sub-region. Our dataset includes 180 bilateral mammograms from 180 women who underwent routine screening examinations, all interpreted as negative and not recalled by the radiologists during the original screening procedures. A computerized breast cancer risk analysis scheme using four image processing modules, including sub-region segmentation, bilateral feature extraction, feature selection, and classification was designed to detect and compute image feature asymmetry between the left and right breasts imaged on the mammograms. The highest computed area under the curve (AUC) is 0.763 ± 0.021 when applying the multiple sub-region features to our testing dataset. The positive predictive value and the negative predictive value were 0.60 and 0.73, respectively. The study demonstrates that (1) features extracted from multiple sub-regions can improve the performance of our scheme compared to using features from whole breast area only; (2) a classifier using asymmetry bilateral features can effectively predict breast cancer risk; (3) incorporating texture and morphological features with density features can boost the classification accuracy.

  12. Classifying human voices by using hybrid SFX time-series preprocessing and ensemble feature selection.

    Science.gov (United States)

    Fong, Simon; Lan, Kun; Wong, Raymond

    2013-01-01

    Voice biometrics is one kind of physiological characteristics whose voice is different for each individual person. Due to this uniqueness, voice classification has found useful applications in classifying speakers' gender, mother tongue or ethnicity (accent), emotion states, identity verification, verbal command control, and so forth. In this paper, we adopt a new preprocessing method named Statistical Feature Extraction (SFX) for extracting important features in training a classification model, based on piecewise transformation treating an audio waveform as a time-series. Using SFX we can faithfully remodel statistical characteristics of the time-series; together with spectral analysis, a substantial amount of features are extracted in combination. An ensemble is utilized in selecting only the influential features to be used in classification model induction. We focus on the comparison of effects of various popular data mining algorithms on multiple datasets. Our experiment consists of classification tests over four typical categories of human voice data, namely, Female and Male, Emotional Speech, Speaker Identification, and Language Recognition. The experiments yield encouraging results supporting the fact that heuristically choosing significant features from both time and frequency domains indeed produces better performance in voice classification than traditional signal processing techniques alone, like wavelets and LPC-to-CC.

  13. Multiclonal plastic antibodies for selective aflatoxin extraction from food samples.

    Science.gov (United States)

    Bayram, Engin; Yılmaz, Erkut; Uzun, Lokman; Say, Rıdvan; Denizli, Adil

    2017-04-15

    Herein, we focused on developing a new generation of monolithic columns for extracting aflatoxin from real food samples by combining the superior features of molecularly imprinted polymers and cryogels. To accomplish this, we designed multiclonal plastic antibodies through simultaneous imprinting of aflatoxin subtypes B1, B2, G1, and G2. We applied Fourier transform infrared (FTIR) spectroscopy, scanning electron microscopy (SEM), and spectrofluorimetry to characterize the materials, and conducted selectivity studies using ochratoxin A and aflatoxin M1 (a metabolite of aflatoxin B1), as well as other aflatoxins, under competitive conditions. We determined optimal aflatoxin extraction conditions in terms of concentration, flow rate, temperature, and embedded particle amount as up to 25ng/mL for each species, 0.43mL/min, 7.0, 30°C, and 200mg, respectively. These multiclonal plastic antibodies showed imprinting efficiencies against ochratoxin A and aflatoxin M1 of 1.84 and 26.39, respectively, even under competitive conditions. Finally, we tested reusability, repeatability, reproducibility, and robustness of columns throughout inter- and intra-column variation studies. Copyright © 2016 Elsevier Ltd. All rights reserved.

  14. [Classification technique for hyperspectral image based on subspace of bands feature extraction and LS-SVM].

    Science.gov (United States)

    Gao, Heng-zhen; Wan, Jian-wei; Zhu, Zhen-zhen; Wang, Li-bao; Nian, Yong-jian

    2011-05-01

    The present paper proposes a novel hyperspectral image classification algorithm based on LS-SVM (least squares support vector machine). The LS-SVM uses the features extracted from subspace of bands (SOB). The maximum noise fraction (MNF) method is adopted as the feature extraction method. The spectral correlations of the hyperspectral image are used in order to divide the feature space into several SOBs. Then the MNF is used to extract characteristic features of the SOBs. The extracted features are combined into the feature vector for classification. So the strong bands correlation is avoided and the spectral redundancies are reduced. The LS-SVM classifier is adopted, which replaces inequality constraints in SVM by equality constraints. So the computation consumption is reduced and the learning performance is improved. The proposed method optimizes spectral information by feature extraction and reduces the spectral noise. The classifier performance is improved. Experimental results show the superiorities of the proposed algorithm.

  15. Feature Extraction and Classification of Echo Signal of Ground Penetrating Radar

    Institute of Scientific and Technical Information of China (English)

    ZHOU Hui-lin; TIAN Mao; CHEN Xiao-li

    2005-01-01

    Automatic feature extraction and classification algorithm of echo signal of ground penetrating radar is presented. Dyadic wavelet transform and the average energy of the wavelet coefficients are applied in this paper to decompose and extract feature of the echo signal. Then, the extracted feature vector is fed up to a feed-forward multi-layer perceptron classifier. Experimental results based on the measured GPR echo signals obtained from the Mei-shan railway are presented.

  16. Apriori and N-gram Based Chinese Text Feature Extraction Method

    Institute of Scientific and Technical Information of China (English)

    王晔; 黄上腾

    2004-01-01

    A feature extraction, which means extracting the representative words from a text, is an important issue in text mining field. This paper presented a new Apriori and N-gram based Chinese text feature extraction method, and analyzed its correctness and performance. Our method solves the question that the exist extraction methods cannot find the frequent words with arbitrary length in Chinese texts. The experimental results show this method is feasible.

  17. Texture feature selection with relevance learning to classify interstitial lung disease patterns

    Science.gov (United States)

    Huber, Markus B.; Bunte, Kerstin; Nagarajan, Mahesh B.; Biehl, Michael; Ray, Lawrence A.; Wismueller, Axel

    2011-03-01

    The Generalized Matrix Learning Vector Quantization (GMLVQ) is used to estimate the relevance of texture features in their ability to classify interstitial lung disease patterns in high-resolution computed tomography (HRCT) images. After a stochastic gradient descent, the GMLVQ algorithm provides a discriminative distance measure of relevance factors, which can account for pairwise correlations between different texture features and their importance for the classification of healthy and diseased patterns. Texture features were extracted from gray-level co-occurrence matrices (GLCMs), and were ranked and selected according to their relevance obtained by GMLVQ and, for comparison, to a mutual information (MI) criteria. A k-nearest-neighbor (kNN) classifier and a Support Vector Machine with a radial basis function kernel (SVMrbf) were optimized in a 10-fold crossvalidation for different texture feature sets. In our experiment with real-world data, the feature sets selected by the GMLVQ approach had a significantly better classification performance compared with feature sets selected by a MI ranking.

  18. A ROC-based feature selection method for computer-aided detection and diagnosis

    Science.gov (United States)

    Wang, Songyuan; Zhang, Guopeng; Liao, Qimei; Zhang, Junying; Jiao, Chun; Lu, Hongbing

    2014-03-01

    Image-based computer-aided detection and diagnosis (CAD) has been a very active research topic aiming to assist physicians to detect lesions and distinguish them from benign to malignant. However, the datasets fed into a classifier usually suffer from small number of samples, as well as significantly less samples available in one class (have a disease) than the other, resulting in the classifier's suboptimal performance. How to identifying the most characterizing features of the observed data for lesion detection is critical to improve the sensitivity and minimize false positives of a CAD system. In this study, we propose a novel feature selection method mR-FAST that combines the minimal-redundancymaximal relevance (mRMR) framework with a selection metric FAST (feature assessment by sliding thresholds) based on the area under a ROC curve (AUC) generated on optimal simple linear discriminants. With three feature datasets extracted from CAD systems for colon polyps and bladder cancer, we show that the space of candidate features selected by mR-FAST is more characterizing for lesion detection with higher AUC, enabling to find a compact subset of superior features at low cost.

  19. Selective extraction of naturally occurring radioactive Ra2+

    NARCIS (Netherlands)

    van Leeuwen, F.W.B.; Verboom, Willem; Reinhoudt, David

    2005-01-01

    Organic extractants play a significant role in the selective removal of radioactive cations from waste streams. Although, literature on the selective removal of man-made radioactive material such as Americium (Am) is widespread, the selective removal of naturally occurring radioactive material such

  20. Spectrum based feature extraction using spectrum intensity ratio for SSVEP detection.

    Science.gov (United States)

    Itai, Akitoshi; Funase, Arao

    2012-01-01

    Recent years, a Steady-State Visual Evoked Potential (SSVEP) is used as a basis for Brain Computer Interface (BCI)[1]. Various feature extraction and classification techniques are proposed to achieve BCI based on SSVEP. The feature extraction of SSVEP is developed in the frequency domain regardless of the limitation in flickering frequency of visual stimulus caused by hardware architecture. We introduce here the feature extraction using a spectrum intensity ratio. Results show that the detection ratio reaches 84% by using a spectrum intensity ratio with unsupervised classification. It also indicates the SSVEP is enhanced by proposed feature extraction with second harmonic.

  1. PyEEG: an open source Python module for EEG/MEG feature extraction.

    Science.gov (United States)

    Bao, Forrest Sheng; Liu, Xin; Zhang, Christina

    2011-01-01

    Computer-aided diagnosis of neural diseases from EEG signals (or other physiological signals that can be treated as time series, e.g., MEG) is an emerging field that has gained much attention in past years. Extracting features is a key component in the analysis of EEG signals. In our previous works, we have implemented many EEG feature extraction functions in the Python programming language. As Python is gaining more ground in scientific computing, an open source Python module for extracting EEG features has the potential to save much time for computational neuroscientists. In this paper, we introduce PyEEG, an open source Python module for EEG feature extraction.

  2. Textural feature selection for enhanced detection of stationary humans in through-the-wall radar imagery

    Science.gov (United States)

    Chaddad, A.; Ahmad, F.; Amin, M. G.; Sevigny, P.; DiFilippo, D.

    2014-05-01

    Feature-based methods have been recently considered in the literature for detection of stationary human targets in through-the-wall radar imagery. Specifically, textural features, such as contrast, correlation, energy, entropy, and homogeneity, have been extracted from gray-level co-occurrence matrices (GLCMs) to aid in discriminating the true targets from multipath ghosts and clutter that closely mimic the target in size and intensity. In this paper, we address the task of feature selection to identify the relevant subset of features in the GLCM domain, while discarding those that are either redundant or confusing, thereby improving the performance of feature-based scheme to distinguish between targets and ghosts/clutter. We apply a Decision Tree algorithm to find the optimal combination of co-occurrence based textural features for the problem at hand. We employ a K-Nearest Neighbor classifier to evaluate the performance of the optimal textural feature based scheme in terms of its target and ghost/clutter discrimination capability and use real-data collected with the vehicle-borne multi-channel through-the-wall radar imaging system by Defence Research and Development Canada. For the specific data analyzed, it is shown that the identified dominant features yield a higher classification accuracy, with lower number of false alarms and missed detections, compared to the full GLCM based feature set.

  3. Image mining and Automatic Feature extraction from Remotely Sensed Image (RSI using Cubical Distance Methods

    Directory of Open Access Journals (Sweden)

    S.Sasikala

    2013-04-01

    Full Text Available Information processing and decision support system using image mining techniques is in advance drive with huge availability of remote sensing image (RSI. RSI describes inherent properties of objects by recording their natural reflectance in the electro-magnetic spectral (ems region. Information on such objects could be gathered by their color properties or their spectral values in various ems range in the form of pixels. Present paper explains a method of such information extraction using cubical distance method and subsequent results. Thismethod is one among the simpler in its approach and considers grouping of pixels on the basis of equal distance from a specified point in the image or selected pixel having definite attribute values (DN in different spectral layers of the RSI. The color distance and the occurrence pixel distance play a vital role in determining similarobjects as clusters aid in extracting features in the RSI domain.

  4. Feature evaluation and extraction based on neural network in analog circuit fault diagnosis

    Institute of Scientific and Technical Information of China (English)

    Yuan Haiying; Chen Guangju; Xie Yongle

    2007-01-01

    Choosing the right characteristic parameter is the key to fault diagnosis in analog circuit.The feature evaluation and extraction methods based on neural network are presented.Parameter evaluation of circuit features is realized by training results from neural network; the superior nonlinear mapping capability is competent for extracting fault features which are normalized and compressed subsequently.The complex classification problem on fault pattern recognition in analog circuit is transferred into feature processing stage by feature extraction based on neural network effectively, which improves the diagnosis efficiency.A fault diagnosis illustration validated this method.

  5. A fingerprint feature extraction algorithm based on curvature of Bezier curve

    Institute of Scientific and Technical Information of China (English)

    2007-01-01

    Fingerprint feature extraction is a key step of fingerprint identification. A novel feature extraction algorithm is proposed in this paper, which describes fingerprint feature with the bending information of fingerprint ridges. Ridges in the specific region of fingerprint images are traced firstly in the algorithm, and then these ridges are fit with Bezier curve. Finally, the point that has the maximal curvature on Bezier curve is defined as a feature point. Experimental results demonstrate that this kind of feature points characterize the bending trend of fingerprint ridges effectively, and they are robust to noise, in addition, the extraction precision of this algorithm is also better than the conventional approaches.

  6. Feature Extraction of Chinese Materia Medica Fingerprint Based on Star Plot Representation of Multivariate Data

    Institute of Scientific and Technical Information of China (English)

    CUI Jian-xin; HONG Wen-xue; ZHOU Rong-juan; GAO Hai-bo

    2011-01-01

    Objective To study a novel feature extraction method of Chinese materia medica (CMM) fingerprint. Methods On the basis of the radar graphical presentation theory of multivariate, the radar map was used to figure the non-map parameters of the CMM fingerprint, then to extract the map features and to propose the feature fusion. Results Better performance was achieved when using this method to test data. Conclusion This shows that the feature extraction based on radar chart presentation can mine the valuable features that facilitate the identification of Chinese medicine.

  7. An Optimal SVM with Feature Selection Using Multiobjective PSO

    Directory of Open Access Journals (Sweden)

    Iman Behravan

    2016-01-01

    Full Text Available Support vector machine is a classifier, based on the structured risk minimization principle. The performance of the SVM depends on different parameters such as penalty factor, C, and the kernel factor, σ. Also choosing an appropriate kernel function can improve the recognition score and lower the amount of computation. Furthermore, selecting the useful features among several features in dataset not only increases the performance of the SVM, but also reduces the computational time and complexity. So this is an optimization problem which can be solved by heuristic algorithm. In some cases besides the recognition score, the reliability of the classifier’s output is important. So in such cases a multiobjective optimization algorithm is needed. In this paper we have got the MOPSO algorithm to optimize the parameters of the SVM, choose appropriate kernel function, and select the best feature subset simultaneously in order to optimize the recognition score and the reliability of the SVM concurrently. Nine different datasets, from UCI machine learning repository, are used to evaluate the power and the effectiveness of the proposed method (MOPSO-SVM. The results of the proposed method are compared to those which are achieved by single SVM, RBF, and MLP neural networks.

  8. Feature Extraction in the North Sinai Desert Using Spaceborne Synthetic Aperture Radar: Potential Archaeological Applications

    Directory of Open Access Journals (Sweden)

    Christopher Stewart

    2016-10-01

    Full Text Available Techniques were implemented to extract anthropogenic features in the desert region of North Sinai using data from the first- and second-generation Phased Array type L-band Synthetic Aperture Radar (PALSAR-1 and 2. To obtain a synoptic view over the study area, a mosaic of average, multitemporal (De Grandi filtered PALSAR-1 σ° backscatter of North Sinai was produced. Two subset regions were selected for further analysis. The first included an area of abundant linear features of high relative backscatter in a strategic, but sparsely developed area between the Wadi Tumilat and Gebel Maghara. The second included an area of low backscatter anomaly features in a coastal sabkha around the archaeological sites of Tell el-Farama, Tell el-Mahzan, and Tell el-Kanais. Over the subset region between the Wadi Tumilat and Gebel Maghara, algorithms were developed to extract linear features and convert them to vector format to facilitate interpretation. The algorithms were based on mathematical morphology, but to distinguish apparent man-made features from sand dune ridges, several techniques were applied. The first technique took as input the average σ° backscatter and used a Digital Elevation Model (DEM derived Local Incidence Angle (LAI mask to exclude sand dune ridges. The second technique, which proved more effective, used the average interferometric coherence as input. Extracted features were compared with other available information layers and in some cases revealed partially buried roads. Over the coastal subset region a time series of PALSAR-2 spotlight data were processed. The coefficient of variation (CoV of De Grandi filtered imagery clearly revealed anomaly features of low CoV. These were compared with the results of an archaeological field walking survey carried out previously. The features generally correspond with isolated areas identified in the field survey as having a higher density of archaeological finds, and interpreted as possible

  9. Classification of features selected through Optimum Index Factor (OIF)for improving classification accuracy

    Institute of Scientific and Technical Information of China (English)

    Nilanchal Patel; Brijesh Kaushal

    2011-01-01

    The present investigation was performed to determine if the features selected through Optimum Index Factor (OIF) could provide improved classification accuracy of the various categories on the satellite images of the individual years as well as stacked images of two different years as compared to all the features considered together. Further, in order to determine if there occurs increase in the classification accuracy of the different categories with corresponding increase in the OIF values of the features extracted from both the individual years' and stacked images, we performed linear regression between the producer's accuracy (PA) of the various categories with the OIF values of the different combinations of the features. The investigations demonstrated that there occurs significant improvement in the PA of two impervious categories viz. moderate built-up and low density built-up determined from the classification of the bands and principal components associated with the highest OIF value as compared to all the bands and principal components for both the individual years' and stacked images respectively. Regression analyses exhibited positive trends between the regression coefficients and OIF values forthe various categories determined for the individual years' and stacked images respectively signifying the prevalence of direct relationship between the increase in the information content with corresponding increase in the OIF values. The research proved that features extracted through OIF from both the individual years' and stacked images are capable of providing significantly improved PA as compared to all the features pooled together.

  10. Solid waste bin level detection using gray level co-occurrence matrix feature extraction approach.

    Science.gov (United States)

    Arebey, Maher; Hannan, M A; Begum, R A; Basri, Hassan

    2012-08-15

    This paper presents solid waste bin level detection and classification using gray level co-occurrence matrix (GLCM) feature extraction methods. GLCM parameters, such as displacement, d, quantization, G, and the number of textural features, are investigated to determine the best parameter values of the bin images. The parameter values and number of texture features are used to form the GLCM database. The most appropriate features collected from the GLCM are then used as inputs to the multi-layer perceptron (MLP) and the K-nearest neighbor (KNN) classifiers for bin image classification and grading. The classification and grading performance for DB1, DB2 and DB3 features were selected with both MLP and KNN classifiers. The results demonstrated that the KNN classifier, at KNN = 3, d = 1 and maximum G values, performs better than using the MLP classifier with the same database. Based on the results, this method has the potential to be used in solid waste bin level classification and grading to provide a robust solution for solid waste bin level detection, monitoring and management.

  11. Nonlocal sparse model with adaptive structural clustering for feature extraction of aero-engine bearings

    Science.gov (United States)

    Zhang, Han; Chen, Xuefeng; Du, Zhaohui; Li, Xiang; Yan, Ruqiang

    2016-04-01

    Fault information of aero-engine bearings presents two particular phenomena, i.e., waveform distortion and impulsive feature frequency band dispersion, which leads to a challenging problem for current techniques of bearing fault diagnosis. Moreover, although many progresses of sparse representation theory have been made in feature extraction of fault information, the theory also confronts inevitable performance degradation due to the fact that relatively weak fault information has not sufficiently prominent and sparse representations. Therefore, a novel nonlocal sparse model (coined NLSM) and its algorithm framework has been proposed in this paper, which goes beyond simple sparsity by introducing more intrinsic structures of feature information. This work adequately exploits the underlying prior information that feature information exhibits nonlocal self-similarity through clustering similar signal fragments and stacking them together into groups. Within this framework, the prior information is transformed into a regularization term and a sparse optimization problem, which could be solved through block coordinate descent method (BCD), is formulated. Additionally, the adaptive structural clustering sparse dictionary learning technique, which utilizes k-Nearest-Neighbor (kNN) clustering and principal component analysis (PCA) learning, is adopted to further enable sufficient sparsity of feature information. Moreover, the selection rule of regularization parameter and computational complexity are described in detail. The performance of the proposed framework is evaluated through numerical experiment and its superiority with respect to the state-of-the-art method in the field is demonstrated through the vibration signals of experimental rig of aircraft engine bearings.

  12. Spectrophotometric validation of assay method for selected medicinal plant extracts

    OpenAIRE

    Matthew Arhewoh; Augustine O. Okhamafe

    2014-01-01

    Objective: To develop UV spectrophotometric assay validation methods for some selected medicinal plant extracts.Methods: Dried, powdered leaves of Annona muricata (AM) and Andrographis paniculata (AP) as well as seeds of Garcinia kola (GK) and Hunteria umbellata (HU) were separately subjected to maceration using distilled water. Different concentrations of the extracts were scanned spectrophotometrically to obtain wavelengths of maximum absorbance. The different extracts were then subjected t...

  13. Mitotic apparatus: the selective extraction of protein with mild acid.

    Science.gov (United States)

    Bibring, T; Baxandall, J

    1968-07-26

    The treatment of isolated mitotic apparatus with mild (pH 3) hydrochloric acid results in the extraction of less than 10 percent of its protein, accompanied by the selective morphological disappearance of the microtubules. The same extraction can be shown to dissolve outer doublet microtubules from sperm flagella. A protein with points of similarity to the flagellar microtubule protein is the major component of the extract from mitotic apparatus.

  14. Large Margin Multi-Modal Multi-Task Feature Extraction for Image Classification.

    Science.gov (United States)

    Yong Luo; Yonggang Wen; Dacheng Tao; Jie Gui; Chao Xu

    2016-01-01

    The features used in many image analysis-based applications are frequently of very high dimension. Feature extraction offers several advantages in high-dimensional cases, and many recent studies have used multi-task feature extraction approaches, which often outperform single-task feature extraction approaches. However, most of these methods are limited in that they only consider data represented by a single type of feature, even though features usually represent images from multiple modalities. We, therefore, propose a novel large margin multi-modal multi-task feature extraction (LM3FE) framework for handling multi-modal features for image classification. In particular, LM3FE simultaneously learns the feature extraction matrix for each modality and the modality combination coefficients. In this way, LM3FE not only handles correlated and noisy features, but also utilizes the complementarity of different modalities to further help reduce feature redundancy in each modality. The large margin principle employed also helps to extract strongly predictive features, so that they are more suitable for prediction (e.g., classification). An alternating algorithm is developed for problem optimization, and each subproblem can be efficiently solved. Experiments on two challenging real-world image data sets demonstrate the effectiveness and superiority of the proposed method.

  15. STATISTICAL PROBABILITY BASED ALGORITHM FOR EXTRACTING FEATURE POINTS IN 2-DIMENSIONAL IMAGE

    Institute of Scientific and Technical Information of China (English)

    Guan Yepeng; Gu Weikang; Ye Xiuqing; Liu Jilin

    2004-01-01

    An algorithm for automatically extracting feature points is developed after the area of feature points in 2-dimensional (2D) imagebeing located by probability theory, correlated methods and criterion for abnormity. Feature points in 2D image can be extracted only by calculating standard deviation of gray within sampled pixels area in our approach statically. While extracting feature points, the limitation to confirm threshold by tentative method according to some a priori information on processing image can be avoided. It is proved that the proposed algorithm is valid and reliable by extracting feature points on actual natural images with abundant and weak texture, including multi-object with complex background, respectively. It can meet the demand of extracting feature points of 2D image automatically in machine vision system.

  16. Feature extraction for target identification and image classification of OMIS hyperspectral image

    Institute of Scientific and Technical Information of China (English)

    DU Pei-jun; TAN Kun; SU Hong-jun

    2009-01-01

    In order to combine feature extraction operations with specific hyperspectrai remote sensing information processing objectives, two aspects of feature extraction were explored. Based on clustering and decision tree algorithm, spectral absorption index (SAI), continuum-removal and derivative spectral analysis were employed to discover characterized spectral features of dif-ferent targets, and decision trees for identifying a specific class and discriminating different classes were generated. By combining support vector machine (SVM) classifier with different feature extraction strategies including principal component analysis (PCA), minimum noise fraction (MNF), grouping PCA, and derivate spectral analysis, the performance of feature extraction approaches in classification was evaluated. The results show that feature extraction by PCA and derivate spectral analysis are effective to OMIS (operational modular imaging spectrometer) image classification using SVM, and SVM outperforms traditional SAM and MLC classifiers for OMIS data.

  17. Information Theory for Gabor Feature Selection for Face Recognition

    Directory of Open Access Journals (Sweden)

    Shen Linlin

    2006-01-01

    Full Text Available A discriminative and robust feature—kernel enhanced informative Gabor feature—is proposed in this paper for face recognition. Mutual information is applied to select a set of informative and nonredundant Gabor features, which are then further enhanced by kernel methods for recognition. Compared with one of the top performing methods in the 2004 Face Verification Competition (FVC2004, our methods demonstrate a clear advantage over existing methods in accuracy, computation efficiency, and memory cost. The proposed method has been fully tested on the FERET database using the FERET evaluation protocol. Significant improvements on three of the test data sets are observed. Compared with the classical Gabor wavelet-based approaches using a huge number of features, our method requires less than 4 milliseconds to retrieve a few hundreds of features. Due to the substantially reduced feature dimension, only 4 seconds are required to recognize 200 face images. The paper also unified different Gabor filter definitions and proposed a training sample generation algorithm to reduce the effects caused by unbalanced number of samples available in different classes.

  18. Information Theory for Gabor Feature Selection for Face Recognition

    Science.gov (United States)

    Shen, Linlin; Bai, Li

    2006-12-01

    A discriminative and robust feature—kernel enhanced informative Gabor feature—is proposed in this paper for face recognition. Mutual information is applied to select a set of informative and nonredundant Gabor features, which are then further enhanced by kernel methods for recognition. Compared with one of the top performing methods in the 2004 Face Verification Competition (FVC2004), our methods demonstrate a clear advantage over existing methods in accuracy, computation efficiency, and memory cost. The proposed method has been fully tested on the FERET database using the FERET evaluation protocol. Significant improvements on three of the test data sets are observed. Compared with the classical Gabor wavelet-based approaches using a huge number of features, our method requires less than 4 milliseconds to retrieve a few hundreds of features. Due to the substantially reduced feature dimension, only 4 seconds are required to recognize 200 face images. The paper also unified different Gabor filter definitions and proposed a training sample generation algorithm to reduce the effects caused by unbalanced number of samples available in different classes.

  19. Recursive Feature Selection with Significant Variables of Support Vectors

    Directory of Open Access Journals (Sweden)

    Chen-An Tsai

    2012-01-01

    Full Text Available The development of DNA microarray makes researchers screen thousands of genes simultaneously and it also helps determine high- and low-expression level genes in normal and disease tissues. Selecting relevant genes for cancer classification is an important issue. Most of the gene selection methods use univariate ranking criteria and arbitrarily choose a threshold to choose genes. However, the parameter setting may not be compatible to the selected classification algorithms. In this paper, we propose a new gene selection method (SVM-t based on the use of t-statistics embedded in support vector machine. We compared the performance to two similar SVM-based methods: SVM recursive feature elimination (SVMRFE and recursive support vector machine (RSVM. The three methods were compared based on extensive simulation experiments and analyses of two published microarray datasets. In the simulation experiments, we found that the proposed method is more robust in selecting informative genes than SVMRFE and RSVM and capable to attain good classification performance when the variations of informative and noninformative genes are different. In the analysis of two microarray datasets, the proposed method yields better performance in identifying fewer genes with good prediction accuracy, compared to SVMRFE and RSVM.

  20. Multi-Scale Analysis Based Curve Feature Extraction in Reverse Engineering

    Institute of Scientific and Technical Information of China (English)

    YANG Hongjuan; ZHOU Yiqi; CHEN Chengjun; ZHAO Zhengxu

    2006-01-01

    A sectional curve feature extraction algorithm based on multi-scale analysis is proposed for reverse engineering. The algorithm consists of two parts: feature segmentation and feature classification. In the first part, curvature scale space is applied to multi-scale analysis and original feature detection. To obtain the primary and secondary curve primitives, feature fusion is realized by multi-scale feature detection information transmission. In the second part: projection height function is presented based on the area of quadrilateral, which improved criterions of sectional curve feature classification. Results of synthetic curves and practical scanned sectional curves are given to illustrate the efficiency of the proposed algorithm on feature extraction. The consistence between feature extraction based on multi-scale curvature analysis and curve primitives is verified.

  1. Optimal Feature Extraction Using Greedy Approach for Random Image Components and Subspace Approach in Face Recognition

    Institute of Scientific and Technical Information of China (English)

    Mathu Soothana S.Kumar Retna Swami; Muneeswaran Karuppiah

    2013-01-01

    An innovative and uniform framework based on a combination of Gabor wavelets with principal component analysis (PCA) and multiple discriminant analysis (MDA) is presented in this paper.In this framework,features are extracted from the optimal random image components using greedy approach.These feature vectors are then projected to subspaces for dimensionality reduction which is used for solving linear problems.The design of Gabor filters,PCA and MDA are crucial processes used for facial feature extraction.The FERET,ORL and YALE face databases are used to generate the results.Experiments show that optimal random image component selection (ORICS) plus MDA outperforms ORICS and subspace projection approach such as ORICS plus PCA.Our method achieves 96.25%,99.44% and 100% recognition accuracy on the FERET,ORL and YALE databases for 30% training respectively.This is a considerably improved performance compared with other standard methodologies described in the literature.

  2. Wood Texture Features Extraction by Using GLCM Combined With Various Edge Detection Methods

    Science.gov (United States)

    Fahrurozi, A.; Madenda, S.; Ernastuti; Kerami, D.

    2016-06-01

    An image forming specific texture can be distinguished manually through the eye. However, sometimes it is difficult to do if the texture owned quite similar. Wood is a natural material that forms a unique texture. Experts can distinguish the quality of wood based texture observed in certain parts of the wood. In this study, it has been extracted texture features of the wood image that can be used to identify the characteristics of wood digitally by computer. Feature extraction carried out using Gray Level Co-occurrence Matrices (GLCM) built on an image from several edge detection methods applied to wood image. Edge detection methods used include Roberts, Sobel, Prewitt, Canny and Laplacian of Gaussian. The image of wood taken in LE2i laboratory, Universite de Bourgogne from the wood sample in France that grouped by their quality by experts and divided into four types of quality. Obtained a statistic that illustrates the distribution of texture features values of each wood type which compared according to the edge operator that is used and selection of specified GLCM parameters.

  3. Compressive sensing-based feature extraction for bearing fault diagnosis using a heuristic neural network

    Science.gov (United States)

    Yuan, Haiying; Wang, Xiuyu; Sun, Xun; Ju, Zijian

    2017-06-01

    Bearing fault diagnosis collects massive amounts of vibration data about a rotating machinery system, whose fault classification largely depends on feature extraction. Features reflecting bearing work states are directly extracted using time-frequency analysis of vibration signals, which leads to high dimensional feature data. To address the problem of feature dimension reduction, a compressive sensing-based feature extraction algorithm is developed to construct a concise fault feature set. Next, a heuristic PSO-BP neural network, whose learning process perfectly combines particle swarm optimization and the Levenberg-Marquardt algorithm, is constructed for fault classification. Numerical simulation experiments are conducted on four datasets sampled under different severity levels and load conditions, which verify that the proposed fault diagnosis method achieves efficient feature extraction and high classification accuracy.

  4. Sequential Clustering based Facial Feature Extraction Method for Automatic Creation of Facial Models from Orthogonal Views

    CERN Document Server

    Ghahari, Alireza

    2009-01-01

    Multiview 3D face modeling has attracted increasing attention recently and has become one of the potential avenues in future video systems. We aim to make more reliable and robust automatic feature extraction and natural 3D feature construction from 2D features detected on a pair of frontal and profile view face images. We propose several heuristic algorithms to minimize possible errors introduced by prevalent nonperfect orthogonal condition and noncoherent luminance. In our approach, we first extract the 2D features that are visible to both cameras in both views. Then, we estimate the coordinates of the features in the hidden profile view based on the visible features extracted in the two orthogonal views. Finally, based on the coordinates of the extracted features, we deform a 3D generic model to perform the desired 3D clone modeling. Present study proves the scope of resulted facial models for practical applications like face recognition and facial animation.

  5. Improving permafrost distribution modelling using feature selection algorithms

    Science.gov (United States)

    Deluigi, Nicola; Lambiel, Christophe; Kanevski, Mikhail

    2016-04-01

    The availability of an increasing number of spatial data on the occurrence of mountain permafrost allows the employment of machine learning (ML) classification algorithms for modelling the distribution of the phenomenon. One of the major problems when dealing with high-dimensional dataset is the number of input features (variables) involved. Application of ML classification algorithms to this large number of variables leads to the risk of overfitting, with the consequence of a poor generalization/prediction. For this reason, applying feature selection (FS) techniques helps simplifying the amount of factors required and improves the knowledge on adopted features and their relation with the studied phenomenon. Moreover, taking away irrelevant or redundant variables from the dataset effectively improves the quality of the ML prediction. This research deals with a comparative analysis of permafrost distribution models supported by FS variable importance assessment. The input dataset (dimension = 20-25, 10 m spatial resolution) was constructed using landcover maps, climate data and DEM derived variables (altitude, aspect, slope, terrain curvature, solar radiation, etc.). It was completed with permafrost evidences (geophysical and thermal data and rock glacier inventories) that serve as training permafrost data. Used FS algorithms informed about variables that appeared less statistically important for permafrost presence/absence. Three different algorithms were compared: Information Gain (IG), Correlation-based Feature Selection (CFS) and Random Forest (RF). IG is a filter technique that evaluates the worth of a predictor by measuring the information gain with respect to the permafrost presence/absence. Conversely, CFS is a wrapper technique that evaluates the worth of a subset of predictors by considering the individual predictive ability of each variable along with the degree of redundancy between them. Finally, RF is a ML algorithm that performs FS as part of its

  6. A Scheme of sEMG Feature Extraction for Improving Myoelectric Pattern Recognition

    Institute of Scientific and Technical Information of China (English)

    Shuai Ding; Liang Wang

    2016-01-01

    This paper proposed a feature extraction scheme based on sparse representation considering the non⁃stationary property of surface electromyography ( sEMG ) . Sparse Bayesian Learning ( SBL ) algorithm was introduced to extract the feature with optimal class separability to improve recognition accuracies of multi⁃movement patterns. The SBL algorithm exploited the compressibility ( or weak sparsity) of sEMG signal in some transformed domains. The proposed feature extracted by using the SBL algorithm was named SRC. The feature SRC represented time⁃varying characteristics of sEMG signal very effectively. We investigated the effect of the feature SRC by comparing with other fourteen individual features and eighteen multi⁃feature sets in offline recognition. The results demonstrated the feature SRC revealed the important dynamic information in the sEMG signals. And the multi⁃feature sets formed by the feature SRC and other single features yielded more superior performance on recognition accuracy. The best average recognition accuracy of 91. 67% was gained by using SVM classifier with the multi⁃feature set combining the feature SRC and the feature wavelength ( WL ) . The proposed feature extraction scheme is promising for multi⁃movement recognition with high accuracy.

  7. Feature Extraction Method of Rolling Bearing Fault Signal Based on EEMD and Cloud Model Characteristic Entropy

    Directory of Open Access Journals (Sweden)

    Long Han

    2015-09-01

    Full Text Available The randomness and fuzziness that exist in rolling bearings when faults occur result in uncertainty in acquisition signals and reduce the accuracy of signal feature extraction. To solve this problem, this study proposes a new method in which cloud model characteristic entropy (CMCE is set as the signal characteristic eigenvalue. This approach can overcome the disadvantages of traditional entropy complexity in parameter selection when solving uncertainty problems. First, the acoustic emission signals under normal and damage rolling bearing states collected from the experiments are decomposed via ensemble empirical mode decomposition. The mutual information method is then used to select the sensitive intrinsic mode functions that can reflect signal characteristics to reconstruct the signal and eliminate noise interference. Subsequently, CMCE is set as the eigenvalue of the reconstructed signal. Finally, through the comparison of experiments between sample entropy, root mean square and CMCE, the results show that CMCE can better represent the characteristic information of the fault signal.

  8. Feature-Selective Attentional Modulations in Human Frontoparietal Cortex.

    Science.gov (United States)

    Ester, Edward F; Sutterer, David W; Serences, John T; Awh, Edward

    2016-08-03

    Control over visual selection has long been framed in terms of a dichotomy between "source" and "site," where top-down feedback signals originating in frontoparietal cortical areas modulate or bias sensory processing in posterior visual areas. This distinction is motivated in part by observations that frontoparietal cortical areas encode task-level variables (e.g., what stimulus is currently relevant or what motor outputs are appropriate), while posterior sensory areas encode continuous or analog feature representations. Here, we present evidence that challenges this distinction. We used fMRI, a roving searchlight analysis, and an inverted encoding model to examine representations of an elementary feature property (orientation) across the entire human cortical sheet while participants attended either the orientation or luminance of a peripheral grating. Orientation-selective representations were present in a multitude of visual, parietal, and prefrontal cortical areas, including portions of the medial occipital cortex, the lateral parietal cortex, and the superior precentral sulcus (thought to contain the human homolog of the macaque frontal eye fields). Additionally, representations in many-but not all-of these regions were stronger when participants were instructed to attend orientation relative to luminance. Collectively, these findings challenge models that posit a strict segregation between sources and sites of attentional control on the basis of representational properties by demonstrating that simple feature values are encoded by cortical regions throughout the visual processing hierarchy, and that representations in many of these areas are modulated by attention. Influential models of visual attention posit a distinction between top-down control and bottom-up sensory processing networks. These models are motivated in part by demonstrations showing that frontoparietal cortical areas associated with top-down control represent abstract or categorical stimulus

  9. Feature selection and classification of multiparametric medical images using bagging and SVM

    Science.gov (United States)

    Fan, Yong; Resnick, Susan M.; Davatzikos, Christos

    2008-03-01

    This paper presents a framework for brain classification based on multi-parametric medical images. This method takes advantage of multi-parametric imaging to provide a set of discriminative features for classifier construction by using a regional feature extraction method which takes into account joint correlations among different image parameters; in the experiments herein, MRI and PET images of the brain are used. Support vector machine classifiers are then trained based on the most discriminative features selected from the feature set. To facilitate robust classification and optimal selection of parameters involved in classification, in view of the well-known "curse of dimensionality", base classifiers are constructed in a bagging (bootstrap aggregating) framework for building an ensemble classifier and the classification parameters of these base classifiers are optimized by means of maximizing the area under the ROC (receiver operating characteristic) curve estimated from their prediction performance on left-out samples of bootstrap sampling. This classification system is tested on a sex classification problem, where it yields over 90% classification rates for unseen subjects. The proposed classification method is also compared with other commonly used classification algorithms, with favorable results. These results illustrate that the methods built upon information jointly extracted from multi-parametric images have the potential to perform individual classification with high sensitivity and specificity.

  10. A New Method of Semantic Feature Extraction for Medical Images Data

    Institute of Scientific and Technical Information of China (English)

    XIE Conghua; SONG Yuqing; CHANG Jinyi

    2006-01-01

    In order to overcome the disadvantages of color, shape and texture-based features definition for medical images, this paper defines a new kind of semantic feature and its extraction algorithm. We firstly use kernel density estimation statistical model to describe the complicated medical image data, secondly, define some typical representative pixels of images as feature and finally, take hill-climbing strategy of Artificial Intelligence to extract those semantic features. Results of a content-based medial image retrieve system show that our semantic features have better distinguishing ability than those color, shape and texture-based features and can improve the ratios of recall and precision of this system smartly.

  11. Feature curve extraction from point clouds via developable strip intersection

    Directory of Open Access Journals (Sweden)

    Kai Wah Lee

    2016-04-01

    Full Text Available In this paper, we study the problem of computing smooth feature curves from CAD type point clouds models. The proposed method reconstructs feature curves from the intersections of developable strip pairs which approximate the regions along both sides of the features. The generation of developable surfaces is based on a linear approximation of the given point cloud through a variational shape approximation approach. A line segment sequencing algorithm is proposed for collecting feature line segments into different feature sequences as well as sequential groups of data points. A developable surface approximation procedure is employed to refine incident approximation planes of data points into developable strips. Some experimental results are included to demonstrate the performance of the proposed method.

  12. Feature selection for outcome prediction in oesophageal cancer using genetic algorithm and random forest classifier.

    Science.gov (United States)

    Paul, Desbordes; Su, Ruan; Romain, Modzelewski; Sébastien, Vauclin; Pierre, Vera; Isabelle, Gardin

    2016-12-28

    The outcome prediction of patients can greatly help to personalize cancer treatment. A large amount of quantitative features (clinical exams, imaging, …) are potentially useful to assess the patient outcome. The challenge is to choose the most predictive subset of features. In this paper, we propose a new feature selection strategy called GARF (genetic algorithm based on random forest) extracted from positron emission tomography (PET) images and clinical data. The most relevant features, predictive of the therapeutic response or which are prognoses of the patient survival 3 years after the end of treatment, were selected using GARF on a cohort of 65 patients with a local advanced oesophageal cancer eligible for chemo-radiation therapy. The most relevant predictive results were obtained with a subset of 9 features leading to a random forest misclassification rate of 18±4% and an areas under the of receiver operating characteristic (ROC) curves (AUC) of 0.823±0.032. The most relevant prognostic results were obtained with 8 features leading to an error rate of 20±7% and an AUC of 0.750±0.108. Both predictive and prognostic results show better performances using GARF than using 4 other studied methods.

  13. On the use of feature selection to improve the detection of sea oil spills in SAR images

    Science.gov (United States)

    Mera, David; Bolon-Canedo, Veronica; Cotos, J. M.; Alonso-Betanzos, Amparo

    2017-03-01

    Fast and effective oil spill detection systems are crucial to ensure a proper response to environmental emergencies caused by hydrocarbon pollution on the ocean's surface. Typically, these systems uncover not only oil spills, but also a high number of look-alikes. The feature extraction is a critical and computationally intensive phase where each detected dark spot is independently examined. Traditionally, detection systems use an arbitrary set of features to discriminate between oil spills and look-alikes phenomena. However, Feature Selection (FS) methods based on Machine Learning (ML) have proved to be very useful in real domains for enhancing the generalization capabilities of the classifiers, while discarding the existing irrelevant features. In this work, we present a generic and systematic approach, based on FS methods, for choosing a concise and relevant set of features to improve the oil spill detection systems. We have compared five FS methods: Correlation-based feature selection (CFS), Consistency-based filter, Information Gain, ReliefF and Recursive Feature Elimination for Support Vector Machine (SVM-RFE). They were applied on a 141-input vector composed of features from a collection of outstanding studies. Selected features were validated via a Support Vector Machine (SVM) classifier and the results were compared with previous works. Test experiments revealed that the classifier trained with the 6-input feature vector proposed by SVM-RFE achieved the best accuracy and Cohen's kappa coefficient (87.1% and 74.06% respectively). This is a smaller feature combination with similar or even better classification accuracy than previous works. The presented finding allows to speed up the feature extraction phase without reducing the classifier accuracy. Experiments also confirmed the significance of the geometrical features since 75.0% of the different features selected by the applied FS methods as well as 66.67% of the proposed 6-input feature vector belong to

  14. Antioxidant activity of various extracts of selected gourd vegetables.

    Science.gov (United States)

    Yadav, Baljeet S; Yadav, Roshanlal; Yadav, Ritika B; Garg, Munish

    2016-04-01

    Study was conducted to evaluate the antioxidative activity of methanolic (ME), ethanolic (EE) and butanolic extracts (BE) of selected gourd vegetables. The antioxidant activity was investigated using different assays namely ferric thiocyanate test (FTC), thiobarbituric acid test (TBA), ferric reducing antioxidant power (FRAP) and DPPH free radicals scavenging test. A densitometric HPTLC analysis was performed for the analysis of phenolic acids and flavonoids. Different extracts of the selected gourd vegetables revealed different antioxidant activity. Different extracts of Lagenaria siceraria, Momordica charantia and Luffa cylindrica revealed significantly higher (p siceraria and M. charantia.

  15. Improved Dictionary Formation and Search for Synthetic Aperture Radar Canonical Shape Feature Extraction

    Science.gov (United States)

    2014-03-27

    IMPROVED DICTIONARY FORMATION AND SEARCH FOR SYNTHETIC APERTURE RADAR CANONICAL SHAPE FEATURE EXTRACTION THESIS Matthew P. Crosser, Captain, USAF... SYNTHETIC APERTURE RADAR CANONICAL SHAPE FEATURE EXTRACTION THESIS Presented to the Faculty Department of Electrical and Computer Engineering Graduate School...APPROVED FOR PUBLIC RELEASE; DISTRIBUTION UNLIMITED AFIT-ENG-14-M-21 IMPROVED DICTIONARY FORMATION AND SEARCH FOR SYNTHETIC APERTURE RADAR CANONICAL

  16. Feature extraction for ultrasonic sensor based defect detection in ceramic components

    Science.gov (United States)

    Kesharaju, Manasa; Nagarajah, Romesh

    2014-02-01

    High density silicon carbide materials are commonly used as the ceramic element of hard armour inserts used in traditional body armour systems to reduce their weight, while providing improved hardness, strength and elastic response to stress. Currently, armour ceramic tiles are inspected visually offline using an X-ray technique that is time consuming and very expensive. In addition, from X-rays multiple defects are also misinterpreted as single defects. Therefore, to address these problems the ultrasonic non-destructive approach is being investigated. Ultrasound based inspection would be far more cost effective and reliable as the methodology is applicable for on-line quality control including implementation of accept/reject criteria. This paper describes a recently developed methodology to detect, locate and classify various manufacturing defects in ceramic tiles using sub band coding of ultrasonic test signals. The wavelet transform is applied to the ultrasonic signal and wavelet coefficients in the different frequency bands are extracted and used as input features to an artificial neural network (ANN) for purposes of signal classification. Two different classifiers, using artificial neural networks (supervised) and clustering (un-supervised) are supplied with features selected using Principal Component Analysis(PCA) and their classification performance compared. This investigation establishes experimentally that Principal Component Analysis(PCA) can be effectively used as a feature selection method that provides superior results for classifying various defects in the context of ultrasonic inspection in comparison with the X-ray technique.

  17. Wear Debris Identification Using Feature Extraction and Neural Network

    Institute of Scientific and Technical Information of China (English)

    王伟华; 马艳艳; 殷勇辉; 王成焘

    2004-01-01

    A method and results of identification of wear debris using their morphological features are presented. The color images of wear debris were used as initial data. Each particle was characterized by a set of numerical parameters combined by its shape, color and surface texture features through a computer vision system. Those features were used as input vector of artificial neural network for wear debris identification. A radius basis function (RBF) network based model suitable for wear debris recognition was established,and its algorithm was presented in detail. Compared with traditional recognition methods, the RBF network model is faster in convergence, and higher in accuracy.

  18. Unsupervised Feature Selection Based on the Morisita Index

    Science.gov (United States)

    Golay, Jean; Kanevski, Mikhail

    2016-04-01

    Recent breakthroughs in technology have radically improved our ability to collect and store data. As a consequence, the size of datasets has been increasing rapidly both in terms of number of variables (or features) and number of instances. Since the mechanism of many phenomena is not well known, too many variables are sampled. A lot of them are redundant and contribute to the emergence of three major challenges in data mining: (1) the complexity of result interpretation, (2) the necessity to develop new methods and tools for data processing, (3) the possible reduction in the accuracy of learning algorithms because of the curse of dimensionality. This research deals with a new algorithm for selecting the smallest subset of features conveying all the information of a dataset (i.e. an algorithm for removing redundant features). It is a new version of the Fractal Dimensionality Reduction (FDR) algorithm [1] and it relies on two ideas: (a) In general, data lie on non-linear manifolds of much lower dimension than that of the spaces where they are embedded. (b) The situation describes in (a) is partly due to redundant variables, since they do not contribute to increasing the dimension of manifolds, called Intrinsic Dimension (ID). The suggested algorithm implements these ideas by selecting only the variables influencing the data ID. Unlike the FDR algorithm, it resorts to a recently introduced ID estimator [2] based on the Morisita index of clustering and to a sequential forward search strategy. Consequently, in addition to its ability to capture non-linear dependences, it can deal with large datasets and its implementation is straightforward in any programming environment. Many real world case studies are considered. They are related to environmental pollution and renewable resources. References [1] C. Traina Jr., A.J.M. Traina, L. Wu, C. Faloutsos, Fast feature selection using fractal dimension, in: Proceedings of the XV Brazilian Symposium on Databases, SBBD, pp. 158

  19. 2D-HIDDEN MARKOV MODEL FEATURE EXTRACTION STRATEGY OF ROTATING MACHINERY FAULT DIAGNOSIS

    Institute of Scientific and Technical Information of China (English)

    2006-01-01

    A new feature extraction method based on 2D-hidden Markov model(HMM) is proposed.Meanwhile the time index and frequency index are introduced to represent the new features. The new feature extraction strategy is tested by the experimental data that collected from Bently rotor experiment system. The results show that this methodology is very effective to extract the feature of vibration signals in the rotor speed-up course and can be extended to other non-stationary signal analysis fields in the future.

  20. Feature Extraction Using Supervised Independent Component Analysis by Maximizing Class Distance

    Science.gov (United States)

    Sakaguchi, Yoshinori; Ozawa, Seiichi; Kotani, Manabu

    Recently, Independent Component Analysis (ICA) has been applied to not only problems of blind signal separation, but also feature extraction of patterns. However, the effectiveness of pattern features extracted by conventional ICA algorithms depends on pattern sets; that is, how patterns are distributed in the feature space. As one of the reasons, we have pointed out that ICA features are obtained by increasing only their independence even if the class information is available. In this context, we can expect that more high-performance features can be obtained by introducing the class information into conventional ICA algorithms. In this paper, we propose a supervised ICA (SICA) that maximizes Mahalanobis distance between features of different classes as well as maximize their independence. In the first experiment, two-dimensional artificial data are applied to the proposed SICA algorithm to see how maximizing Mahalanobis distance works well in the feature extraction. As a result, we demonstrate that the proposed SICA algorithm gives good features with high separability as compared with principal component analysis and a conventional ICA. In the second experiment, the recognition performance of features extracted by the proposed SICA is evaluated using the three data sets of UCI Machine Learning Repository. From the results, we show that the better recognition accuracy is obtained using our proposed SICA. Furthermore, we show that pattern features extracted by SICA are better than those extracted by only maximizing the Mahalanobis distance.

  1. Feature Extraction and Spatial Interpolation for Improved Wireless Location Sensing

    Directory of Open Access Journals (Sweden)

    Chris Rizos

    2008-04-01

    Full Text Available This paper proposes a new methodology to improve location-sensing accuracy in wireless network environments eliminating the effects of non-line-of-sight errors. After collecting bulks of anonymous location measurements from a wireless network, the preparation stage of the proposed methodology begins. Investigating the collected location measurements in terms of signal features and geometric features, feature locations are identified. After the identification of feature locations, the non-line-of-sight error correction maps are generated. During the real-time location sensing stage, each user can request localization with a set of location measurements. With respected to the reported measurements, the pre-computed correction maps are applied. As a result, localization accuracy improves by eliminating the non-line-of-sight errors. A simulation result, assuming a typical dense urban environment, demonstrates the benefits of the proposed location sensing methodology.

  2. Performance Comparison between Different Feature Extraction Techniques with SVM Using Gurumukhi Script

    Directory of Open Access Journals (Sweden)

    Sandeep Dangi,

    2014-07-01

    Full Text Available This paper represent the offline handwritten character recognition for Gurumukhi script. It is a major script of india. Many work has been done in many languages such as English , Chinese , Devanagri , Tamil etc. Gurumukhi is a script of Punjabi Language which is widely spoken across the globe. In this paper focus on better character recognition accuracy. The dataset include 7000 samples collected in different writing styles. These dataset divided in two set Training and Test. For Training set collect 5600 samples and 1400 as test set. The evaluated feature extraction include: Distance Profile, Diagonal feature and BDD(Background Direction Distribution. These features were classified by using SVM classifier. The Performance comparison have been made using one classifier with different feature extraction techniques. The experiment show that Diagonal feature extraction method has achieved highest recognition accuracy 95.39% than other features extraction method.

  3. Comparison of half and full-leaf shape feature extraction for leaf classification

    Science.gov (United States)

    Sainin, Mohd Shamrie; Ahmad, Faudziah; Alfred, Rayner

    2016-08-01

    Shape is the main information for leaf feature that most of the current literatures in leaf identification utilize the whole leaf for feature extraction and to be used in the leaf identification process. In this paper, study of half-leaf features extraction for leaf identification is carried out and the results are compared with the results obtained from the leaf identification based on a full-leaf features extraction. Identification and classification is based on shape features that are represented as cosines and sinus angles. Six single classifiers obtained from WEKA and seven ensemble methods are used to compare their performance accuracies over this data. The classifiers were trained using 65 leaves in order to classify 5 different species of preliminary collection of Malaysian medicinal plants. The result shows that half-leaf features extraction can be used for leaf identification without decreasing the predictive accuracy.

  4. Extracting features buried within high density atom probe point cloud data through simplicial homology

    Energy Technology Data Exchange (ETDEWEB)

    Srinivasan, Srikant; Kaluskar, Kaustubh; Broderick, Scott; Rajan, Krishna, E-mail: krajan@iastate.edu

    2015-12-15

    Feature extraction from Atom Probe Tomography (APT) data is usually performed by repeatedly delineating iso-concentration surfaces of a chemical component of the sample material at different values of concentration threshold, until the user visually determines a satisfactory result in line with prior knowledge. However, this approach allows for important features, buried within the sample, to be visually obscured by the high density and volume (~10{sup 7} atoms) of APT data. This work provides a data driven methodology to objectively determine the appropriate concentration threshold for classifying different phases, such as precipitates, by mapping the topology of the APT data set using a concept from algebraic topology termed persistent simplicial homology. A case study of Sc precipitates in an Al–Mg–Sc alloy is presented demonstrating the power of this technique to capture features, such as precise demarcation of Sc clusters and Al segregation at the cluster boundaries, not easily available by routine visual adjustment. - Highlights: • Provides a data driven methodology to select appropriate concentration threshold. • Maps topology of APT data using persistent simplicial homology. • The application to Sc precipitates in an Al–Mg–Sc alloy is provided. • Capture features not easily available by routine visual adjustment.

  5. An Advanced Approach to Extraction of Colour Texture Features Based on GLCM

    OpenAIRE

    Miroslav Benco; Robert Hudec; Patrik Kamencay; Martina Zachariasova; Slavomir Matuska

    2014-01-01

    This paper discusses research in the area of texture image classification. More specifically, the combination of texture and colour features is researched. The principle objective is to create a robust descriptor for the extraction of colour texture features. The principles of two well-known methods for grey- level texture feature extraction, namely GLCM (grey- level co-occurrence matrix) and Gabor filters, are used in experiments. For the texture classification, the support vector machine is...

  6. LEAST-SQUARES METHOD-BASED FEATURE FITTING AND EXTRACTION IN REVERSE ENGINEERING

    Institute of Scientific and Technical Information of China (English)

    2003-01-01

    The main purpose of reverse engineering is to convert discrete data points into piecewise smooth, continuous surface models.Before carrying out model reconstruction it is significant to extract geometric features because the quality of modeling greatly depends on the representation of features.Some fitting techniques of natural quadric surfaces with least-squares method are described.And these techniques can be directly used to extract quadric surfaces features during the process of segmentation for point cloud.

  7. Efficient feature extraction from wide-area motion imagery by MapReduce in Hadoop

    Science.gov (United States)

    Cheng, Erkang; Ma, Liya; Blaisse, Adam; Blasch, Erik; Sheaff, Carolyn; Chen, Genshe; Wu, Jie; Ling, Haibin

    2014-06-01

    Wide-Area Motion Imagery (WAMI) feature extraction is important for applications such as target tracking, traffic management and accident discovery. With the increasing amount of WAMI collections and feature extraction from the data, a scalable framework is needed to handle the large amount of information. Cloud computing is one of the approaches recently applied in large scale or big data. In this paper, MapReduce in Hadoop is investigated for large scale feature extraction tasks for WAMI. Specifically, a large dataset of WAMI images is divided into several splits. Each split has a small subset of WAMI images. The feature extractions of WAMI images in each split are distributed to slave nodes in the Hadoop system. Feature extraction of each image is performed individually in the assigned slave node. Finally, the feature extraction results are sent to the Hadoop File System (HDFS) to aggregate the feature information over the collected imagery. Experiments of feature extraction with and without MapReduce are conducted to illustrate the effectiveness of our proposed Cloud-Enabled WAMI Exploitation (CAWE) approach.

  8. An Effective Fault Feature Extraction Method for Gas Turbine Generator System Diagnosis

    Directory of Open Access Journals (Sweden)

    Jian-Hua Zhong

    2016-01-01

    Full Text Available Fault diagnosis is very important to maintain the operation of a gas turbine generator system (GTGS in power plants, where any abnormal situations will interrupt the electricity supply. The fault diagnosis of the GTGS faces the main challenge that the acquired data, vibration or sound signals, contain a great deal of redundant information which extends the fault identification time and degrades the diagnostic accuracy. To improve the diagnostic performance in the GTGS, an effective fault feature extraction framework is proposed to solve the problem of the signal disorder and redundant information in the acquired signal. The proposed framework combines feature extraction with a general machine learning method, support vector machine (SVM, to implement an intelligent fault diagnosis. The feature extraction method adopts wavelet packet transform and time-domain statistical features to extract the features of faults from the vibration signal. To further reduce the redundant information in extracted features, kernel principal component analysis is applied in this study. Experimental results indicate that the proposed feature extracted technique is an effective method to extract the useful features of faults, resulting in improvement of the performance of fault diagnosis for the GTGS.

  9. Built-up Areas Extraction in High Resolution SAR Imagery based on the method of Multiple Feature Weighted Fusion

    Science.gov (United States)

    Liu, X.; Zhang, J. X.; Zhao, Z.; Ma, A. D.

    2015-06-01

    Synthetic aperture radar in the application of remote sensing technology is becoming more and more widely because of its all-time and all-weather operation, feature extraction research in high resolution SAR image has become a hot topic of concern. In particular, with the continuous improvement of airborne SAR image resolution, image texture information become more abundant. It's of great significance to classification and extraction. In this paper, a novel method for built-up areas extraction using both statistical and structural features is proposed according to the built-up texture features. First of all, statistical texture features and structural features are respectively extracted by classical method of gray level co-occurrence matrix and method of variogram function, and the direction information is considered in this process. Next, feature weights are calculated innovatively according to the Bhattacharyya distance. Then, all features are weighted fusion. At last, the fused image is classified with K-means classification method and the built-up areas are extracted after post classification process. The proposed method has been tested by domestic airborne P band polarization SAR images, at the same time, two groups of experiments based on the method of statistical texture and the method of structural texture were carried out respectively. On the basis of qualitative analysis, quantitative analysis based on the built-up area selected artificially is enforced, in the relatively simple experimentation area, detection rate is more than 90%, in the relatively complex experimentation area, detection rate is also higher than the other two methods. In the study-area, the results show that this method can effectively and accurately extract built-up areas in high resolution airborne SAR imagery.

  10. Rule set transferability for object-based feature extraction

    NARCIS (Netherlands)

    Anders, N.S.; Seijmonsbergen, Arie C.; Bouten, Willem

    2015-01-01

    Cirques are complex landforms resulting from glacial erosion and can be used to estimate Equilibrium Line Altitudes and infer climate history. Automated extraction of cirques may help research on glacial geomorphology and climate change. Our objective was to test the transferability of an object-

  11. Rule set transferability for object-based feature extraction

    NARCIS (Netherlands)

    Anders, N.S.; Seijmonsbergen, Arie C.; Bouten, Willem

    2015-01-01

    Cirques are complex landforms resulting from glacial erosion and can be used to estimate Equilibrium Line Altitudes and infer climate history. Automated extraction of cirques may help research on glacial geomorphology and climate change. Our objective was to test the transferability of an

  12. Feature selection of seismic waveforms for long period event detection at Cotopaxi Volcano

    Science.gov (United States)

    Lara-Cueva, R. A.; Benítez, D. S.; Carrera, E. V.; Ruiz, M.; Rojo-Álvarez, J. L.

    2016-04-01

    Volcano Early Warning Systems (VEWS) have become a research topic in order to preserve human lives and material losses. In this setting, event detection criteria based on classification using machine learning techniques have proven useful, and a number of systems have been proposed in the literature. However, to the best of our knowledge, no comprehensive and principled study has been conducted to compare the influence of the many different sets of possible features that have been used as input spaces in previous works. We present an automatic recognition system of volcano seismicity, by considering feature extraction, event classification, and subsequent event detection, in order to reduce the processing time as a first step towards a high reliability automatic detection system in real-time. We compiled and extracted a comprehensive set of temporal, moving average, spectral, and scale-domain features, for separating long period seismic events from background noise. We benchmarked two usual kinds of feature selection techniques, namely, filter (mutual information and statistical dependence) and embedded (cross-validation and pruning), each of them by using suitable and appropriate classification algorithms such as k Nearest Neighbors (k-NN) and Decision Trees (DT). We applied this approach to the seismicity presented at Cotopaxi Volcano in Ecuador during 2009 and 2010. The best results were obtained by using a 15 s segmentation window, feature matrix in the frequency domain, and DT classifier, yielding 99% of detection accuracy and sensitivity. Selected features and their interpretation were consistent among different input spaces, in simple terms of amplitude and spectral content. Our study provides the framework for an event detection system with high accuracy and reduced computational requirements.

  13. A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms.

    Science.gov (United States)

    Şen, Baha; Peker, Musa; Çavuşoğlu, Abdullah; Çelebi, Fatih V

    2014-03-01

    Sleep scoring is one of the most important diagnostic methods in psychiatry and neurology. Sleep staging is a time consuming and difficult task undertaken by sleep experts. This study aims to identify a method which would classify sleep stages automatically and with a high degree of accuracy and, in this manner, will assist sleep experts. This study consists of three stages: feature extraction, feature selection from EEG signals, and classification of these signals. In the feature extraction stage, it is used 20 attribute algorithms in four categories. 41 feature parameters were obtained from these algorithms. Feature selection is important in the elimination of irrelevant and redundant features and in this manner prediction accuracy is improved and computational overhead in classification is reduced. Effective feature selection algorithms such as minimum redundancy maximum relevance (mRMR); fast correlation based feature selection (FCBF); ReliefF; t-test; and Fisher score algorithms are preferred at the feature selection stage in selecting a set of features which best represent EEG signals. The features obtained are used as input parameters for the classification algorithms. At the classification stage, five different classification algorithms (random forest (RF); feed-forward neural network (FFNN); decision tree (DT); support vector machine (SVM); and radial basis function neural network (RBF)) classify the problem. The results, obtained from different classification algorithms, are provided so that a comparison can be made between computation times and accuracy rates. Finally, it is obtained 97.03 % classification accuracy using the proposed method. The results show that the proposed method indicate the ability to design a new intelligent assistance sleep scoring system.

  14. Fault feature extraction of planet gear in wind turbine gearbox based on spectral kurtosis and time wavelet energy spectrum

    Science.gov (United States)

    Kong, Yun; Wang, Tianyang; Li, Zheng; Chu, Fulei

    2017-01-01

    Planetary transmission plays a vital role in wind turbine drivetrains, and its fault diagnosis has been an important and challenging issue. Owing to the complicated and coupled vibration source, time-variant vibration transfer path, and heavy background noise masking effect, the vibration signal of planet gear in wind turbine gearboxes exhibits several unique characteristics: Complex frequency components, low signal-to-noise ratio, and weak fault feature. In this sense, the periodic impulsive components induced by a localized defect are hard to extract, and the fault detection of planet gear in wind turbines remains to be a challenging research work. Aiming to extract the fault feature of planet gear effectively, we propose a novel feature extraction method based on spectral kurtosis and time wavelet energy spectrum (SK-TWES) in the paper. Firstly, the spectral kurtosis (SK) and kurtogram of raw vibration signals are computed and exploited to select the optimal filtering parameter for the subsequent band-pass filtering. Then, the band-pass filtering is applied to extrude periodic transient impulses using the optimal frequency band in which the corresponding SK value is maximal. Finally, the time wavelet energy spectrum analysis is performed on the filtered signal, selecting Morlet wavelet as the mother wavelet which possesses a high similarity to the impulsive components. The experimental signals collected from the wind turbine gearbox test rig demonstrate that the proposed method is effective at the feature extraction and fault diagnosis for the planet gear with a localized defect.

  15. Fault feature extraction of planet gear in wind turbine gearbox based on spectral kurtosis and time wavelet energy spectrum

    Science.gov (United States)

    Kong, Yun; Wang, Tianyang; Li, Zheng; Chu, Fulei

    2017-09-01

    Planetary transmission plays a vital role in wind turbine drivetrains, and its fault diagnosis has been an important and challenging issue. Owing to the complicated and coupled vibration source, time-variant vibration transfer path, and heavy background noise masking effect, the vibration signal of planet gear in wind turbine gearboxes exhibits several unique characteristics: Complex frequency components, low signal-to-noise ratio, and weak fault feature. In this sense, the periodic impulsive components induced by a localized defect are hard to extract, and the fault detection of planet gear in wind turbines remains to be a challenging research work. Aiming to extract the fault feature of planet gear effectively, we propose a novel feature extraction method based on spectral kurtosis and time wavelet energy spectrum (SK-TWES) in the paper. Firstly, the spectral kurtosis (SK) and kurtogram of raw vibration signals are computed and exploited to select the optimal filtering parameter for the subsequent band-pass filtering. Then, the band-pass filtering is applied to extrude periodic transient impulses using the optimal frequency band in which the corresponding SK value is maximal. Finally, the time wavelet energy spectrum analysis is performed on the filtered signal, selecting Morlet wavelet as the mother wavelet which possesses a high similarity to the impulsive components. The experimental signals collected from the wind turbine gearbox test rig demonstrate that the proposed method is effective at the feature extraction and fault diagnosis for the planet gear with a localized defect.

  16. Robust Speech Recognition Method Based on Discriminative Environment Feature Extraction

    Institute of Scientific and Technical Information of China (English)

    HAN Jiqing; GAO Wen

    2001-01-01

    It is an effective approach to learn the influence of environmental parameters,such as additive noise and channel distortions, from training data for robust speech recognition.Most of the previous methods are based on maximum likelihood estimation criterion. However,these methods do not lead to a minimum error rate result. In this paper, a novel discrimina-tive learning method of environmental parameters, which is based on Minimum ClassificationError (MCE) criterion, is proposed. In the method, a simple classifier and the Generalized Probabilistic Descent (GPD) algorithm are adopted to iteratively learn the environmental parameters. Consequently, the clean speech features are estimated from the noisy speech features with the estimated environmental parameters, and then the estimations of clean speech features are utilized in the back-end HMM classifier. Experiments show that the best error rate reduction of 32.1% is obtained, tested on a task of 18 isolated confusion Korean words, relative to a conventional HMM system.

  17. Selection of clinical features for pattern recognition applied to gait analysis.

    Science.gov (United States)

    Altilio, Rosa; Paoloni, Marco; Panella, Massimo

    2017-04-01

    This paper deals with the opportunity of extracting useful information from medical data retrieved directly from a stereophotogrammetric system applied to gait analysis. A feature selection method to exhaustively evaluate all the possible combinations of the gait parameters is presented, in order to find the best subset able to classify among diseased and healthy subjects. This procedure will be used for estimating the performance of widely used classification algorithms, whose performance has been ascertained in many real-world problems with respect to well-known classification benchmarks, both in terms of number of selected features and classification accuracy. Precisely, support vector machine, Naive Bayes and K nearest neighbor classifiers can obtain the lowest classification error, with an accuracy greater than 97 %. For the considered classification problem, the whole set of features will be proved to be redundant and it can be significantly pruned. Namely, groups of 3 or 5 features only are able to preserve high accuracy when the aim is to check the anomaly of a gait. The step length and the swing speed are the most informative features for the gait analysis, but also cadence and stride may add useful information for the movement evaluation.

  18. Ant-cuckoo colony optimization for feature selection in digital mammogram.

    Science.gov (United States)

    Jona, J B; Nagaveni, N

    2014-01-15

    Digital mammogram is the only effective screening method to detect the breast cancer. Gray Level Co-occurrence Matrix (GLCM) textural features are extracted from the mammogram. All the features are not essential to detect the mammogram. Therefore identifying the relevant feature is the aim of this work. Feature selection improves the classification rate and accuracy of any classifier. In this study, a new hybrid metaheuristic named Ant-Cuckoo Colony Optimization a hybrid of Ant Colony Optimization (ACO) and Cuckoo Search (CS) is proposed for feature selection in Digital Mammogram. ACO is a good metaheuristic optimization technique but the drawback of this algorithm is that the ant will walk through the path where the pheromone density is high which makes the whole process slow hence CS is employed to carry out the local search of ACO. Support Vector Machine (SVM) classifier with Radial Basis Kernal Function (RBF) is done along with the ACO to classify the normal mammogram from the abnormal mammogram. Experiments are conducted in miniMIAS database. The performance of the new hybrid algorithm is compared with the ACO and PSO algorithm. The results show that the hybrid Ant-Cuckoo Colony Optimization algorithm is more accurate than the other techniques.

  19. Weak transient fault feature extraction based on an optimized Morlet wavelet and kurtosis

    Science.gov (United States)

    Qin, Yi; Xing, Jianfeng; Mao, Yongfang

    2016-08-01

    Aimed at solving the key problem in weak transient detection, the present study proposes a new transient feature extraction approach using the optimized Morlet wavelet transform, kurtosis index and soft-thresholding. Firstly, a fast optimization algorithm based on the Shannon entropy is developed to obtain the optimized Morlet wavelet parameter. Compared to the existing Morlet wavelet parameter optimization algorithm, this algorithm has lower computation complexity. After performing the optimized Morlet wavelet transform on the analyzed signal, the kurtosis index is used to select the characteristic scales and obtain the corresponding wavelet coefficients. From the time-frequency distribution of the periodic impulsive signal, it is found that the transient signal can be reconstructed by the wavelet coefficients at several characteristic scales, rather than the wavelet coefficients at just one characteristic scale, so as to improve the accuracy of transient detection. Due to the noise influence on the characteristic wavelet coefficients, the adaptive soft-thresholding method is applied to denoise these coefficients. With the denoised wavelet coefficients, the transient signal can be reconstructed. The proposed method was applied to the analysis of two simulated signals, and the diagnosis of a rolling bearing fault and a gearbox fault. The superiority of the method over the fast kurtogram method was verified by the results of simulation analysis and real experiments. It is concluded that the proposed method is extremely suitable for extracting the periodic impulsive feature from strong background noise.

  20. Variable selection in near-infrared spectroscopy: Benchmarking of feature selection methods on biodiesel data

    Energy Technology Data Exchange (ETDEWEB)

    Balabin, Roman M., E-mail: balabin@org.chem.ethz.ch [Department of Chemistry and Applied Biosciences, ETH Zurich, 8093 Zurich (Switzerland); Smirnov, Sergey V. [Unimilk Joint Stock Co., 143421 Moscow Region (Russian Federation)

    2011-04-29

    During the past several years, near-infrared (near-IR/NIR) spectroscopy has increasingly been adopted as an analytical tool in various fields from petroleum to biomedical sectors. The NIR spectrum (above 4000 cm{sup -1}) of a sample is typically measured by modern instruments at a few hundred of wavelengths. Recently, considerable effort has been directed towards developing procedures to identify variables (wavelengths) that contribute useful information. Variable selection (VS) or feature selection, also called frequency selection or wavelength selection, is a critical step in data analysis for vibrational spectroscopy (infrared, Raman, or NIRS). In this paper, we compare the performance of 16 different feature selection methods for the prediction of properties of biodiesel fuel, including density, viscosity, methanol content, and water concentration. The feature selection algorithms tested include stepwise multiple linear regression (MLR-step), interval partial least squares regression (iPLS), backward iPLS (BiPLS), forward iPLS (FiPLS), moving window partial least squares regression (MWPLS), (modified) changeable size moving window partial least squares (CSMWPLS/MCSMWPLSR), searching combination moving window partial least squares (SCMWPLS), successive projections algorithm (SPA), uninformative variable elimination (UVE, including UVE-SPA), simulated annealing (SA), back-propagation artificial neural networks (BP-ANN), Kohonen artificial neural network (K-ANN), and genetic algorithms (GAs, including GA-iPLS). Two linear techniques for calibration model building, namely multiple linear regression (MLR) and partial least squares regression/projection to latent structures (PLS/PLSR), are used for the evaluation of biofuel properties. A comparison with a non-linear calibration model, artificial neural networks (ANN-MLP), is also provided. Discussion of gasoline, ethanol-gasoline (bioethanol), and diesel fuel data is presented. The results of other spectroscopic

  1. A-Survey of Feature Extraction and Classification Techniques in OCR Systems

    Directory of Open Access Journals (Sweden)

    Rohit Verma

    2012-11-01

    Full Text Available This paper describes a set of feature extraction and classification techniques, which play very important role in the recognition of characters. Feature extraction provides us methods with the help of which we can identify characters uniquely and with high degree of accuracy. Feature extraction helps us to find the shape contained in the pattern. Although a number of techniques are available for feature extraction and classification, but the choice of an excellent technique decides the degree of accuracy of recognition. A lot of research has been done in this field and new techniques of extraction and classification has been developed. The objective of this paper is to review these techniques, so that the set of these techniques can be appreciated.

  2. Improved face representation by nonuniform multilevel selection of Gabor convolution features.

    Science.gov (United States)

    Du, Shan; Ward, Rabab Kreidieh

    2009-12-01

    Gabor wavelets are widely employed in face representation to decompose face images into their spatial-frequency domains. The Gabor wavelet transform, however, introduces very high dimensional data. To reduce this dimensionality, uniform sampling of Gabor features has traditionally been used. Since uniform sampling equally treats all the features, it can lead to a loss of important features while retaining trivial ones. In this paper, we propose a new face representation method that employs nonuniform multilevel selection of Gabor features. The proposed method is based on the local statistics of the Gabor features and is implemented using a coarse-to-fine hierarchical strategy. Gabor features that correspond to important face regions are automatically selected and sampled finer than other features. The nonuniformly extracted Gabor features are then classified using principal component analysis and/or linear discriminant analysis for the purpose of face recognition. To verify the effectiveness of the proposed method, experiments have been conducted on benchmark face image databases where the images vary in illumination, expression, pose, and scale. Compared with the methods that use the original gray-scale image with 4096-dimensional data and uniform sampling with 2560-dimensional data, the proposed method results in a significantly higher recognition rate, with a substantial lower dimension of around 700. The experimental results also show that the proposed method works well not only when multiple sample images are available for training but also when only one sample image is available for each person. The proposed face representation method has the advantages of low complexity, low dimensionality, and high discriminance.

  3. Texture Feature Extraction Method Combining Nonsubsampled Contour Transformation with Gray Level Co-occurrence Matrix

    Directory of Open Access Journals (Sweden)

    Xiaolan He

    2013-12-01

    Full Text Available Gray level co-occurrence matrix (GLCM is an important method to extract the image texture features of synthetic aperture radar (SAR. However, GLCM can only extract the textures under single scale and single direction. A kind of texture feature extraction method combining nonsubsampled contour transformation (NSCT and GLCM is proposed, so as to achieve the extraction of texture features under multi-scale and multi-direction. We firstly conducted multi-scale and multi-direction decomposition on the SAR images with NSCT, secondly extracted the symbiosis amount with GLCM from the obtained sub-band images, then conducted the correlation analysis for the extracted symbiosis amount to remove the redundant characteristic quantity; and combined it with the gray features to constitute the multi-feature vector. Finally, we made full use of the advantages of the support vector machine in the aspects of small sample database and generalization ability, and completed the division of multi-feature vector space by SVM so as to achieve the SAR image segmentation. The results of the experiment showed that the segmentation accuracy rate could be improved and good edge retention effect could be obtained through using the GLCM texture extraction method based on NSCT domain and multi-feature fusion in the SAR image segmentation.

  4. Bispectrum-based feature extraction technique for devising a practical brain-computer interface

    Science.gov (United States)

    Shahid, Shahjahan; Prasad, Girijesh

    2011-04-01

    The extraction of distinctly separable features from electroencephalogram (EEG) is one of the main challenges in designing a brain-computer interface (BCI). Existing feature extraction techniques for a BCI are mostly developed based on traditional signal processing techniques assuming that the signal is Gaussian and has linear characteristics. But the motor imagery (MI)-related EEG signals are highly non-Gaussian, non-stationary and have nonlinear dynamic characteristics. This paper proposes an advanced, robust but simple feature extraction technique for a MI-related BCI. The technique uses one of the higher order statistics methods, the bispectrum, and extracts the features of nonlinear interactions over several frequency components in MI-related EEG signals. Along with a linear discriminant analysis classifier, the proposed technique has been used to design an MI-based BCI. Three performance measures, classification accuracy, mutual information and Cohen's kappa have been evaluated and compared with a BCI using a contemporary power spectral density-based feature extraction technique. It is observed that the proposed technique extracts nearly recording-session-independent distinct features resulting in significantly much higher and consistent MI task detection accuracy and Cohen's kappa. It is therefore concluded that the bispectrum-based feature extraction is a promising technique for detecting different brain states.

  5. Leveraging Large Data with Weak Supervision for Joint Feature and Opinion Word Extraction

    Institute of Scientific and Technical Information of China (English)

    房磊; 刘彪; 黄民烈

    2015-01-01

    Product feature and opinion word extraction is very important for fine granular sentiment analysis. In this paper, we leverage large-scale unlabeled data for joint extraction of feature and opinion words under a knowledge poor setting, in which only a few feature-opinion pairs are utilized as weak supervision. Our major contributions are two-fold: first, we propose a data-driven approach to represent product features and opinion words as a list of corpus-level syntactic relations, which captures rich language structures;second, we build a simple yet robust unsupervised model with prior knowledge incorporated to extract new feature and opinion words, which obtains high performance robustly. The extraction process is based upon a bootstrapping framework which, to some extent, reduces error propagation under large data. Experimental results under various settings compared with state-of-the-art baselines demonstrate that our method is effective and promising.

  6. Feature Extraction from 3D Point Cloud Data Based on Discrete Curves

    Directory of Open Access Journals (Sweden)

    Yi An

    2013-01-01

    Full Text Available Reliable feature extraction from 3D point cloud data is an important problem in many application domains, such as reverse engineering, object recognition, industrial inspection, and autonomous navigation. In this paper, a novel method is proposed for extracting the geometric features from 3D point cloud data based on discrete curves. We extract the discrete curves from 3D point cloud data and research the behaviors of chord lengths, angle variations, and principal curvatures at the geometric features in the discrete curves. Then, the corresponding similarity indicators are defined. Based on the similarity indicators, the geometric features can be extracted from the discrete curves, which are also the geometric features of 3D point cloud data. The threshold values of the similarity indicators are taken from [0,1], which characterize the relative relationship and make the threshold setting easier and more reasonable. The experimental results demonstrate that the proposed method is efficient and reliable.

  7. Shift- and deformation-robust optical character recognition based on parallel extraction of simple features

    Science.gov (United States)

    Jang, Ju-Seog; Shin, Dong-Hak

    1997-03-01

    For a flexible pattern recognition system that is robust to the input variations, a feature extraction approach is investigated. Two types of features are extracted: one is line orientations, and the other is the eigenvectors of the covariance matrix of the patterns that cannot be distinguished with the line orientation features alone. For the feature extraction, the Vander Lugt-type filters are used, which are recorded in a small spot of holographic recording medium by use of multiplexing techniques. A multilayer perceptron implemented in a computer is trained with a set of optically extracted features, so that it can recognize the input patterns that are not used in the training. Through preliminary experiments, where English character patterns composed of only straight line segments were tested, the feasibility of our approach is demonstrated.

  8. The extraction of wind turbine rolling bearing fault features based on VMD and bispectrum

    Science.gov (United States)

    Yuan, Jingyi; Song, Peng; Wang, Yongjie

    2017-08-01

    Aiming at extracting wind turbine rolling bearing fault feature against the background noise, the method of based on variational mode decomposition and bispectrum were proposed. Firstly, the rolling bearing fault signal was decomposed using VMD. The two components, which had obvious impact features, were extracted and reconstructed using the kurtosis-correlation coefficient criteria. Secondly, the reconstructed signal was analyzed using the bispectrum. The method has good noise suppression capability. Lastly, according to the bispectrum analysis, the fault feature of rolling bearing could be extracted. The analysis of rolling bearing fault simulation signal verifies the effectiveness of the proposed method. And it was applied to extract the fault features of the bearing fault test signal. The different fault features of rolling bearing could be identified effectively. Thus the fault diagnosis can be achieved accurately.

  9. AUTO-EXTRACTING TECHNIQUE OF DYNAMIC CHAOS FEATURES FOR NONLINEAR TIME SERIES

    Institute of Scientific and Technical Information of China (English)

    CHEN Guo

    2006-01-01

    The main purpose of nonlinear time series analysis is based on the rebuilding theory of phase space, and to study how to transform the response signal to rebuilt phase space in order to extract dynamic feature information, and to provide effective approach for nonlinear signal analysis and fault diagnosis of nonlinear dynamic system. Now, it has already formed an important offset of nonlinear science. But, traditional method cannot extract chaos features automatically, and it needs man's participation in the whole process. A new method is put forward, which can implement auto-extracting of chaos features for nonlinear time series. Firstly, to confirm time delay τ by autocorrelation method; Secondly, to compute embedded dimension m and correlation dimension D;Thirdly, to compute the maximum Lyapunov index λmax; Finally, to calculate the chaos degree Dch of features extracting has important meaning to fault diagnosis of nonlinear system based on nonlinear chaos features. Examples show validity of the proposed method.

  10. Comparative Analysis of PSO and GA in Geom-Statistical Character Features Selection for Online Character Recognition

    Directory of Open Access Journals (Sweden)

    Fenwa O.D

    2015-08-01

    Full Text Available Online handwriting recognition today has special interest due to increased usage of the hand held devices and it has become a difficult problem because of the high variability and ambiguity in the character shapes written by individuals. One major problem encountered by researchers in developing character recognition system is selection of efficient features (optimal features. In this paper, a feature extraction technique for online character recognition system was developed using hybrid of geometrical and statistical (Geom-statistical features. Thus, through the integration of geometrical and statistical features, insights were gained into new character properties, since these types of features were considered to be complementary. Several optimization techniques have been used in literature for feature selection in character recognition such as; Ant Colony Optimization Algorithm (ACO, Genetic Algorithm (GA, Particle Swarm Optimization (PSO and Simulated Annealing but comparative analysis of GA and PSO in online character has not been carried out. In this paper, a comparative analysis of performance was made between the GA and PSO in optimizing the Geom-statistical features in online character recognition using Modified Optical Backpropagation (MOBP as classifier. Simulation of the system was done and carried out on Matlab 7.10a. The results generated show that PSO is a well-accepted optimization algorithm in selection of optimal features as it outperforms the GA in terms of number of features selected, training time and recognition accuracy.

  11. Anticancer activities of selected species of North American lichen extracts.

    Science.gov (United States)

    Shrestha, Gajendra; El-Naggar, Atif M; St Clair, Larry L; O'Neill, Kim L

    2015-01-01

    Cancer is the second leading cause of human deaths in the USA. Despite continuous efforts to treat cancer over the past 50 years, human mortality rates have not decreased significantly. Natural products, such as lichens, have been good sources of anticancer drugs. This study reports the cytotoxic activity of crude extracts of 17 lichen species against Burkitt's lymphoma (Raji) cells. Out of the 17 lichen species, extracts from 14 species showed cytotoxicity against Raji cells. On the basis of IC50 values, we selected Xanthoparmelia chlorochroa and Tuckermannopsis ciliaris to study the mechanism of cell death. Viability of normal lymphocytes was not affected by the extracts of X. chlorochroa and T. ciliaris. We found that extracts from both lichens decreased proliferation, accumulated cells at the G0 /G1 stage, and caused apoptosis in a dose-dependent manner. Both lichen extracts also caused upregulation of p53. The T. ciliaris extract upregulated the expression of TK1 but X. chlorochroa did not. We also found that usnic, salazinic, constictic, and norstictic acids were present in the extract of X. chlorochroa, whereas protolichesterinic acid in T. ciliaris extracts. Our data demonstrate that lichen extracts merit further research as a potential source of anticancer drugs.

  12. Pattern representation in feature extraction and classifier design: matrix versus vector.

    Science.gov (United States)

    Wang, Zhe; Chen, Songcan; Liu, Jun; Zhang, Daoqiang

    2008-05-01

    The matrix, as an extended pattern representation to the vector, has proven to be effective in feature extraction. However, the subsequent classifier following the matrix-pattern- oriented feature extraction is generally still based on the vector pattern representation (namely, MatFE + VecCD), where it has been demonstrated that the effectiveness in classification just attributes to the matrix representation in feature extraction. This paper looks at the possibility of applying the matrix pattern representation to both feature extraction and classifier design. To this end, we propose a so-called fully matrixized approach, i.e., the matrix-pattern-oriented feature extraction followed by the matrix-pattern-oriented classifier design (MatFE + MatCD). To more comprehensively validate MatFE + MatCD, we further consider all the possible combinations of feature extraction (FE) and classifier design (CD) on the basis of patterns represented by matrix and vector respectively, i.e., MatFE + MatCD, MatFE + VecCD, just the matrix-pattern-oriented classifier design (MatCD), the vector-pattern-oriented feature extraction followed by the matrix-pattern-oriented classifier design (VecFE + MatCD), the vector-pattern-oriented feature extraction followed by the vector-pattern-oriented classifier design (VecFE + VecCD) and just the vector-pattern-oriented classifier design (VecCD). The experiments on the combinations have shown the following: 1) the designed fully matrixized approach (MatFE + MatCD) has an effective and efficient performance on those patterns with the prior structural knowledge such as images; and 2) the matrix gives us an alternative feasible pattern representation in feature extraction and classifier designs, and meanwhile provides a necessary validation for "ugly duckling" and "no free lunch" theorems.

  13. Edge-Based Feature Extraction Method and Its Application to Image Retrieval

    Directory of Open Access Journals (Sweden)

    G. Ohashi

    2003-10-01

    Full Text Available We propose a novel feature extraction method for content-bases image retrieval using graphical rough sketches. The proposed method extracts features based on the shape and texture of objects. This edge-based feature extraction method functions by representing the relative positional relationship between edge pixels, and has the advantage of being shift-, scale-, and rotation-invariant. In order to verify its effectiveness, we applied the proposed method to 1,650 images obtained from the Hamamatsu-city Museum of Musical Instruments and 5,500 images obtained from Corel Photo Gallery. The results verified that the proposed method is an effective tool for achieving accurate retrieval.

  14. Diagonal Based Feature Extraction for Handwritten Alphabets Recognition System using Neural Network

    CERN Document Server

    Pradeep, J; Himavathi, S; 10.5121/ijcsit.2011.3103

    2011-01-01

    An off-line handwritten alphabetical character recognition system using multilayer feed forward neural network is described in the paper. A new method, called, diagonal based feature extraction is introduced for extracting the features of the handwritten alphabets. Fifty data sets, each containing 26 alphabets written by various people, are used for training the neural network and 570 different handwritten alphabetical characters are used for testing. The proposed recognition system performs quite well yielding higher levels of recognition accuracy compared to the systems employing the conventional horizontal and vertical methods of feature extraction. This system will be suitable for converting handwritten documents into structural text form and recognizing handwritten names.

  15. Wavelet Energy Feature Extraction and Matching for Palmprint Recognition

    Institute of Scientific and Technical Information of China (English)

    Xiang-Qian Wu; Kuan-Quan Wang; David Zhang

    2005-01-01

    According to the fact that the basic features of a palmprint, including principal lines, wrinkles and ridges,have different resolutions, in this paper we analyze palmprints using a multi-resolution method and define a novel palmprint feature, which called wavelet energy feature (WEF), based on the wavelet transform. WEF can reflect the wavelet energy distribution of the principal lines, wrinkles and ridges in different directions at different resolutions (scales), thus it can efficiently characterize palmprints. This paper also analyses the discriminabilities of each level WEF and, according to these discriminabilities, chooses a suitable weight for each level to compute the weighted city block distance for recognition. The experimental results show that the order of the discriminabilities of each level WEF, from strong to weak, is the 4th, 3rd,5th, 2nd and 1st level. It also shows that WEF is robust to some extent in rotation and translation of the images. Accuracies of 99.24% and 99.45% have been obtained in palmprint verification and palmprint identification, respectively. These results demonstrate the power of the proposed approach.

  16. The fuzzy Hough Transform-feature extraction in medical images

    Energy Technology Data Exchange (ETDEWEB)

    Philip, K.P.; Dove, E.L.; Stanford, W.; Chandran, K.B. (Univ. of Iowa, Iowa City, IA (United States)); McPherson, D.D.; Gotteiner, N.L. (Northwestern Univ., Chicago, IL (United States). Dept. of Internal Medicine)

    1994-06-01

    Identification of anatomical features is a necessary step for medical image analysis. Automatic methods for feature identification using conventional pattern recognition techniques typically classify an object as a member of a predefined class of objects, but do not attempt to recover the exact or approximate shape of that object. For this reason, such techniques are usually not sufficient to identify the borders of organs when individual geometry varies in local detail, even though the general geometrical shape is similar. The authors present an algorithm that detects features in an image based on approximate geometrical models. The algorithm is based on the traditional and generalized Hough Transforms but includes notions from fuzzy set theory. The authors use the new algorithm to roughly estimate the actual locations of boundaries of an internal organ, and from this estimate, to determine a region of interest around the organ. Based on this rough estimate of the border location, and the derived region of interest, the authors find the final estimate of the true borders with other image processing techniques. The authors present results that demonstrate that the algorithm was successfully used to estimate the approximate location of the chest wall in humans, and of the left ventricular contours of a dog heart obtained from cine-computed tomographic images. The authors use this fuzzy Hough Transform algorithm as part of a larger procedures to automatically identify the myocardial contours of the heart. This algorithm may also allow for more rapid image processing and clinical decision making in other medical imaging applications.

  17. Hand veins feature extraction using DT-CNNS

    Science.gov (United States)

    Malki, Suleyman; Spaanenburg, Lambert

    2007-05-01

    As the identification process is based on the unique patterns of the users, biometrics technologies are expected to provide highly secure authentication systems. The existing systems using fingerprints or retina patterns are, however, very vulnerable. One's fingerprints are accessible as soon as the person touches a surface, while a high resolution camera easily captures the retina pattern. Thus, both patterns can easily be "stolen" and forged. Beside, technical considerations decrease the usability for these methods. Due to the direct contact with the finger, the sensor gets dirty, which decreases the authentication success ratio. Aligning the eye with a camera to capture the retina pattern gives uncomfortable feeling. On the other hand, vein patterns of either a palm of the hand or a single finger offer stable, unique and repeatable biometrics features. A fingerprint-based identification system using Cellular Neural Networks has already been proposed by Gao. His system covers all stages of a typical fingerprint verification procedure from Image Preprocessing to Feature Matching. This paper performs a critical review of the individual algorithmic steps. Notably, the operation of False Feature Elimination is applied only once instead of 3 times. Furthermore, the number of iterations is limited to 1 for all used templates. Hence, the computational need of the feedback contribution is removed. Consequently the computational effort is drastically reduced without a notable chance in quality. This allows a full integration of the detection mechanism. The system is prototyped on a Xilinx Virtex II Pro P30 FPGA.

  18. Automatic extraction of disease-specific features from Doppler images

    Science.gov (United States)

    Negahdar, Mohammadreza; Moradi, Mehdi; Parajuli, Nripesh; Syeda-Mahmood, Tanveer

    2017-03-01

    Flow Doppler imaging is widely used by clinicians to detect diseases of the valves. In particular, continuous wave (CW) Doppler mode scan is routinely done during echocardiography and shows Doppler signal traces over multiple heart cycles. Traditionally, echocardiographers have manually traced such velocity envelopes to extract measurements such as decay time and pressure gradient which are then matched to normal and abnormal values based on clinical guidelines. In this paper, we present a fully automatic approach to deriving these measurements for aortic stenosis retrospectively from echocardiography videos. Comparison of our method with measurements made by echocardiographers shows large agreement as well as identification of new cases missed by echocardiographers.

  19. Feature Extraction and Automatic Material Classification of Underground Objects from Ground Penetrating Radar Data

    Directory of Open Access Journals (Sweden)

    Qingqing Lu

    2014-01-01

    Full Text Available Ground penetrating radar (GPR is a powerful tool for detecting objects buried underground. However, the interpretation of the acquired signals remains a challenging task since an experienced user is required to manage the entire operation. Particularly difficult is the classification of the material type of underground objects in noisy environment. This paper proposes a new feature extraction method. First, discrete wavelet transform (DWT transforms A-Scan data and approximation coefficients are extracted. Then, fractional Fourier transform (FRFT is used to transform approximation coefficients into fractional domain and we extract features. The features are supplied to the support vector machine (SVM classifiers to automatically identify underground objects material. Experiment results show that the proposed feature-based SVM system has good performances in classification accuracy compared to statistical and frequency domain feature-based SVM system in noisy environment and the classification accuracy of features proposed in this paper has little relationship with the SVM models.

  20. Feature Subset Selection for Hot Method Prediction using Genetic Algorithm wrapped with Support Vector Machines

    Directory of Open Access Journals (Sweden)

    S. Johnson

    2011-01-01

    Full Text Available Problem statement: All compilers have simple profiling-based heuristics to identify and predict program hot methods and also to make optimization decisions. The major challenge in the profile-based optimization is addressing the problem of overhead. The aim of this work is to perform feature subset selection using Genetic Algorithms (GA to improve and refine the machine learnt static hot method predictive technique and to compare the performance of the new models against the simple heuristics. Approach: The relevant features for training the predictive models are extracted from an initial set of randomly selected ninety static program features, with the help of the GA wrapped with the predictive model using the Support Vector Machine (SVM, a Machine Learning (ML algorithm. Results: The GA-generated feature subsets containing thirty and twenty nine features respectively for the two predictive models when tested on MiBench predict Long Running Hot Methods (LRHM and frequently called hot methods (FCHM with the respective accuracies of 71% and 80% achieving an increase of 19% and 22%. Further, inlining of the predicted LRHM and FCHM improve the program performance by 3% and 5% as against 4% and 6% with Low Level Virtual Machines (LLVM default heuristics. When intra-procedural optimizations (IPO are performed on the predicted hot methods, this system offers a performance improvement of 5% and 4% as against 0% and 3% by LLVM default heuristics on LRHM and FCHM respectively. However, we observe an improvement of 36% in certain individual programs. Conclusion: Overall, the results indicate that the GA wrapped with SVM derived feature reduction improves the hot method prediction accuracy and that the technique of hot method prediction based optimization is potentially useful in selective optimization.

  1. Feature Selection by Merging Sequential Bidirectional Search into Relevance Vector Machine in Condition Monitoring

    Institute of Scientific and Technical Information of China (English)

    ZHANG Kui; DONG Yu; BALL Andrew

    2015-01-01

    For more accurate fault detection and diagnosis, there is an increasing trend to use a large number of sensors and to collect data at high frequency. This inevitably produces large-scale data and causes difficulties in fault classification. Actually, the classification methods are simply intractable when applied to high-dimensional condition monitoring data. In order to solve the problem, engineers have to resort to complicated feature extraction methods to reduce the dimensionality of data. However, the features transformed by the methods cannot be understood by the engineers due to a loss of the original engineering meaning. In this paper, other forms of dimensionality reduction technique(feature selection methods) are employed to identify machinery condition, based only on frequency spectrum data. Feature selection methods are usually divided into three main types: filter, wrapper and embedded methods. Most studies are mainly focused on the first two types, whilst the development and application of the embedded feature selection methods are very limited. This paper attempts to explore a novel embedded method. The method is formed by merging a sequential bidirectional search algorithm into scale parameters tuning within a kernel function in the relevance vector machine. To demonstrate the potential for applying the method to machinery fault diagnosis, the method is implemented to rolling bearing experimental data. The results obtained by using the method are consistent with the theoretical interpretation, proving that this algorithm has important engineering significance in revealing the correlation between the faults and relevant frequency features. The proposed method is a theoretical extension of relevance vector machine, and provides an effective solution to detect the fault-related frequency components with high efficiency.

  2. Feature selection by merging sequential bidirectional search into relevance vector machine in condition monitoring

    Science.gov (United States)

    Zhang, Kui; Dong, Yu; Ball, Andrew

    2015-11-01

    For more accurate fault detection and diagnosis, there is an increasing trend to use a large number of sensors and to collect data at high frequency. This inevitably produces large-scale data and causes difficulties in fault classification. Actually, the classification methods are simply intractable when applied to high-dimensional condition monitoring data. In order to solve the problem, engineers have to resort to complicated feature extraction methods to reduce the dimensionality of data. However, the features transformed by the methods cannot be understood by the engineers due to a loss of the original engineering meaning. In this paper, other forms of dimensionality reduction technique(feature selection methods) are employed to identify machinery condition, based only on frequency spectrum data. Feature selection methods are usually divided into three main types: filter, wrapper and embedded methods. Most studies are mainly focused on the first two types, whilst the development and application of the embedded feature selection methods are very limited. This paper attempts to explore a novel embedded method. The method is formed by merging a sequential bidirectional search algorithm into scale parameters tuning within a kernel function in the relevance vector machine. To demonstrate the potential for applying the method to machinery fault diagnosis, the method is implemented to rolling bearing experimental data. The results obtained by using the method are consistent with the theoretical interpretation, proving that this algorithm has important engineering significance in revealing the correlation between the faults and relevant frequency features. The proposed method is a theoretical extension of relevance vector machine, and provides an effective solution to detect the fault-related frequency components with high efficiency.

  3. Relevant Feature Integration and Extraction for Single-Trial Motor Imagery Classification

    Directory of Open Access Journals (Sweden)

    Lili Li

    2017-06-01

    Full Text Available Brain computer interfaces provide a novel channel for the communication between brain and output devices. The effectiveness of the brain computer interface is based on the classification accuracy of single trial brain signals. The common spatial pattern (CSP algorithm is believed to be an effective algorithm for the classification of single trial brain signals. As the amplitude feature for spatial projection applied by this algorithm is based on a broad frequency bandpass filter (mainly 5–30 Hz in which the frequency band is often selected by experience, the CSP is sensitive to noise and the influence of other irrelevant information in the selected broad frequency band. In this paper, to improve the CSP, a novel relevant feature integration and extraction algorithm is proposed. Before projecting, we integrated the motor relevant information to suppress the interference of noise and irrelevant information, as well as to improve the spatial difference for projection. The algorithm was evaluated with public datasets. It showed significantly better classification performance with single trial electroencephalography (EEG data, increasing by 6.8% compared with the CSP.

  4. Selective extraction of isolated mitotic apparatus. Evidence that typical microtubule protein is extracted by organic mercurial.

    Science.gov (United States)

    Bibring, T; Baxandall, J

    1971-02-01

    Mitotic apparatus isolated from sea urchin eggs has been treated with meralluride sodium under conditions otherwise resembling those of its isolation. The treatment causes a selective morphological disappearance of microtubules while extracting a major protein fraction, probably consisting of two closely related proteins, which constitutes about 10% of mitotic apparatus protein. Extraction of other cell particulates under similar conditions yields much less of this protein. The extracted protein closely resembles outer doublet microtubule protein from sea urchin sperm tail in properties considered typical of microtubule proteins: precipitation by calcium ion and vinblastine, electrophoretic mobility in both acid and basic polyacrylamide gels, sedimentation coefficient, molecular weight, and, according to a preliminary determination, amino acid composition. An antiserum against a preparation of sperm tail outer doublet microtubules cross-reacts with the extract from mitotic apparatus. On the basis of these findings it appears that microtubule protein is selectively extracted from isolated mitotic apparatus by treatment with meralluride, and is a typical microtubule protein.

  5. VHDL implementation of feature-extraction algorithm for the PANDA electromagnetic calorimeter

    Science.gov (United States)

    Guliyev, E.; Kavatsyuk, M.; Lemmens, P. J. J.; Tambave, G.; Löhner, H.; Panda Collaboration

    2012-02-01

    A simple, efficient, and robust feature-extraction algorithm, developed for the digital front-end electronics of the electromagnetic calorimeter of the PANDA spectrometer at FAIR, Darmstadt, is implemented in VHDL for a commercial 16 bit 100 MHz sampling ADC. The source-code is available as an open-source project and is adaptable for other projects and sampling ADCs. Best performance with different types of signal sources can be achieved through flexible parameter selection. The on-line data-processing in FPGA enables to construct an almost dead-time free data acquisition system which is successfully evaluated as a first step towards building a complete trigger-less readout chain. Prototype setups are studied to determine the dead-time of the implemented algorithm, the rate of false triggering, timing performance, and event correlations.

  6. Signals features extraction in liquid-gas flow measurements using gamma densitometry. Part 1: time domain

    Science.gov (United States)

    Hanus, Robert; Zych, Marcin; Petryka, Leszek; Jaszczur, Marek; Hanus, Paweł

    2016-03-01

    The paper presents an application of the gamma-absorption method to study a gas-liquid two-phase flow in a horizontal pipeline. In the tests on laboratory installation two 241Am radioactive sources and scintillation probes with NaI(Tl) crystals have been used. The experimental set-up allows recording of stochastic signals, which describe instantaneous content of the stream in the particular cross-section of the flow mixture. The analyses of these signals by statistical methods allow to determine the mean velocity of the gas phase. Meanwhile, the selected features of signals provided by the absorption set, can be applied to recognition of the structure of the flow. In this work such three structures of air-water flow as: plug, bubble, and transitional plug - bubble one were considered. The recorded raw signals were analyzed in time domain and several features were extracted. It was found that following features of signals as the mean, standard deviation, root mean square (RMS), variance and 4th moment are most useful to recognize the structure of the flow.

  7. Signals features extraction in liquid-gas flow measurements using gamma densitometry. Part 1: time domain

    Directory of Open Access Journals (Sweden)

    Hanus Robert

    2016-01-01

    Full Text Available The paper presents an application of the gamma-absorption method to study a gas-liquid two-phase flow in a horizontal pipeline. In the tests on laboratory installation two 241Am radioactive sources and scintillation probes with NaI(Tl crystals have been used. The experimental set-up allows recording of stochastic signals, which describe instantaneous content of the stream in the particular cross-section of the flow mixture. The analyses of these signals by statistical methods allow to determine the mean velocity of the gas phase. Meanwhile, the selected features of signals provided by the absorption set, can be applied to recognition of the structure of the flow. In this work such three structures of air-water flow as: plug, bubble, and transitional plug – bubble one were considered. The recorded raw signals were analyzed in time domain and several features were extracted. It was found that following features of signals as the mean, standard deviation, root mean square (RMS, variance and 4th moment are most useful to recognize the structure of the flow.

  8. Water Feature Extraction and Change Detection Using Multitemporal Landsat Imagery

    Directory of Open Access Journals (Sweden)

    Komeil Rokni

    2014-05-01

    Full Text Available Lake Urmia is the 20th largest lake and the second largest hyper saline lake (before September 2010 in the world. It is also the largest inland body of salt water in the Middle East. Nevertheless, the lake has been in a critical situation in recent years due to decreasing surface water and increasing salinity. This study modeled the spatiotemporal changes of Lake Urmia in the period 2000–2013 using the multi-temporal Landsat 5-TM, 7-ETM+ and 8-OLI images. In doing so, the applicability of different satellite-derived indexes including Normalized Difference Water Index (NDWI, Modified NDWI (MNDWI, Normalized Difference Moisture Index (NDMI, Water Ratio Index (WRI, Normalized Difference Vegetation Index (NDVI, and Automated Water Extraction Index (AWEI were investigated for the extraction of surface water from Landsat data. Overall, the NDWI was found superior to other indexes and hence it was used to model the spatiotemporal changes of the lake. In addition, a new approach based on Principal Components of multi-temporal NDWI (NDWI-PCs was proposed and evaluated for surface water change detection. The results indicate an intense decreasing trend in Lake Urmia surface area in the period 2000–2013, especially between 2010 and 2013 when the lake lost about one third of its surface area compared to the year 2000. The results illustrate the effectiveness of the NDWI-PCs approach for surface water change detection, especially in detecting the changes between two and three different times, simultaneously.

  9. An auto-calibrated neural spike recording channel with feature extraction capabilities

    Science.gov (United States)

    Rodríguez-Pérez, Alberto; Ruiz-Amaya, Jesús; Delgado-Restituto, Manuel; Rodríguez-Vázquez, Ángel

    2011-05-01

    This paper presents a power efficient architecture for a neural spike recording channel. The channel offers a selfcalibration operation mode and can be used both for signal tracking (to raw digitize the acquired neural waveform) and feature extraction (to build a PWL approximation of the spikes in order to reduce data bandwidth on the RF-link). The neural threshold voltage is adaptively calculated during the spike detection period using basic digital operations. The neural input signal is amplified and filtered using a LNA, reconfigurable Band-Pass Filter, followed by a fully reconfigurable 8-bit ADC. The key element is the ADC architecture. It is a binary search data converter with a SCimplementation. Due to its architecture, it can be programmed to work either as a PGA, S&H or ADC. In order to allow power saving, inactive blocks are powered off depending on the selected operation mode, ADC sampling frequency is reconfigured and bias current is dynamically adapted during the conversion. Due to the ADC low input capacitance, the power consumption of the input LNA can be decreased and the overall power consumption of the channel is low. The prototype was implemented using a CMOS 0.13um standard process, and it occupies 400um x 400um. Simulations from extracted layout show very promising results. The power consumption of the complete channel for the signal tracking operations is 2.8uW, and is increased to 3.0uW when the feature extraction operation is performed, one of the lowest reported.

  10. Detailed Hydrographic Feature Extraction from High-Resolution LiDAR Data

    Energy Technology Data Exchange (ETDEWEB)

    Danny L. Anderson

    2012-05-01

    Detailed hydrographic feature extraction from high-resolution light detection and ranging (LiDAR) data is investigated. Methods for quantitatively evaluating and comparing such extractions are presented, including the use of sinuosity and longitudinal root-mean-square-error (LRMSE). These metrics are then used to quantitatively compare stream networks in two studies. The first study examines the effect of raster cell size on watershed boundaries and stream networks delineated from LiDAR-derived digital elevation models (DEMs). The study confirmed that, with the greatly increased resolution of LiDAR data, smaller cell sizes generally yielded better stream network delineations, based on sinuosity and LRMSE. The second study demonstrates a new method of delineating a stream directly from LiDAR point clouds, without the intermediate step of deriving a DEM. Direct use of LiDAR point clouds could improve efficiency and accuracy of hydrographic feature extractions. The direct delineation method developed herein and termed “mDn”, is an extension of the D8 method that has been used for several decades with gridded raster data. The method divides the region around a starting point into sectors, using the LiDAR data points within each sector to determine an average slope, and selecting the sector with the greatest downward slope to determine the direction of flow. An mDn delineation was compared with a traditional grid-based delineation, using TauDEM, and other readily available, common stream data sets. Although, the TauDEM delineation yielded a sinuosity that more closely matches the reference, the mDn delineation yielded a sinuosity that was higher than either the TauDEM method or the existing published stream delineations. Furthermore, stream delineation using the mDn method yielded the smallest LRMSE.

  11. Selective Extraction of Uranium from Liquid or Supercritical Carbon Dioxide

    Energy Technology Data Exchange (ETDEWEB)

    Farawila, Anne F.; O' Hara, Matthew J.; Wai, Chien M.; Taylor, Harry Z.; Liao, Yu-Jung

    2012-07-31

    Current liquid-liquid extraction processes used in recycling irradiated nuclear fuel rely on (1) strong nitric acid to dissolve uranium oxide fuel, and (2) the use of aliphatic hydrocarbons as a diluent in formulating the solvent used to extract uranium. The nitric acid dissolution process is not selective. It dissolves virtually the entire fuel meat which complicates the uranium extraction process. In addition, a solvent washing process is used to remove TBP degradation products, which adds complexity to the recycling plant and increases the overall plant footprint and cost. A liquid or supercritical carbon dioxide (l/sc -CO2) system was designed to mitigate these problems. Indeed, TBP nitric acid complexes are highly soluble in l/sc -CO2 and are capable of extracting uranium directly from UO2, UO3 and U3O8 powders. This eliminates the need for total acid dissolution of the irradiated fuel. Furthermore, since CO2 is easily recycled by evaporation at room temperature and pressure, it eliminates the complex solvent washing process. In this report, we demonstrate: (1) A reprocessing scheme starting with the selective extraction of uranium from solid uranium oxides into a TBP-HNO3 loaded Sc-CO2 phase, (2) Back extraction of uranium into an aqueous phase, and (3) Conversion of recovered purified uranium into uranium oxide. The purified uranium product from step 3 can be disposed of as low level waste, or mixed with enriched uranium for use in a reactor for another fuel cycle. After an introduction on the concept and properties of supercritical fluids, we first report the characterization of the different oxides used for this project. Our extraction system and our online monitoring capability using UV-Vis absorbance spectroscopy directly in sc-CO2 is then presented. Next, the uranium extraction efficiencies and kinetics is demonstrated for different oxides and under different physical and chemical conditions: l/sc -CO2 pressure and temperature, TBP/HNO3 complex used

  12. The fuzzy Hough transform-feature extraction in medical images.

    Science.gov (United States)

    Philip, K P; Dove, E L; McPherson, D D; Gotteiner, N L; Stanford, W; Chandran, K B

    1994-01-01

    Identification of anatomical features is a necessary step for medical image analysis. Automatic methods for feature identification using conventional pattern recognition techniques typically classify an object as a member of a predefined class of objects, but do not attempt to recover the exact or approximate shape of that object. For this reason, such techniques are usually not sufficient to identify the borders of organs when individual geometry varies in local detail, even though the general geometrical shape is similar. The authors present an algorithm that detects features in an image based on approximate geometrical models. The algorithm is based on the traditional and generalized Hough Transforms but includes notions from fuzzy set theory. The authors use the new algorithm to roughly estimate the actual locations of boundaries of an internal organ, and from this estimate, to determine a region of interest around the organ. Based on this rough estimate of the border location, and the derived region of interest, the authors find the final (improved) estimate of the true borders with other (subsequently used) image processing techniques. They present results that demonstrate that the algorithm was successfully used to estimate the approximate location of the chest wall in humans, and of the left ventricular contours of a dog heart obtained from cine-computed tomographic images. The authors use this fuzzy Hough transform algorithm as part of a larger procedure to automatically identify the myocardial contours of the heart. This algorithm may also allow for more rapid image processing and clinical decision making in other medical imaging applications.

  13. Novel Method for Color Textures Features Extraction Based on GLCM

    Directory of Open Access Journals (Sweden)

    R. Hudec

    2007-12-01

    Full Text Available Texture is one of most popular features for image classification and retrieval. Forasmuch as grayscale textures provide enough information to solve many tasks, the color information was not utilized. But in the recent years, many researchers have begun to take color information into consideration. In the texture analysis field, many algorithms have been enhanced to process color textures and new ones have been researched. In this paper the new method for color GLCM textures and comparing with other good known methods is presented.

  14. Iris image enhancement for feature recognition and extraction

    CSIR Research Space (South Africa)

    Mabuza, GP

    2012-10-01

    Full Text Available Gonzalez, R.C. and Woods, R.E. 2002. Digital Image Processing 2nd Edition, Instructor?s manual .Englewood Cliffs, Prentice Hall, pp 17-36. Proen?a, H. and Alexandre, L.A. 2007. Toward Noncooperative Iris Recognition: A classification approach using... for performing such tasks and yielding better accuracy (Gonzalez & Woods, 2002). METHODOLOGY The block diagram in Figure 2 demonstrates the processes followed to achieve the results. Figure 2: Methodology flow chart Iris image enhancement for feature...

  15. Detergent selection for enhanced extraction of membrane proteins.

    Science.gov (United States)

    Arachea, Buenafe T; Sun, Zhen; Potente, Nina; Malik, Radhika; Isailovic, Dragan; Viola, Ronald E

    2012-11-01

    Generating stable conditions for membrane proteins after extraction from their lipid bilayer environment is essential for subsequent characterization. Detergents are the most widely used means to obtain this stable environment; however, different types of membrane proteins have been found to require detergents with varying properties for optimal extraction efficiency and stability after extraction. The extraction profiles of several detergent types have been examined for membranes isolated from bacteria and yeast, and for a set of recombinant target proteins. The extraction efficiencies of these detergents increase at higher concentrations, and were shown to correlate with their respective CMC values. Two alkyl sugar detergents, octyl-β-d-glucoside (OG) and 5-cyclohexyl-1-pentyl-β-d-maltoside (Cymal-5), and a zwitterionic surfactant, N-decylphosphocholine (Fos-choline-10), were generally effective in the extraction of a broad range of membrane proteins. However, certain detergents were more effective than others in the extraction of specific classes of integral membrane proteins, offering guidelines for initial detergent selection. The differences in extraction efficiencies among this small set of detergents supports the value of detergent screening and optimization to increase the yields of targeted membrane proteins.

  16. Geometric feature extraction by a multimarked point process.

    Science.gov (United States)

    Lafarge, Florent; Gimel'farb, Georgy; Descombes, Xavier

    2010-09-01

    This paper presents a new stochastic marked point process for describing images in terms of a finite library of geometric objects. Image analysis based on conventional marked point processes has already produced convincing results but at the expense of parameter tuning, computing time, and model specificity. Our more general multimarked point process has simpler parametric setting, yields notably shorter computing times, and can be applied to a variety of applications. Both linear and areal primitives extracted from a library of geometric objects are matched to a given image using a probabilistic Gibbs model, and a Jump-Diffusion process is performed to search for the optimal object configuration. Experiments with remotely sensed images and natural textures show that the proposed approach has good potential. We conclude with a discussion about the insertion of more complex object interactions in the model by studying the compromise between model complexity and efficiency.

  17. Medical Image Fusion Based on Feature Extraction and Sparse Representation.

    Science.gov (United States)

    Fei, Yin; Wei, Gao; Zongxi, Song

    2017-01-01

    As a novel multiscale geometric analysis tool, sparse representation has shown many advantages over the conventional image representation methods. However, the standard sparse representation does not take intrinsic structure and its time complexity into consideration. In this paper, a new fusion mechanism for multimodal medical images based on sparse representation and decision map is proposed to deal with these problems simultaneously. Three decision maps are designed including structure information map (SM) and energy information map (EM) as well as structure and energy map (SEM) to make the results reserve more energy and edge information. SM contains the local structure feature captured by the Laplacian of a Gaussian (LOG) and EM contains the energy and energy distribution feature detected by the mean square deviation. The decision map is added to the normal sparse representation based method to improve the speed of the algorithm. Proposed approach also improves the quality of the fused results by enhancing the contrast and reserving more structure and energy information from the source images. The experiment results of 36 groups of CT/MR, MR-T1/MR-T2, and CT/PET images demonstrate that the method based on SR and SEM outperforms five state-of-the-art methods.

  18. FEATURE EXTRACTION OF RETINAL IMAGE FOR DIAGNOSIS OF ABNORMAL EYES

    Directory of Open Access Journals (Sweden)

    S. Praveenkumar

    2011-05-01

    Full Text Available Currently, medical image processing draws intense interests of scien- tists and physicians to aid in clinical diagnosis. The retinal Fundus image is widely used in the diagnosis and treatment of various eye diseases such as Diabetic Retinopathy, glaucoma etc. If these diseases are detected and treated early, many of the visual losses can be pre- vented. This paper presents the methods to detect main features of Fundus images such as optic disk, fovea, exudates and blood vessels. To determine the optic Disk and its centre we find the brightest part of the Fundus. The candidate region of fovea is defined an area circle. The detection of fovea is done by using its spatial relationship with optic disk. Exudates are found using their high grey level variation and their contours are determined by means of morphological recon- struction techniques. The blood vessels are highlighted using bottom hat transform and morphological dilation after edge detection. All the enhanced features are then combined in the Fundus image for the detection of abnormalities in eye.

  19. Ischemia episode detection in ECG using kernel density estimation, support vector machine and feature selection

    Directory of Open Access Journals (Sweden)

    Park Jinho

    2012-06-01

    Full Text Available Abstract Background Myocardial ischemia can be developed into more serious diseases. Early Detection of the ischemic syndrome in electrocardiogram (ECG more accurately and automatically can prevent it from developing into a catastrophic disease. To this end, we propose a new method, which employs wavelets and simple feature selection. Methods For training and testing, the European ST-T database is used, which is comprised of 367 ischemic ST episodes in 90 records. We first remove baseline wandering, and detect time positions of QRS complexes by a method based on the discrete wavelet transform. Next, for each heart beat, we extract three features which can be used for differentiating ST episodes from normal: 1 the area between QRS offset and T-peak points, 2 the normalized and signed sum from QRS offset to effective zero voltage point, and 3 the slope from QRS onset to offset point. We average the feature values for successive five beats to reduce effects of outliers. Finally we apply classifiers to those features. Results We evaluated the algorithm by kernel density estimation (KDE and support vector machine (SVM methods. Sensitivity and specificity for KDE were 0.939 and 0.912, respectively. The KDE classifier detects 349 ischemic ST episodes out of total 367 ST episodes. Sensitivity and specificity of SVM were 0.941 and 0.923, respectively. The SVM classifier detects 355 ischemic ST episodes. Conclusions We proposed a new method for detecting ischemia in ECG. It contains signal processing techniques of removing baseline wandering and detecting time positions of QRS complexes by discrete wavelet transform, and feature extraction from morphology of ECG waveforms explicitly. It was shown that the number of selected features were sufficient to discriminate ischemic ST episodes from the normal ones. We also showed how the proposed KDE classifier can automatically select kernel bandwidths, meaning that the algorithm does not require any numerical

  20. A Review of Feature Extraction Software for Microarray Gene Expression Data

    Directory of Open Access Journals (Sweden)

    Ching Siang Tan

    2014-01-01

    Full Text Available When gene expression data are too large to be processed, they are transformed into a reduced representation set of genes. Transforming large-scale gene expression data into a set of genes is called feature extraction. If the genes extracted are carefully chosen, this gene set can extract the relevant information from the large-scale gene expression data, allowing further analysis by using this reduced representation instead of the full size data. In this paper, we review numerous software applications that can be used for feature extraction. The software reviewed is mainly for Principal Component Analysis (PCA, Independent Component Analysis (ICA, Partial Least Squares (PLS, and Local Linear Embedding (LLE. A summary and sources of the software are provided in the last section for each feature extraction method.

  1. Bio-medical (EMG Signal Analysis and Feature Extraction Using Wavelet Transform

    Directory of Open Access Journals (Sweden)

    Rhutuja Raut

    2015-03-01

    Full Text Available In this paper, the multi-channel electromyogram acquisition system is being developed using programmable system on chip (PSOC microcontroller to obtain the surface of EMG signal. The two pairs of single-channel surface electrodes are utilized to measure the EMG signal obtained from forearm muscles. Then different levels of Wavelet family are used to analyze the EMG signal. Later features in terms of root mean square, logarithm of root mean square, centroid of frequency, as well as standard deviation were used to extract the EMG signal. The proposed method of feature extraction for extracting EMG signal states that root means square feature extraction method gives better performance as compared to the other features. In the near future, this method can be used to control a mechanical arm as well as robotic arm in field of real-time processing.

  2. Recent development of feature extraction and classification multispectral/hyperspectral images: a systematic literature review

    Science.gov (United States)

    Setiyoko, A.; Dharma, I. G. W. S.; Haryanto, T.

    2017-01-01

    Multispectral data and hyperspectral data acquired from satellite sensor have the ability in detecting various objects on the earth ranging from low scale to high scale modeling. These data are increasingly being used to produce geospatial information for rapid analysis by running feature extraction or classification process. Applying the most suited model for this data mining is still challenging because there are issues regarding accuracy and computational cost. This research aim is to develop a better understanding regarding object feature extraction and classification applied for satellite image by systematically reviewing related recent research projects. A method used in this research is based on PRISMA statement. After deriving important points from trusted sources, pixel based and texture-based feature extraction techniques are promising technique to be analyzed more in recent development of feature extraction and classification.

  3. Micromotion feature extraction of radar target using tracking pulses with adaptive pulse repetition frequency adjustment

    Science.gov (United States)

    Chen, Yijun; Zhang, Qun; Ma, Changzheng; Luo, Ying; Yeo, Tat Soon

    2014-01-01

    In multifunction phased array radar systems, different activities (e.g., tracking, searching, imaging, feature extraction, recognition, etc.) would need to be performed simultaneously. To relieve the conflict of the radar resource distribution, a micromotion feature extraction method using tracking pulses with adaptive pulse repetition frequencies (PRFs) is proposed in this paper. In this method, the idea of a varying PRF is utilized to solve the frequency-domain aliasing problem of the micro-Doppler signal. With appropriate atom set construction, the micromotion feature can be extracted and the image of the target can be obtained based on the Orthogonal Matching Pursuit algorithm. In our algorithm, the micromotion feature of a radar target is extracted from the tracking pulses and the quality of the constructed image is fed back into the radar system to adaptively adjust the PRF of the tracking pulses. Finally, simulation results illustrate the effectiveness of the proposed method.

  4. Weak Fault Feature Extraction of Rolling Bearings Based on an Improved Kurtogram.

    Science.gov (United States)

    Chen, Xianglong; Feng, Fuzhou; Zhang, Bingzhi

    2016-09-13

    Kurtograms have been verified to be an efficient tool in bearing fault detection and diagnosis because of their superiority in extracting transient features. However, the short-time Fourier Transform is insufficient in time-frequency analysis and kurtosis is deficient in detecting cyclic transients. Those factors weaken the performance of the original kurtogram in extracting weak fault features. Correlated Kurtosis (CK) is then designed, as a more effective solution, in detecting cyclic transients. Redundant Second Generation Wavelet Packet Transform (RSGWPT) is deemed to be effective in capturing more detailed local time-frequency description of the signal, and restricting the frequency aliasing components of the analysis results. The authors in this manuscript, combining the CK with the RSGWPT, propose an improved kurtogram to extract weak fault features from bearing vibration signals. The analysis of simulation signals and real application cases demonstrate that the proposed method is relatively more accurate and effective in extracting weak fault features.

  5. Weak Fault Feature Extraction of Rolling Bearings Based on an Improved Kurtogram

    Directory of Open Access Journals (Sweden)

    Xianglong Chen

    2016-09-01

    Full Text Available Kurtograms have been verified to be an efficient tool in bearing fault detection and diagnosis because of their superiority in extracting transient features. However, the short-time Fourier Transform is insufficient in time-frequency analysis and kurtosis is deficient in detecting cyclic transients. Those factors weaken the performance of the original kurtogram in extracting weak fault features. Correlated Kurtosis (CK is then designed, as a more effective solution, in detecting cyclic transients. Redundant Second Generation Wavelet Packet Transform (RSGWPT is deemed to be effective in capturing more detailed local time-frequency description of the signal, and restricting the frequency aliasing components of the analysis results. The authors in this manuscript, combining the CK with the RSGWPT, propose an improved kurtogram to extract weak fault features from bearing vibration signals. The analysis of simulation signals and real application cases demonstrate that the proposed method is relatively more accurate and effective in extracting weak fault features.

  6. A Local Asynchronous Distributed Privacy Preserving Feature Selection Algorithm for Large Peer-to-Peer Networks

    Data.gov (United States)

    National Aeronautics and Space Administration — In this paper we develop a local distributed privacy preserving algorithm for feature selection in a large peer-to-peer environment. Feature selection is often used...

  7. D Feature Point Extraction from LIDAR Data Using a Neural Network

    Science.gov (United States)

    Feng, Y.; Schlichting, A.; Brenner, C.

    2016-06-01

    Accurate positioning of vehicles plays an important role in autonomous driving. In our previous research on landmark-based positioning, poles were extracted both from reference data and online sensor data, which were then matched to improve the positioning accuracy of the vehicles. However, there are environments which contain only a limited number of poles. 3D feature points are one of the proper alternatives to be used as landmarks. They can be assumed to be present in the environment, independent of certain object classes. To match the LiDAR data online to another LiDAR derived reference dataset, the extraction of 3D feature points is an essential step. In this paper, we address the problem of 3D feature point extraction from LiDAR datasets. Instead of hand-crafting a 3D feature point extractor, we propose to train it using a neural network. In this approach, a set of candidates for the 3D feature points is firstly detected by the Shi-Tomasi corner detector on the range images of the LiDAR point cloud. Using a back propagation algorithm for the training, the artificial neural network is capable of predicting feature points from these corner candidates. The training considers not only the shape of each corner candidate on 2D range images, but also their 3D features such as the curvature value and surface normal value in z axis, which are calculated directly based on the LiDAR point cloud. Subsequently the extracted feature points on the 2D range images are retrieved in the 3D scene. The 3D feature points extracted by this approach are generally distinctive in the 3D space. Our test shows that the proposed method is capable of providing a sufficient number of repeatable 3D feature points for the matching task. The feature points extracted by this approach have great potential to be used as landmarks for a better localization of vehicles.

  8. DCT domain feature extraction scheme based on motor unit action potential of EMG signal for neuromuscular disease classification.

    Science.gov (United States)

    Doulah, Abul Barkat Mollah Sayeed Ud; Fattah, Shaikh Anowarul; Zhu, Wei-Ping; Ahmad, M Omair

    2014-01-01

    A feature extraction scheme based on discrete cosine transform (DCT) of electromyography (EMG) signals is proposed for the classification of normal event and a neuromuscular disease, namely the amyotrophic lateral sclerosis. Instead of employing DCT directly on EMG data, it is employed on the motor unit action potentials (MUAPs) extracted from the EMG signal via a template matching-based decomposition technique. Unlike conventional MUAP-based methods, only one MUAP with maximum dynamic range is selected for DCT-based feature extraction. Magnitude and frequency values of a few high-energy DCT coefficients corresponding to the selected MUAP are used as the desired feature which not only reduces computational burden, but also offers better feature quality with high within-class compactness and between-class separation. For the purpose of classification, the K-nearest neighbourhood classifier is employed. Extensive analysis is performed on clinical EMG database and it is found that the proposed method provides a very satisfactory performance in terms of specificity, sensitivity and overall classification accuracy.

  9. A Permutation Importance-Based Feature Selection Method for Short-Term Electricity Load Forecasting Using Random Forest

    Directory of Open Access Journals (Sweden)

    Nantian Huang

    2016-09-01

    Full Text Available The prediction accuracy of short-term load forecast (STLF depends on prediction model choice and feature selection result. In this paper, a novel random forest (RF-based feature selection method for STLF is proposed. First, 243 related features were extracted from historical load data and the time information of prediction points to form the original feature set. Subsequently, the original feature set was used to train an RF as the original model. After the training process, the prediction error of the original model on the test set was recorded and the permutation importance (PI value of each feature was obtained. Then, an improved sequential backward search method was used to select the optimal forecasting feature subset based on the PI value of each feature. Finally, the optimal forecasting feature subset was used to train a new RF model as the final prediction model. Experiments showed that the prediction accuracy of RF trained by the optimal forecasting feature subset was higher than that of the original model and comparative models based on support vector regression and artificial neural network.

  10. Automatic extraction of geometric lip features with application to multi-modal speaker identification

    OpenAIRE

    Arsic, I.; Vilagut Abad, R.; Thiran, J.

    2006-01-01

    In this paper we consider the problem of automatic extraction of the geometric lip features for the purposes of multi-modal speaker identification. The use of visual information from the mouth region can be of great importance for improving the speaker identification system performance in noisy conditions. We propose a novel method for automated lip features extraction that utilizes color space transformation and a fuzzy-based c-means clustering technique. Using the obtained visual cues close...

  11. Spatial and Spectral Nonparametric Linear Feature Extraction Method for Hyperspectral Image Classification

    Directory of Open Access Journals (Sweden)

    Jinn-Min Yang

    2016-11-01

    Full Text Available Feature extraction (FE or dimensionality reduction (DR plays quite an important role in the field of pattern recognition. Feature extraction aims to reduce the dimensionality of the high-dimensional dataset to enhance the classification accuracy and foster the classification speed, particularly when the training sample size is small, namely the small sample size (SSS problem. Remotely sensed hyperspectral images (HSIs are often with hundreds of measured features (bands which potentially provides more accurate and detailed information for classification, but it generally needs more samples to estimate parameters to achieve a satisfactory result. The cost of collecting ground-truth of remotely sensed hyperspectral scene can be considerably difficult and expensive. Therefore, FE techniques have been an important part for hyperspectral image classification. Unlike lots of feature extraction methods are based only on the spectral (band information of the training samples, some feature extraction methods integrating both spatial and spectral information of training samples show more effective results in recent years. Spatial contexture information has been proven to be useful to improve the HSI data representation and to increase classification accuracy. In this paper, we propose a spatial and spectral nonparametric linear feature extraction method for hyperspectral image classification. The spatial and spectral information is extracted for each training sample and used to design the within-class and between-class scatter matrices for constructing the feature extraction model. The experimental results on one benchmark hyperspectral image demonstrate that the proposed method obtains stable and satisfactory results than some existing spectral-based feature extraction.

  12. Synthesis of two-dimensional materials by selective extraction.

    Science.gov (United States)

    Naguib, Michael; Gogotsi, Yury

    2015-01-20

    CONSPECTUS: Two-dimensional (2D) materials have attracted much attention in the past decade. They offer high specific surface area, as well as electronic structure and properties that differ from their bulk counterparts due to the low dimensionality. Graphene is the best known and the most studied 2D material, but metal oxides and hydroxides (including clays), dichalcogenides, boron nitride (BN), and other materials that are one or several atoms thick are receiving increasing attention. They may deliver a combination of properties that cannot be provided by other materials. The most common synthesis approach in general is by reacting different elements or compounds to form a new compound. However, this approach does not necessarily work well for low-dimensional structures, since it favors formation of energetically preferred 3D (bulk) solids. Many 2D materials are produced by exfoliation of van der Waals solids, such as graphite or MoS2, breaking large particles into 2D layers. However, these approaches are not universal; for example, 2D transition metal carbides cannot be produced by any of them. An alternative but less studied way of material synthesis is the selective extraction process, which is based on the difference in reactivity and stability between the different components (elements or structural units) of the original material. It can be achieved using thermal, chemical, or electrochemical processes. Many 2D materials have been synthesized using selective extraction, such as graphene from SiC, transition metal oxides (TMO) from layered 3D salts, and transition metal carbides or carbonitrides (MXenes) from MAX phases. Selective extraction synthesis is critically important when the bonds between the building blocks of the material are too strong (e.g., in carbides) to be broken mechanically in order to form nanostructures. Unlike extractive metallurgy, where the extracted metal is the goal of the process, selective extraction of one or more elements from

  13. Robust Speech Recognition Using Temporal Pattern Feature Extracted From MTMLP Structure

    Directory of Open Access Journals (Sweden)

    Yasser Shekofteh

    2014-10-01

    Full Text Available Temporal Pattern feature of a speech signal could be either extracted from the time domain or via their front-end vectors. This feature includes long-term information of variations in the connected speech units. In this paper, the second approach is followed, i.e. the features which are the cases of temporal computations, consisting of Spectral-based (LFBE and Cepstrum-based (MFCC feature vectors, are considered. To extract these features, we use posterior probability-based output of the proposed MTMLP neural networks. The combination of the temporal patterns, which represents the long-term dynamics of the speech signal, together with some traditional features, composed of the MFCC and its first and second derivatives are evaluated in an ASR task. It is shown that the use of such a combined feature vector results in the increase of the phoneme recognition accuracy by more than 1 percent regarding the results of the baseline system, which does not benefit from the long-term temporal patterns. In addition, it is shown that the use of extracted features by the proposed method gives robust recognition under different noise conditions (by 13 percent and, therefore, the proposed method is a robust feature extraction method.

  14. Development of orodispersible films with selected Indonesian medicinal plant extracts

    NARCIS (Netherlands)

    Visser, Johanna; Eugresya, Gabriella; Hinrichs, Wouter; Tjandrawinata, Raymond; Avanti, Christina; Frijlink, H.W.; Woerdenbag, Herman

    2016-01-01

    This study focused on the incorporation into orodispersible films (ODFs) of the dried extracts of five selected Indonesian medicinal plants: Lagerstroemia speciosa (L.) Pers. (LS), Phyllanthus niruri L. (PN), Cinnamomum burmanii Blume (CB), Zingiber officinale Roscoe (ZO) and Phaleria macrocarpa (Sc

  15. A feature extraction method for the signal sorting of interleaved radar pulse serial

    Institute of Scientific and Technical Information of China (English)

    GUO Qiang; ZHANG Xingzhou; LI Zheng

    2007-01-01

    In this paper,a new feature extraction method for radar pulse sequences is presented based on structure function and empirical mode decomposition,In this method,2-D feature information was constituted by using radio frequency and time-of-arrival,which analyzed the feature of radar pulse sequences for the very first time by employing structure function and empirical mode decomposition.The experiment shows that the method can efficiently extract the frequency of a period-change radio frequency signal in a complex pulses environment and reveals a new feature for the signal sorting of interleaved radar pulse serial.This paper provides a novel way for extracting the new sorting feature of radar signals.

  16. A Method of SAR Target Recognition Based on Gabor Filter and Local Texture Feature Extraction

    Directory of Open Access Journals (Sweden)

    Wang Lu

    2015-12-01

    Full Text Available This paper presents a novel texture feature extraction method based on a Gabor filter and Three-Patch Local Binary Patterns (TPLBP for Synthetic Aperture Rader (SAR target recognition. First, SAR images are processed by a Gabor filter in different directions to enhance the significant features of the targets and their shadows. Then, the effective local texture features based on the Gabor filtered images are extracted by TPLBP. This not only overcomes the shortcoming of Local Binary Patterns (LBP, which cannot describe texture features for large scale neighborhoods, but also maintains the rotation invariant characteristic which alleviates the impact of the direction variations of SAR targets on recognition performance. Finally, we use an Extreme Learning Machine (ELM classifier and extract the texture features. The experimental results of MSTAR database demonstrate the effectiveness of the proposed method.

  17. NEW METHOD FOR WEAK FAULT FEATURE EXTRACTION BASED ON SECOND GENERATION WAVELET TRANSFORM AND ITS APPLICATION

    Institute of Scientific and Technical Information of China (English)

    Duan Chendong; He Zhengjia; Jiang Hongkai

    2004-01-01

    A new time-domain analysis method that uses second generation wavelet transform (SGWT) for weak fault feature extraction is proposed. To extract incipient fault feature, a biorthogonal wavelet with the characteristics of impact is constructed by using SGWT. Processing detail signal of SGWT with a sliding window devised on the basis of rotating operation cycle, and extracting modulus maximum from each window, fault features in time-domain are highlighted. To make further analysis on the reason of the fault, wavelet package transform based on SGWT is used to process vibration data again. Calculating the energy of each frequency-band, the energy distribution features of the signal are attained. Then taking account of the fault features and the energy distribution, the reason of the fault is worked out. An early impact-rub fault caused by axis misalignment and rotor imbalance is successfully detected by using this method in an oil refinery.

  18. Rolling bearing feature frequency extraction using extreme average envelope decomposition

    Science.gov (United States)

    Shi, Kunju; Liu, Shulin; Jiang, Chao; Zhang, Hongli

    2016-09-01

    The vibration signal contains a wealth of sensitive information which reflects the running status of the equipment. It is one of the most important steps for precise diagnosis to decompose the signal and extracts the effective information properly. The traditional classical adaptive signal decomposition method, such as EMD, exists the problems of mode mixing, low decomposition accuracy etc. Aiming at those problems, EAED(extreme average envelope decomposition) method is presented based on EMD. EAED method has three advantages. Firstly, it is completed through midpoint envelopment method rather than using maximum and minimum envelopment respectively as used in EMD. Therefore, the average variability of the signal can be described accurately. Secondly, in order to reduce the envelope errors during the signal decomposition, replacing two envelopes with one envelope strategy is presented. Thirdly, the similar triangle principle is utilized to calculate the time of extreme average points accurately. Thus, the influence of sampling frequency on the calculation results can be significantly reduced. Experimental results show that EAED could separate out single frequency components from a complex signal gradually. EAED could not only isolate three kinds of typical bearing fault characteristic of vibration frequency components but also has fewer decomposition layers. EAED replaces quadratic enveloping to an envelope which ensuring to isolate the fault characteristic frequency under the condition of less decomposition layers. Therefore, the precision of signal decomposition is improved.

  19. Aggregation of Electric Current Consumption Features to Extract Maintenance KPIs

    Science.gov (United States)

    Simon, Victor; Johansson, Carl-Anders; Galar, Diego

    2017-09-01

    All electric powered machines offer the possibility of extracting information and calculating Key Performance Indicators (KPIs) from the electric current signal. Depending on the time window, sampling frequency and type of analysis, different indicators from the micro to macro level can be calculated for such aspects as maintenance, production, energy consumption etc. On the micro-level, the indicators are generally used for condition monitoring and diagnostics and are normally based on a short time window and a high sampling frequency. The macro indicators are normally based on a longer time window with a slower sampling frequency and are used as indicators for overall performance, cost or consumption. The indicators can be calculated directly from the current signal but can also be based on a combination of information from the current signal and operational data like rpm, position etc. One or several of those indicators can be used for prediction and prognostics of a machine's future behavior. This paper uses this technique to calculate indicators for maintenance and energy optimization in electric powered machines and fleets of machines, especially machine tools.

  20. Suitable features selection for monitoring thermal condition of electrical equipment using infrared thermography

    Science.gov (United States)

    Huda, A. S. N.; Taib, S.

    2013-11-01

    Monitoring the thermal condition of electrical equipment is necessary for maintaining the reliability of electrical system. The degradation of electrical equipment can cause excessive overheating, which can lead to the eventual failure of the equipment. Additionally, failure of equipment requires a lot of maintenance cost, manpower and can also be catastrophic- causing injuries or even deaths. Therefore, the recognition processof equipment conditions as normal and defective is an essential step towards maintaining reliability and stability of the system. The study introduces infrared thermography based condition monitoring of electrical equipment. Manual analysis of thermal image for detecting defects and classifying the status of equipment take a lot of time, efforts and can also lead to incorrect diagnosis results. An intelligent system that can separate the equipment automatically could help to overcome these problems. This paper discusses an intelligent classification system for the conditions of equipment using neural networks. Three sets of features namely first order histogram based statistical, grey level co-occurrence matrix and component based intensity features are extracted by image analysis, which are used as input data for the neural networks. The multilayered perceptron networks are trained using four different training algorithms namely Resilient back propagation, Bayesian Regulazation, Levenberg-Marquardt and Scale conjugate gradient. The experimental results show that the component based intensity features perform better compared to other two sets of features. Finally, after selecting the best features, multilayered perceptron network trained using Levenberg-Marquardt algorithm achieved the best results to classify the conditions of electrical equipment.