Salient Region Detection via Feature Combination and Discriminative Classifier

Directory of Open Access Journals (Sweden)

Deming Kong

2015-01-01

Full Text Available We introduce a novel approach to detect salient regions of an image via feature combination and discriminative classifier. Our method, which is based on hierarchical image abstraction, uses the logistic regression approach to map the regional feature vector to a saliency score. Four saliency cues are used in our approach, including color contrast in a global context, center-boundary priors, spatially compact color distribution, and objectness, which is as an atomic feature of segmented region in the image. By mapping a four-dimensional regional feature to fifteen-dimensional feature vector, we can linearly separate the salient regions from the clustered background by finding an optimal linear combination of feature coefficients in the fifteen-dimensional feature space and finally fuse the saliency maps across multiple levels. Furthermore, we introduce the weighted salient image center into our saliency analysis task. Extensive experiments on two large benchmark datasets show that the proposed approach achieves the best performance over several state-of-the-art approaches.

Visual Tracking via Feature Tensor Multimanifold Discriminate Analysis

Directory of Open Access Journals (Sweden)

Ting-quan Deng

2014-01-01

Full Text Available In the visual tracking scenarios, if there are multiple objects, due to the interference of similar objects, tracking may fail in the progress of occlusion to separation. To address this problem, this paper proposed a visual tracking algorithm with discrimination through multimanifold learning. Color-gradient-based feature tensor was used to describe object appearance for accommodation of partial occlusion. A prior multimanifold tensor dataset is established through the template matching tracking algorithm. For the purpose of discrimination, tensor distance was defined to determine the intramanifold and intermanifold neighborhood relationship in multimanifold space. Then multimanifold discriminate analysis was employed to construct multilinear projection matrices of submanifolds. Finally, object states were obtained by combining with sequence inference. Meanwhile, the multimanifold dataset and manifold learning embedded projection should be updated online. Experiments were conducted on two real visual surveillance sequences to evaluate the proposed algorithm with three state-of-the-art tracking methods qualitatively and quantitatively. Experimental results show that the proposed algorithm can achieve effective and robust effect in multi-similar-object mutual occlusion scenarios.

General tensor discriminant analysis and gabor features for gait recognition.

Science.gov (United States)

Tao, Dacheng; Li, Xuelong; Wu, Xindong; Maybank, Stephen J

2007-10-01

The traditional image representations are not suited to conventional classification methods, such as the linear discriminant analysis (LDA), because of the under sample problem (USP): the dimensionality of the feature space is much higher than the number of training samples. Motivated by the successes of the two dimensional LDA (2DLDA) for face recognition, we develop a general tensor discriminant analysis (GTDA) as a preprocessing step for LDA. The benefits of GTDA compared with existing preprocessing methods, e.g., principal component analysis (PCA) and 2DLDA, include 1) the USP is reduced in subsequent classification by, for example, LDA; 2) the discriminative information in the training tensors is preserved; and 3) GTDA provides stable recognition rates because the alternating projection optimization algorithm to obtain a solution of GTDA converges, while that of 2DLDA does not. We use human gait recognition to validate the proposed GTDA. The averaged gait images are utilized for gait representation. Given the popularity of Gabor function based image decompositions for image understanding and object recognition, we develop three different Gabor function based image representations: 1) the GaborD representation is the sum of Gabor filter responses over directions, 2) GaborS is the sum of Gabor filter responses over scales, and 3) GaborSD is the sum of Gabor filter responses over scales and directions. The GaborD, GaborS and GaborSD representations are applied to the problem of recognizing people from their averaged gait images.A large number of experiments were carried out to evaluate the effectiveness (recognition rate) of gait recognition based on first obtaining a Gabor, GaborD, GaborS or GaborSD image representation, then using GDTA to extract features and finally using LDA for classification. The proposed methods achieved good performance for gait recognition based on image sequences from the USF HumanID Database. Experimental comparisons are made with nine

Facial Affect Recognition Using Regularized Discriminant Analysis-Based Algorithms

Directory of Open Access Journals (Sweden)

Cheng-Yuan Shih

2010-01-01

Full Text Available This paper presents a novel and effective method for facial expression recognition including happiness, disgust, fear, anger, sadness, surprise, and neutral state. The proposed method utilizes a regularized discriminant analysis-based boosting algorithm (RDAB with effective Gabor features to recognize the facial expressions. Entropy criterion is applied to select the effective Gabor feature which is a subset of informative and nonredundant Gabor features. The proposed RDAB algorithm uses RDA as a learner in the boosting algorithm. The RDA combines strengths of linear discriminant analysis (LDA and quadratic discriminant analysis (QDA. It solves the small sample size and ill-posed problems suffered from QDA and LDA through a regularization technique. Additionally, this study uses the particle swarm optimization (PSO algorithm to estimate optimal parameters in RDA. Experiment results demonstrate that our approach can accurately and robustly recognize facial expressions.

Sub-pattern based multi-manifold discriminant analysis for face recognition

Science.gov (United States)

Dai, Jiangyan; Guo, Changlu; Zhou, Wei; Shi, Yanjiao; Cong, Lin; Yi, Yugen

2018-04-01

In this paper, we present a Sub-pattern based Multi-manifold Discriminant Analysis (SpMMDA) algorithm for face recognition. Unlike existing Multi-manifold Discriminant Analysis (MMDA) approach which is based on holistic information of face image for recognition, SpMMDA operates on sub-images partitioned from the original face image and then extracts the discriminative local feature from the sub-images separately. Moreover, the structure information of different sub-images from the same face image is considered in the proposed method with the aim of further improve the recognition performance. Extensive experiments on three standard face databases (Extended YaleB, CMU PIE and AR) demonstrate that the proposed method is effective and outperforms some other sub-pattern based face recognition methods.

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.

Machinery running state identification based on discriminant semi-supervised local tangent space alignment for feature fusion and extraction

International Nuclear Information System (INIS)

Su, Zuqiang; Xiao, Hong; Zhang, Yi; Tang, Baoping; Jiang, Yonghua

2017-01-01

Extraction of sensitive features is a challenging but key task in data-driven machinery running state identification. Aimed at solving this problem, a method for machinery running state identification that applies discriminant semi-supervised local tangent space alignment (DSS-LTSA) for feature fusion and extraction is proposed. Firstly, in order to extract more distinct features, the vibration signals are decomposed by wavelet packet decomposition WPD, and a mixed-domain feature set consisted of statistical features, autoregressive (AR) model coefficients, instantaneous amplitude Shannon entropy and WPD energy spectrum is extracted to comprehensively characterize the properties of machinery running state(s). Then, the mixed-dimension feature set is inputted into DSS-LTSA for feature fusion and extraction to eliminate redundant information and interference noise. The proposed DSS-LTSA can extract intrinsic structure information of both labeled and unlabeled state samples, and as a result the over-fitting problem of supervised manifold learning and blindness problem of unsupervised manifold learning are overcome. Simultaneously, class discrimination information is integrated within the dimension reduction process in a semi-supervised manner to improve sensitivity of the extracted fusion features. Lastly, the extracted fusion features are inputted into a pattern recognition algorithm to achieve the running state identification. The effectiveness of the proposed method is verified by a running state identification case in a gearbox, and the results confirm the improved accuracy of the running state identification. (paper)

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.

EEG feature selection method based on decision tree.

Science.gov (United States)

Duan, Lijuan; Ge, Hui; Ma, Wei; Miao, Jun

2015-01-01

This paper aims to solve automated feature selection problem in brain computer interface (BCI). In order to automate feature selection process, we proposed a novel EEG feature selection method based on decision tree (DT). During the electroencephalogram (EEG) signal processing, a feature extraction method based on principle component analysis (PCA) was used, and the selection process based on decision tree was performed by searching the feature space and automatically selecting optimal features. Considering that EEG signals are a series of non-linear signals, a generalized linear classifier named support vector machine (SVM) was chosen. In order to test the validity of the proposed method, we applied the EEG feature selection method based on decision tree to BCI Competition II datasets Ia, and the experiment showed encouraging results.

Infrared video based gas leak detection method using modified FAST features

Science.gov (United States)

Wang, Min; Hong, Hanyu; Huang, Likun

2018-03-01

In order to detect the invisible leaking gas that is usually dangerous and easily leads to fire or explosion in time, many new technologies have arisen in the recent years, among which the infrared video based gas leak detection is widely recognized as a viable tool. However, all the moving regions of a video frame can be detected as leaking gas regions by the existing infrared video based gas leak detection methods, without discriminating the property of each detected region, e.g., a walking person in a video frame may be also detected as gas by the current gas leak detection methods.To solve this problem, we propose a novel infrared video based gas leak detection method in this paper, which is able to effectively suppress strong motion disturbances.Firstly, the Gaussian mixture model(GMM) is used to establish the background model.Then due to the observation that the shapes of gas regions are different from most rigid moving objects, we modify the Features From Accelerated Segment Test (FAST) algorithm and use the modified FAST (mFAST) features to describe each connected component. In view of the fact that the statistical property of the mFAST features extracted from gas regions is different from that of other motion regions, we propose the Pixel-Per-Points (PPP) condition to further select candidate connected components.Experimental results show that the algorithm is able to effectively suppress most strong motion disturbances and achieve real-time leaking gas detection.

Discrimination Features of Chromatic Figures in Various Background Characteristics

Directory of Open Access Journals (Sweden)

Y A Chudina

2013-12-01

Full Text Available Visual recognition features of images with different figure-ground segregation have been considered in the article. The research was carried out within the framework of Sokolov and Izmaylov’s spherical model and was based on the construction of color objects discrimination models depending on the changes of background characteristics. The research has revealed the specific influence of the background on figure discrimination. The derived models reflect the mechanisms of the all-in-one perception of the visual space.

FEATURE SELECTION METHODS BASED ON MUTUAL INFORMATION FOR CLASSIFYING HETEROGENEOUS FEATURES

Directory of Open Access Journals (Sweden)

Ratri Enggar Pawening

2016-06-01

Full Text Available Datasets with heterogeneous features can affect feature selection results that are not appropriate because it is difficult to evaluate heterogeneous features concurrently. Feature transformation (FT is another way to handle heterogeneous features subset selection. The results of transformation from non-numerical into numerical features may produce redundancy to the original numerical features. In this paper, we propose a method to select feature subset based on mutual information (MI for classifying heterogeneous features. We use unsupervised feature transformation (UFT methods and joint mutual information maximation (JMIM methods. UFT methods is used to transform non-numerical features into numerical features. JMIM methods is used to select feature subset with a consideration of the class label. The transformed and the original features are combined entirely, then determine features subset by using JMIM methods, and classify them using support vector machine (SVM algorithm. The classification accuracy are measured for any number of selected feature subset and compared between UFT-JMIM methods and Dummy-JMIM methods. The average classification accuracy for all experiments in this study that can be achieved by UFT-JMIM methods is about 84.47% and Dummy-JMIM methods is about 84.24%. This result shows that UFT-JMIM methods can minimize information loss between transformed and original features, and select feature subset to avoid redundant and irrelevant features.

Discriminant forest classification method and system

Science.gov (United States)

Chen, Barry Y.; Hanley, William G.; Lemmond, Tracy D.; Hiller, Lawrence J.; Knapp, David A.; Mugge, Marshall J.

2012-11-06

A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.

[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.

L1-norm kernel discriminant analysis via Bayes error bound optimization for robust feature extraction.

Science.gov (United States)

Zheng, Wenming; Lin, Zhouchen; Wang, Haixian

2014-04-01

A novel discriminant analysis criterion is derived in this paper under the theoretical framework of Bayes optimality. In contrast to the conventional Fisher's discriminant criterion, the major novelty of the proposed one is the use of L1 norm rather than L2 norm, which makes it less sensitive to the outliers. With the L1-norm discriminant criterion, we propose a new linear discriminant analysis (L1-LDA) method for linear feature extraction problem. To solve the L1-LDA optimization problem, we propose an efficient iterative algorithm, in which a novel surrogate convex function is introduced such that the optimization problem in each iteration is to simply solve a convex programming problem and a close-form solution is guaranteed to this problem. Moreover, we also generalize the L1-LDA method to deal with the nonlinear robust feature extraction problems via the use of kernel trick, and hereafter proposed the L1-norm kernel discriminant analysis (L1-KDA) method. Extensive experiments on simulated and real data sets are conducted to evaluate the effectiveness of the proposed method in comparing with the state-of-the-art methods.

Discriminating Induced-Microearthquakes Using New Seismic Features

Science.gov (United States)

Mousavi, S. M.; Horton, S.

2016-12-01

We studied characteristics of induced-microearthquakes on the basis of the waveforms recorded on a limited number of surface receivers using machine-learning techniques. Forty features in the time, frequency, and time-frequency domains were measured on each waveform, and several techniques such as correlation-based feature selection, Artificial Neural Networks (ANNs), Logistic Regression (LR) and X-mean were used as research tools to explore the relationship between these seismic features and source parameters. The results show that spectral features have the highest correlation to source depth. Two new measurements developed as seismic features for this study, spectral centroids and 2D cross-correlations in the time-frequency domain, performed better than the common seismic measurements. These features can be used by machine learning techniques for efficient automatic classification of low energy signals recorded at one or more seismic stations. We applied the technique to 440 microearthquakes-1.7Reference: Mousavi, S.M., S.P. Horton, C. A. Langston, B. Samei, (2016) Seismic features and automatic discrimination of deep and shallow induced-microearthquakes using neural network and logistic regression, Geophys. J. Int. doi: 10.1093/gji/ggw258.

Demands on attention and the role of response priming in visual discrimination of feature conjunctions.

Science.gov (United States)

Fournier, Lisa R; Herbert, Rhonda J; Farris, Carrie

2004-10-01

This study examined how response mapping of features within single- and multiple-feature targets affects decision-based processing and attentional capacity demands. Observers judged the presence or absence of 1 or 2 target features within an object either presented alone or with distractors. Judging the presence of 2 features relative to the less discriminable of these features alone was faster (conjunction benefits) when the task-relevant features differed in discriminability and were consistently mapped to responses. Conjunction benefits were attributed to asynchronous decision priming across attended, task-relevant dimensions. A failure to find conjunction benefits for disjunctive conjunctions was attributed to increased memory demands and variable feature-response mapping for 2- versus single-feature targets. Further, attentional demands were similar between single- and 2-feature targets when response mapping, memory demands, and discriminability of the task-relevant features were equated between targets. Implications of the findings for recent attention models are discussed. (c) 2004 APA, all rights reserved

Enhancing the discrimination accuracy between metastases, gliomas and meningiomas on brain MRI by volumetric textural features and ensemble pattern recognition methods.

Science.gov (United States)

Georgiadis, Pantelis; Cavouras, Dionisis; Kalatzis, Ioannis; Glotsos, Dimitris; Athanasiadis, Emmanouil; Kostopoulos, Spiros; Sifaki, Koralia; Malamas, Menelaos; Nikiforidis, George; Solomou, Ekaterini

2009-01-01

Three-dimensional (3D) texture analysis of volumetric brain magnetic resonance (MR) images has been identified as an important indicator for discriminating among different brain pathologies. The purpose of this study was to evaluate the efficiency of 3D textural features using a pattern recognition system in the task of discriminating benign, malignant and metastatic brain tissues on T1 postcontrast MR imaging (MRI) series. The dataset consisted of 67 brain MRI series obtained from patients with verified and untreated intracranial tumors. The pattern recognition system was designed as an ensemble classification scheme employing a support vector machine classifier, specially modified in order to integrate the least squares features transformation logic in its kernel function. The latter, in conjunction with using 3D textural features, enabled boosting up the performance of the system in discriminating metastatic, malignant and benign brain tumors with 77.14%, 89.19% and 93.33% accuracy, respectively. The method was evaluated using an external cross-validation process; thus, results might be considered indicative of the generalization performance of the system to "unseen" cases. The proposed system might be used as an assisting tool for brain tumor characterization on volumetric MRI series.

Optimal Threshold Determination for Discriminating Driving Anger Intensity Based on EEG Wavelet Features and ROC Curve Analysis

Directory of Open Access Journals (Sweden)

Ping Wan

2016-08-01

Full Text Available Driving anger, called “road rage”, has become increasingly common nowadays, affecting road safety. A few researches focused on how to identify driving anger, however, there is still a gap in driving anger grading, especially in real traffic environment, which is beneficial to take corresponding intervening measures according to different anger intensity. This study proposes a method for discriminating driving anger states with different intensity based on Electroencephalogram (EEG spectral features. First, thirty drivers were recruited to conduct on-road experiments on a busy route in Wuhan, China where anger could be inducted by various road events, e.g., vehicles weaving/cutting in line, jaywalking/cyclist crossing, traffic congestion and waiting red light if they want to complete the experiments ahead of basic time for extra paid. Subsequently, significance analysis was used to select relative energy spectrum of β band (β% and relative energy spectrum of θ band (θ% for discriminating the different driving anger states. Finally, according to receiver operating characteristic (ROC curve analysis, the optimal thresholds (best cut-off points of β% and θ% for identifying none anger state (i.e., neutral were determined to be 0.2183 ≤ θ% < 1, 0 < β% < 0.2586; low anger state is 0.1539 ≤ θ% < 0.2183, 0.2586 ≤ β% < 0.3269; moderate anger state is 0.1216 ≤ θ% < 0.1539, 0.3269 ≤ β% < 0.3674; high anger state is 0 < θ% < 0.1216, 0.3674 ≤ β% < 1. Moreover, the discrimination performances of verification indicate that, the overall accuracy (Acc of the optimal thresholds of β% for discriminating the four driving anger states is 80.21%, while 75.20% for that of θ%. The results can provide theoretical foundation for developing driving anger detection or warning devices based on the relevant optimal thresholds.

SAR Target Recognition via Supervised Discriminative Dictionary Learning and Sparse Representation of the SAR-HOG Feature

Directory of Open Access Journals (Sweden)

Shengli Song

2016-08-01

Full Text Available Automatic target recognition (ATR in synthetic aperture radar (SAR images plays an important role in both national defense and civil applications. Although many methods have been proposed, SAR ATR is still very challenging due to the complex application environment. Feature extraction and classification are key points in SAR ATR. In this paper, we first design a novel feature, which is a histogram of oriented gradients (HOG-like feature for SAR ATR (called SAR-HOG. Then, we propose a supervised discriminative dictionary learning (SDDL method to learn a discriminative dictionary for SAR ATR and propose a strategy to simplify the optimization problem. Finally, we propose a SAR ATR classifier based on SDDL and sparse representation (called SDDLSR, in which both the reconstruction error and the classification error are considered. Extensive experiments are performed on the MSTAR database under standard operating conditions and extended operating conditions. The experimental results show that SAR-HOG can reliably capture the structures of targets in SAR images, and SDDL can further capture subtle differences among the different classes. By virtue of the SAR-HOG feature and SDDLSR, the proposed method achieves the state-of-the-art performance on MSTAR database. Especially for the extended operating conditions (EOC scenario “Training 17 ∘ —Testing 45 ∘ ”, the proposed method improves remarkably with respect to the previous works.

Boosting Discriminant Learners for Gait Recognition Using MPCA Features

Directory of Open Access Journals (Sweden)

Haiping Lu

2009-01-01

Full Text Available This paper proposes a boosted linear discriminant analysis (LDA solution on features extracted by the multilinear principal component analysis (MPCA to enhance gait recognition performance. Three-dimensional gait objects are projected in the MPCA space first to obtain low-dimensional tensorial features. Then, lower-dimensional vectorial features are obtained through discriminative feature selection. These feature vectors are then fed into an LDA-style booster, where several regularized and weakened LDA learners work together to produce a strong learner through a novel feature weighting and sampling process. The LDA learner employs a simple nearest-neighbor classifier with a weighted angle distance measure for classification. The experimental results on the NIST/USF “Gait Challenge” data-sets show that the proposed solution has successfully improved the gait recognition performance and outperformed several state-of-the-art gait recognition algorithms.

A PCA aided cross-covariance scheme for discriminative feature extraction from EEG signals.

Science.gov (United States)

Zarei, Roozbeh; He, Jing; Siuly, Siuly; Zhang, Yanchun

2017-07-01

Feature extraction of EEG signals plays a significant role in Brain-computer interface (BCI) as it can significantly affect the performance and the computational time of the system. The main aim of the current work is to introduce an innovative algorithm for acquiring reliable discriminating features from EEG signals to improve classification performances and to reduce the time complexity. This study develops a robust feature extraction method combining the principal component analysis (PCA) and the cross-covariance technique (CCOV) for the extraction of discriminatory information from the mental states based on EEG signals in BCI applications. We apply the correlation based variable selection method with the best first search on the extracted features to identify the best feature set for characterizing the distribution of mental state signals. To verify the robustness of the proposed feature extraction method, three machine learning techniques: multilayer perceptron neural networks (MLP), least square support vector machine (LS-SVM), and logistic regression (LR) are employed on the obtained features. The proposed methods are evaluated on two publicly available datasets. Furthermore, we evaluate the performance of the proposed methods by comparing it with some recently reported algorithms. The experimental results show that all three classifiers achieve high performance (above 99% overall classification accuracy) for the proposed feature set. Among these classifiers, the MLP and LS-SVM methods yield the best performance for the obtained feature. The average sensitivity, specificity and classification accuracy for these two classifiers are same, which are 99.32%, 100%, and 99.66%, respectively for the BCI competition dataset IVa and 100%, 100%, and 100%, for the BCI competition dataset IVb. The results also indicate the proposed methods outperform the most recently reported methods by at least 0.25% average accuracy improvement in dataset IVa. The execution time

Use of the discriminant Fourier-derived cepstrum with feature-level post-processing for surface electromyographic signal classification

International Nuclear Information System (INIS)

Chen, Xinpu; Zhu, Xiangyang; Zhang, Dingguo

2009-01-01

Myoelectrical pattern classification is a crucial part in multi-functional prosthesis control. This paper investigates a discriminant Fourier-derived cepstrum (DFC) and feature-level post-processing (FLPP) to discriminate hand and wrist motions using the surface electromyographic signal. The Fourier-derived cepstrum takes advantage of the Fourier magnitude or sub-band power energy of signals directly and provides flexible use of spectral information changing with different motions. Appropriate cepstral coefficients are selected by a proposed separability criterion to construct DFC features. For the post-processing, FLPP which combines features from several analysis windows is used to improve the feature performance further. In this work, two classifiers (a linear discriminant classifier and quadratic discriminant classifier) without hyper-parameter optimization are employed to simplify the training procedure and avoid the possible bias of feature evaluation. Experimental results of the 11-motion problem show that the proposed DFC feature outperforms traditional features such as time-domain statistics and autoregressive-derived cepstrum in terms of the classification accuracy, and it is a promising method for the multi-functionality and high-accuracy control of myoelectric prostheses

Assay based on electrical impedance spectroscopy to discriminate between normal and cancerous mammalian cells

Science.gov (United States)

Giana, Fabián Eduardo; Bonetto, Fabián José; Bellotti, Mariela Inés

2018-03-01

In this work we present an assay to discriminate between normal and cancerous cells. The method is based on the measurement of electrical impedance spectra of in vitro cell cultures. We developed a protocol consisting on four consecutive measurement phases, each of them designed to obtain different information about the cell cultures. Through the analysis of the measured data, 26 characteristic features were obtained for both cell types. From the complete set of features, we selected the most relevant in terms of their discriminant capacity by means of conventional statistical tests. A linear discriminant analysis was then carried out on the selected features, allowing the classification of the samples in normal or cancerous with 4.5% of false positives and no false negatives.

Time-Contrastive Learning Based DNN Bottleneck Features for Text-Dependent Speaker Verification

DEFF Research Database (Denmark)

Sarkar, Achintya Kumar; Tan, Zheng-Hua

2017-01-01

In this paper, we present a time-contrastive learning (TCL) based bottleneck (BN) feature extraction method for speech signals with an application to text-dependent (TD) speaker verification (SV). It is well-known that speech signals exhibit quasi-stationary behavior in and only in a short interval......, and the TCL method aims to exploit this temporal structure. More specifically, it trains deep neural networks (DNNs) to discriminate temporal events obtained by uniformly segmenting speech signals, in contrast to existing DNN based BN feature extraction methods that train DNNs using labeled data...... to discriminate speakers or pass-phrases or phones or a combination of them. In the context of speaker verification, speech data of fixed pass-phrases are used for TCL-BN training, while the pass-phrases used for TCL-BN training are excluded from being used for SV, so that the learned features can be considered...

Clustering based gene expression feature selection method: A computational approach to enrich the classifier efficiency of differentially expressed genes

KAUST Repository

Abusamra, Heba

2016-07-20

The native nature of high dimension low sample size of gene expression data make the classification task more challenging. Therefore, feature (gene) selection become an apparent need. Selecting a meaningful and relevant genes for classifier not only decrease the computational time and cost, but also improve the classification performance. Among different approaches of feature selection methods, however most of them suffer from several problems such as lack of robustness, validation issues etc. Here, we present a new feature selection technique that takes advantage of clustering both samples and genes. Materials and methods We used leukemia gene expression dataset [1]. The effectiveness of the selected features were evaluated by four different classification methods; support vector machines, k-nearest neighbor, random forest, and linear discriminate analysis. The method evaluate the importance and relevance of each gene cluster by summing the expression level for each gene belongs to this cluster. The gene cluster consider important, if it satisfies conditions depend on thresholds and percentage otherwise eliminated. Results Initial analysis identified 7120 differentially expressed genes of leukemia (Fig. 15a), after applying our feature selection methodology we end up with specific 1117 genes discriminating two classes of leukemia (Fig. 15b). Further applying the same method with more stringent higher positive and lower negative threshold condition, number reduced to 58 genes have be tested to evaluate the effectiveness of the method (Fig. 15c). The results of the four classification methods are summarized in Table 11. Conclusions The feature selection method gave good results with minimum classification error. Our heat-map result shows distinct pattern of refines genes discriminating between two classes of leukemia.

Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning

Directory of Open Access Journals (Sweden)

Zilong Zhou

2018-01-01

Full Text Available The automatic discrimination of rock fracture and blast events is complex and challenging due to the similar waveform characteristics. To solve this problem, a new method based on the signal complexity analysis and machine learning has been proposed in this paper. First, the permutation entropy values of signals at different scale factors are calculated to reflect complexity of signals and constructed into a feature vector set. Secondly, based on the feature vector set, back-propagation neural network (BPNN as a means of machine learning is applied to establish a discriminator for rock fracture and blast events. Then to evaluate the classification performances of the new method, the classifying accuracies of support vector machine (SVM, naive Bayes classifier, and the new method are compared, and the receiver operating characteristic (ROC curves are also analyzed. The results show the new method obtains the best classification performances. In addition, the influence of different scale factor q and number of training samples n on discrimination results is discussed. It is found that the classifying accuracy of the new method reaches the highest value when q = 8–15 or 8–20 and n=140.

Speech feature discrimination in deaf children following cochlear implantation

Science.gov (United States)

Bergeson, Tonya R.; Pisoni, David B.; Kirk, Karen Iler

2002-05-01

Speech feature discrimination is a fundamental perceptual skill that is often assumed to underlie word recognition and sentence comprehension performance. To investigate the development of speech feature discrimination in deaf children with cochlear implants, we conducted a retrospective analysis of results from the Minimal Pairs Test (Robbins et al., 1988) selected from patients enrolled in a longitudinal study of speech perception and language development. The MP test uses a 2AFC procedure in which children hear a word and select one of two pictures (bat-pat). All 43 children were prelingually deafened, received a cochlear implant before 6 years of age or between ages 6 and 9, and used either oral or total communication. Children were tested once every 6 months to 1 year for 7 years; not all children were tested at each interval. By 2 years postimplant, the majority of these children achieved near-ceiling levels of discrimination performance for vowel height, vowel place, and consonant manner. Most of the children also achieved plateaus but did not reach ceiling performance for consonant place and voicing. The relationship between speech feature discrimination, spoken word recognition, and sentence comprehension will be discussed. [Work supported by NIH/NIDCD Research Grant No. R01DC00064 and NIH/NIDCD Training Grant No. T32DC00012.

Discrimination of Rice with Different Pretreatment Methods by Using a Voltammetric Electronic Tongue

Directory of Open Access Journals (Sweden)

Li Wang

2015-07-01

Full Text Available In this study, an application of a voltammetric electronic tongue for discrimination and prediction of different varieties of rice was investigated. Different pretreatment methods were selected, which were subsequently used for the discrimination of different varieties of rice and prediction of unknown rice samples. To this aim, a voltammetric array of sensors based on metallic electrodes was used as the sensing part. The different samples were analyzed by cyclic voltammetry with two sample-pretreatment methods. Discriminant Factorial Analysis was used to visualize the different categories of rice samples; however, radial basis function (RBF artificial neural network with leave-one-out cross-validation method was employed for prediction modeling. The collected signal data were first compressed employing fast Fourier transform (FFT and then significant features were extracted from the voltammetric signals. The experimental results indicated that the sample solutions obtained by the non-crushed pretreatment method could efficiently meet the effect of discrimination and recognition. The satisfactory prediction results of voltammetric electronic tongue based on RBF artificial neural network were obtained with less than five-fold dilution of the sample solution. The main objective of this study was to develop primary research on the application of an electronic tongue system for the discrimination and prediction of solid foods and provide an objective assessment tool for the food industry.

Accurate palm vein recognition based on wavelet scattering and spectral regression kernel discriminant analysis

Science.gov (United States)

Elnasir, Selma; Shamsuddin, Siti Mariyam; Farokhi, Sajad

2015-01-01

Palm vein recognition (PVR) is a promising new biometric that has been applied successfully as a method of access control by many organizations, which has even further potential in the field of forensics. The palm vein pattern has highly discriminative features that are difficult to forge because of its subcutaneous position in the palm. Despite considerable progress and a few practical issues, providing accurate palm vein readings has remained an unsolved issue in biometrics. We propose a robust and more accurate PVR method based on the combination of wavelet scattering (WS) with spectral regression kernel discriminant analysis (SRKDA). As the dimension of WS generated features is quite large, SRKDA is required to reduce the extracted features to enhance the discrimination. The results based on two public databases-PolyU Hyper Spectral Palmprint public database and PolyU Multi Spectral Palmprint-show the high performance of the proposed scheme in comparison with state-of-the-art methods. The proposed approach scored a 99.44% identification rate and a 99.90% verification rate [equal error rate (EER)=0.1%] for the hyperspectral database and a 99.97% identification rate and a 99.98% verification rate (EER=0.019%) for the multispectral database.

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.

Conversion Discriminative Analysis on Mild Cognitive Impairment Using Multiple Cortical Features from MR Images

Directory of Open Access Journals (Sweden)

Shengwen Guo

2017-05-01

Full Text Available Neuroimaging measurements derived from magnetic resonance imaging provide important information required for detecting changes related to the progression of mild cognitive impairment (MCI. Cortical features and changes play a crucial role in revealing unique anatomical patterns of brain regions, and further differentiate MCI patients from normal states. Four cortical features, namely, gray matter volume, cortical thickness, surface area, and mean curvature, were explored for discriminative analysis among three groups including the stable MCI (sMCI, the converted MCI (cMCI, and the normal control (NC groups. In this study, 158 subjects (72 NC, 46 sMCI, and 40 cMCI were selected from the Alzheimer's Disease Neuroimaging Initiative. A sparse-constrained regression model based on the l2-1-norm was introduced to reduce the feature dimensionality and retrieve essential features for the discrimination of the three groups by using a support vector machine (SVM. An optimized strategy of feature addition based on the weight of each feature was adopted for the SVM classifier in order to achieve the best classification performance. The baseline cortical features combined with the longitudinal measurements for 2 years of follow-up data yielded prominent classification results. In particular, the cortical thickness produced a classification with 98.84% accuracy, 97.5% sensitivity, and 100% specificity for the sMCI–cMCI comparison; 92.37% accuracy, 84.78% sensitivity, and 97.22% specificity for the cMCI–NC comparison; and 93.75% accuracy, 92.5% sensitivity, and 94.44% specificity for the sMCI–NC comparison. The best performances obtained by the SVM classifier using the essential features were 5–40% more than those using all of the retained features. The feasibility of the cortical features for the recognition of anatomical patterns was certified; thus, the proposed method has the potential to improve the clinical diagnosis of sub-types of MCI and

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.

Improved neutron-gamma discrimination for a 3He neutron detector using subspace learning methods

Science.gov (United States)

Wang, C. L.; Funk, L. L.; Riedel, R. A.; Berry, K. D.

2017-05-01

3He gas based neutron Linear-Position-Sensitive Detectors (LPSDs) have been used for many neutron scattering instruments. Traditional Pulse-height Analysis (PHA) for Neutron-Gamma Discrimination (NGD) resulted in the neutron-gamma efficiency ratio (NGD ratio) on the order of 105-106. The NGD ratios of 3He detectors need to be improved for even better scientific results from neutron scattering. Digital Signal Processing (DSP) analyses of waveforms were proposed for obtaining better NGD ratios, based on features extracted from rise-time, pulse amplitude, charge integration, a simplified Wiener filter, and the cross-correlation between individual and template waveforms of neutron and gamma events. Fisher Linear Discriminant Analysis (FLDA) and three Multivariate Analyses (MVAs) of the features were performed. The NGD ratios are improved by about 102-103 times compared with the traditional PHA method. Our results indicate the NGD capabilities of 3He tube detectors can be significantly improved with subspace-learning based methods, which may result in a reduced data-collection time and better data quality for further data reduction.

[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.

Discriminative illumination: per-pixel classification of raw materials based on optimal projections of spectral BRDF.

Science.gov (United States)

Liu, Chao; Gu, Jinwei

2014-01-01

Classifying raw, unpainted materials--metal, plastic, ceramic, fabric, and so on--is an important yet challenging task for computer vision. Previous works measure subsets of surface spectral reflectance as features for classification. However, acquiring the full spectral reflectance is time consuming and error-prone. In this paper, we propose to use coded illumination to directly measure discriminative features for material classification. Optimal illumination patterns--which we call "discriminative illumination"--are learned from training samples, after projecting to which the spectral reflectance of different materials are maximally separated. This projection is automatically realized by the integration of incident light for surface reflection. While a single discriminative illumination is capable of linear, two-class classification, we show that multiple discriminative illuminations can be used for nonlinear and multiclass classification. We also show theoretically that the proposed method has higher signal-to-noise ratio than previous methods due to light multiplexing. Finally, we construct an LED-based multispectral dome and use the discriminative illumination method for classifying a variety of raw materials, including metal (aluminum, alloy, steel, stainless steel, brass, and copper), plastic, ceramic, fabric, and wood. Experimental results demonstrate its effectiveness.

Detection-Discrimination Method for Multiple Repeater False Targets Based on Radar Polarization Echoes

Directory of Open Access Journals (Sweden)

Z. W. ZONG

2014-04-01

Full Text Available Multiple repeat false targets (RFTs, created by the digital radio frequency memory (DRFM system of jammer, are widely used in practical to effectively exhaust the limited tracking and discrimination resource of defence radar. In this paper, common characteristic of radar polarization echoes of multiple RFTs is used for target recognition. Based on the echoes from two receiving polarization channels, the instantaneous polarization radio (IPR is defined and its variance is derived by employing Taylor series expansion. A detection-discrimination method is designed based on probability grids. By using the data from microwave anechoic chamber, the detection threshold of the method is confirmed. Theoretical analysis and simulations indicate that the method is valid and feasible. Furthermore, the estimation performance of IPRs of RFTs due to the influence of signal noise ratio (SNR is also covered.

Multiple-Features-Based Semisupervised Clustering DDoS Detection Method

Directory of Open Access Journals (Sweden)

Yonghao Gu

2017-01-01

Full Text Available DDoS attack stream from different agent host converged at victim host will become very large, which will lead to system halt or network congestion. Therefore, it is necessary to propose an effective method to detect the DDoS attack behavior from the massive data stream. In order to solve the problem that large numbers of labeled data are not provided in supervised learning method, and the relatively low detection accuracy and convergence speed of unsupervised k-means algorithm, this paper presents a semisupervised clustering detection method using multiple features. In this detection method, we firstly select three features according to the characteristics of DDoS attacks to form detection feature vector. Then, Multiple-Features-Based Constrained-K-Means (MF-CKM algorithm is proposed based on semisupervised clustering. Finally, using MIT Laboratory Scenario (DDoS 1.0 data set, we verify that the proposed method can improve the convergence speed and accuracy of the algorithm under the condition of using a small amount of labeled data sets.

Earthquake—explosion discrimination using genetic algorithm-based boosting approach

Science.gov (United States)

Orlic, Niksa; Loncaric, Sven

2010-02-01

An important and challenging problem in seismic data processing is to discriminate between natural seismic events such as earthquakes and artificial seismic events such as explosions. Many automatic techniques for seismogram classification have been proposed in the literature. Most of these methods have a similar approach to seismogram classification: a predefined set of features based on ad-hoc feature selection criteria is extracted from the seismogram waveform or spectral data and these features are used for signal classification. In this paper we propose a novel approach for seismogram classification. A specially formulated genetic algorithm has been employed to automatically search for a near-optimal seismogram feature set, instead of using ad-hoc feature selection criteria. A boosting method is added to the genetic algorithm when searching for multiple features in order to improve classification performance. A learning set of seismogram data is used by the genetic algorithm to discover a near-optimal feature set. The feature set identified by the genetic algorithm is then used for seismogram classification. The described method is developed to classify seismograms in two groups, whereas a brief overview of method extension for multiple group classification is given. For method verification, a learning set consisting of 40 local earthquake seismograms and 40 explosion seismograms was used. The method was validated on seismogram set consisting of 60 local earthquake seismograms and 60 explosion seismograms, with correct classification of 85%.

A Feature Subtraction Method for Image Based Kinship Verification under Uncontrolled Environments

DEFF Research Database (Denmark)

Duan, Xiaodong; Tan, Zheng-Hua

2015-01-01

The most fundamental problem of local feature based kinship verification methods is that a local feature can capture the variations of environmental conditions and the differences between two persons having a kin relation, which can significantly decrease the performance. To address this problem...... the feature distance between face image pairs with kinship and maximize the distance between non-kinship pairs. Based on the subtracted feature, the verification is realized through a simple Gaussian based distance comparison method. Experiments on two public databases show that the feature subtraction method...

Feature selection for splice site prediction: A new method using EDA-based feature ranking

Directory of Open Access Journals (Sweden)

Rouzé Pierre

2004-05-01

Full Text Available Abstract Background The identification of relevant biological features in large and complex datasets is an important step towards gaining insight in the processes underlying the data. Other advantages of feature selection include the ability of the classification system to attain good or even better solutions using a restricted subset of features, and a faster classification. Thus, robust methods for fast feature selection are of key importance in extracting knowledge from complex biological data. Results In this paper we present a novel method for feature subset selection applied to splice site prediction, based on estimation of distribution algorithms, a more general framework of genetic algorithms. From the estimated distribution of the algorithm, a feature ranking is derived. Afterwards this ranking is used to iteratively discard features. We apply this technique to the problem of splice site prediction, and show how it can be used to gain insight into the underlying biological process of splicing. Conclusion We show that this technique proves to be more robust than the traditional use of estimation of distribution algorithms for feature selection: instead of returning a single best subset of features (as they normally do this method provides a dynamical view of the feature selection process, like the traditional sequential wrapper methods. However, the method is faster than the traditional techniques, and scales better to datasets described by a large number of features.

Image Mosaic Method Based on SIFT Features of Line Segment

Directory of Open Access Journals (Sweden)

Jun Zhu

2014-01-01

Full Text Available This paper proposes a novel image mosaic method based on SIFT (Scale Invariant Feature Transform feature of line segment, aiming to resolve incident scaling, rotation, changes in lighting condition, and so on between two images in the panoramic image mosaic process. This method firstly uses Harris corner detection operator to detect key points. Secondly, it constructs directed line segments, describes them with SIFT feature, and matches those directed segments to acquire rough point matching. Finally, Ransac method is used to eliminate wrong pairs in order to accomplish image mosaic. The results from experiment based on four pairs of images show that our method has strong robustness for resolution, lighting, rotation, and scaling.

Prediction Model of Collapse Risk Based on Information Entropy and Distance Discriminant Analysis Method

Directory of Open Access Journals (Sweden)

Hujun He

2017-01-01

Full Text Available The prediction and risk classification of collapse is an important issue in the process of highway construction in mountainous regions. Based on the principles of information entropy and Mahalanobis distance discriminant analysis, we have produced a collapse hazard prediction model. We used the entropy measure method to reduce the influence indexes of the collapse activity and extracted the nine main indexes affecting collapse activity as the discriminant factors of the distance discriminant analysis model (i.e., slope shape, aspect, gradient, and height, along with exposure of the structural face, stratum lithology, relationship between weakness face and free face, vegetation cover rate, and degree of rock weathering. We employ postearthquake collapse data in relation to construction of the Yingxiu-Wolong highway, Hanchuan County, China, as training samples for analysis. The results were analyzed using the back substitution estimation method, showing high accuracy and no errors, and were the same as the prediction result of uncertainty measure. Results show that the classification model based on information entropy and distance discriminant analysis achieves the purpose of index optimization and has excellent performance, high prediction accuracy, and a zero false-positive rate. The model can be used as a tool for future evaluation of collapse risk.

Modification method to reduce the impact of blood vessel on noncontact discrimination of human blood based on ;M+N; theory

Science.gov (United States)

Zhang, Linna; Ding, Hongyan; Lin, Ling; Wang, Yimin; Guo, Xin

2018-01-01

Noncontact discriminating human blood is significantly crucial for import-export ports and inspection and quarantine departments. We had already demonstrated that visible diffuse reflectance spectroscopy combining PLS-DA method can successfully realize noncontact human blood discrimination. However, the circulated blood vessels may be produced with different materials. The use of various kinds of blood tubes may have a negative effect on the discrimination, based on ;M+N; theory (Li et al., 2016). In this research, we explored the impact of different material of blood vessels, such as glass tube and plastic tube, on the prediction ability of the discrimination model. Furthermore, we searched for the modification method to reduce the influence from the blood tubes. Our work indicated that generalized diffuse reflectance method can greatly improve the discrimination accuracy. This research can greatly facilitate the application of noncontact discrimination method based on visible and near-infrared diffuse reflectance spectroscopy.

A real-time neutron-gamma discriminator based on the support vector machine method for the time-of-flight neutron spectrometer

Science.gov (United States)

Wei, ZHANG; Tongyu, WU; Bowen, ZHENG; Shiping, LI; Yipo, ZHANG; Zejie, YIN

2018-04-01

A new neutron-gamma discriminator based on the support vector machine (SVM) method is proposed to improve the performance of the time-of-flight neutron spectrometer. The neutron detector is an EJ-299-33 plastic scintillator with pulse-shape discrimination (PSD) property. The SVM algorithm is implemented in field programmable gate array (FPGA) to carry out the real-time sifting of neutrons in neutron-gamma mixed radiation fields. This study compares the ability of the pulse gradient analysis method and the SVM method. The results show that this SVM discriminator can provide a better discrimination accuracy of 99.1%. The accuracy and performance of the SVM discriminator based on FPGA have been evaluated in the experiments. It can get a figure of merit of 1.30.

Feature Vector Construction Method for IRIS Recognition

Science.gov (United States)

Odinokikh, G.; Fartukov, A.; Korobkin, M.; Yoo, J.

2017-05-01

One of the basic stages of iris recognition pipeline is iris feature vector construction procedure. The procedure represents the extraction of iris texture information relevant to its subsequent comparison. Thorough investigation of feature vectors obtained from iris showed that not all the vector elements are equally relevant. There are two characteristics which determine the vector element utility: fragility and discriminability. Conventional iris feature extraction methods consider the concept of fragility as the feature vector instability without respect to the nature of such instability appearance. This work separates sources of the instability into natural and encodinginduced which helps deeply investigate each source of instability independently. According to the separation concept, a novel approach of iris feature vector construction is proposed. The approach consists of two steps: iris feature extraction using Gabor filtering with optimal parameters and quantization with separated preliminary optimized fragility thresholds. The proposed method has been tested on two different datasets of iris images captured under changing environmental conditions. The testing results show that the proposed method surpasses all the methods considered as a prior art by recognition accuracy on both datasets.

Dimensional feature weighting utilizing multiple kernel learning for single-channel talker location discrimination using the acoustic transfer function.

Science.gov (United States)

Takashima, Ryoichi; Takiguchi, Tetsuya; Ariki, Yasuo

2013-02-01

This paper presents a method for discriminating the location of the sound source (talker) using only a single microphone. In a previous work, the single-channel approach for discriminating the location of the sound source was discussed, where the acoustic transfer function from a user's position is estimated by using a hidden Markov model of clean speech in the cepstral domain. In this paper, each cepstral dimension of the acoustic transfer function is newly weighted, in order to obtain the cepstral dimensions having information that is useful for classifying the user's position. Then, this paper proposes a feature-weighting method for the cepstral parameter using multiple kernel learning, defining the base kernels for each cepstral dimension of the acoustic transfer function. The user's position is trained and classified by support vector machine. The effectiveness of this method has been confirmed by sound source (talker) localization experiments performed in different room environments.

Feature discrimination/identification based upon SAR return variations

Science.gov (United States)

Rasco, W. A., Sr.; Pietsch, R.

1978-01-01

A study of the statistics of The look-to-look variation statistics in the returns recorded in-flight by a digital, realtime SAR system are analyzed. The determination that the variations in the look-to-look returns from different classes do carry information content unique to the classes was illustrated by a model based on four variants derived from four look in-flight SAR data under study. The model was limited to four classes of returns: mowed grass on a athletic field, rough unmowed grass and weeds on a large vacant field, young fruit trees in a large orchard, and metal mobile homes and storage buildings in a large mobile home park. The data population in excess of 1000 returns represented over 250 individual pixels from the four classes. The multivariant discriminant model operated on the set of returns for each pixel and assigned that pixel to one of the four classes, based on the target variants and the probability distribution function of the four variants for each class.

A Novel Imbalanced Data Classification Approach Based on Logistic Regression and Fisher Discriminant

Directory of Open Access Journals (Sweden)

Baofeng Shi

2015-01-01

Full Text Available We introduce an imbalanced data classification approach based on logistic regression significant discriminant and Fisher discriminant. First of all, a key indicators extraction model based on logistic regression significant discriminant and correlation analysis is derived to extract features for customer classification. Secondly, on the basis of the linear weighted utilizing Fisher discriminant, a customer scoring model is established. And then, a customer rating model where the customer number of all ratings follows normal distribution is constructed. The performance of the proposed model and the classical SVM classification method are evaluated in terms of their ability to correctly classify consumers as default customer or nondefault customer. Empirical results using the data of 2157 customers in financial engineering suggest that the proposed approach better performance than the SVM model in dealing with imbalanced data classification. Moreover, our approach contributes to locating the qualified customers for the banks and the bond investors.

Finger vein recognition based on the hyperinformation feature

Science.gov (United States)

Xi, Xiaoming; Yang, Gongping; Yin, Yilong; Yang, Lu

2014-01-01

The finger vein is a promising biometric pattern for personal identification due to its advantages over other existing biometrics. In finger vein recognition, feature extraction is a critical step, and many feature extraction methods have been proposed to extract the gray, texture, or shape of the finger vein. We treat them as low-level features and present a high-level feature extraction framework. Under this framework, base attribute is first defined to represent the characteristics of a certain subcategory of a subject. Then, for an image, the correlation coefficient is used for constructing the high-level feature, which reflects the correlation between this image and all base attributes. Since the high-level feature can reveal characteristics of more subcategories and contain more discriminative information, we call it hyperinformation feature (HIF). Compared with low-level features, which only represent the characteristics of one subcategory, HIF is more powerful and robust. In order to demonstrate the potential of the proposed framework, we provide a case study to extract HIF. We conduct comprehensive experiments to show the generality of the proposed framework and the efficiency of HIF on our databases, respectively. Experimental results show that HIF significantly outperforms the low-level features.

Quantitative nucleic features are effective for discrimination of intraductal proliferative lesions of the breast

Directory of Open Access Journals (Sweden)

Masatoshi Yamada

2016-01-01

Full Text Available Background: Intraductal proliferative lesions (IDPLs of the breast are recognized as a risk factor for subsequent invasive carcinoma development. Although opportunities for IDPL diagnosis have increased, these lesions are difficult to diagnose correctly, especially atypical ductal hyperplasia (ADH and low-grade ductal carcinoma in situ (LG-DCIS. In order to define the difference between these lesions, many molecular pathological approaches have been performed. However, still we do not have a molecular marker and objective histological index about IDPLs of the breast. Methods: We generated full digital pathology archives from 175 female IDPL patients, including usual ductal hyperplasia (UDH, ADH, LG-DCIS, intermediate-grade (IM-DCIS, and high-grade (HG-DCIS. After total 2,035,807 nucleic segmentations were extracted, we evaluated nuclear features using step-wise linear discriminant analysis (LDA and a support vector machine. Results: High diagnostic accuracy (81.8–99.3% was achieved between pathologists' diagnoses and two-group LDA predictions from nucleic features for IDPL discrimination. Grouping of nuclear features as size and shape-related or intranuclear texture-related revealed that the latter group was more important when distinguishing between normal duct, UDH, ADH, and LG-DCIS. However, these two groups were equally important when discriminating between LG-DCIS and HG-DCIS. The Mahalanobis distances between each group showed that the smallest distance values occurred between LG-DCIS and IM-DCIS and between ADH and Normal. On the other hand, the distance value between ADH and LG-DCIS was larger than this distance. Conclusions: In this study, we have presented a practical and useful digital pathological method that incorporates nuclear morphological and textural features for IDPL prediction. We expect that this novel algorithm is used for the automated diagnosis assisting system for breast cancer.

Quantitative nucleic features are effective for discrimination of intraductal proliferative lesions of the breast

Science.gov (United States)

Yamada, Masatoshi; Saito, Akira; Yamamoto, Yoichiro; Cosatto, Eric; Kurata, Atsushi; Nagao, Toshitaka; Tateishi, Ayako; Kuroda, Masahiko

2016-01-01

Background: Intraductal proliferative lesions (IDPLs) of the breast are recognized as a risk factor for subsequent invasive carcinoma development. Although opportunities for IDPL diagnosis have increased, these lesions are difficult to diagnose correctly, especially atypical ductal hyperplasia (ADH) and low-grade ductal carcinoma in situ (LG-DCIS). In order to define the difference between these lesions, many molecular pathological approaches have been performed. However, still we do not have a molecular marker and objective histological index about IDPLs of the breast. Methods: We generated full digital pathology archives from 175 female IDPL patients, including usual ductal hyperplasia (UDH), ADH, LG-DCIS, intermediate-grade (IM)-DCIS, and high-grade (HG)-DCIS. After total 2,035,807 nucleic segmentations were extracted, we evaluated nuclear features using step-wise linear discriminant analysis (LDA) and a support vector machine. Results: High diagnostic accuracy (81.8–99.3%) was achieved between pathologists’ diagnoses and two-group LDA predictions from nucleic features for IDPL discrimination. Grouping of nuclear features as size and shape-related or intranuclear texture-related revealed that the latter group was more important when distinguishing between normal duct, UDH, ADH, and LG-DCIS. However, these two groups were equally important when discriminating between LG-DCIS and HG-DCIS. The Mahalanobis distances between each group showed that the smallest distance values occurred between LG-DCIS and IM-DCIS and between ADH and Normal. On the other hand, the distance value between ADH and LG-DCIS was larger than this distance. Conclusions: In this study, we have presented a practical and useful digital pathological method that incorporates nuclear morphological and textural features for IDPL prediction. We expect that this novel algorithm is used for the automated diagnosis assisting system for breast cancer. PMID:26955499

Feature extraction and learning using context cue and Rényi entropy based mutual information

DEFF Research Database (Denmark)

Pan, Hong; Olsen, Søren Ingvor; Zhu, Yaping

2015-01-01

information. In particular, for feature extraction, we develop a new set of kernel descriptors−Context Kernel Descriptors (CKD), which enhance the original KDES by embedding the spatial context into the descriptors. Context cues contained in the context kernel enforce some degree of spatial consistency, thus...... improving the robustness of CKD. For feature learning and reduction, we propose a novel codebook learning method, based on a Rényi quadratic entropy based mutual information measure called Cauchy-Schwarz Quadratic Mutual Information (CSQMI), to learn a compact and discriminative CKD codebook. Projecting...... as the information about the underlying labels of the CKD using CSQMI. Thus the resulting codebook and reduced CKD are discriminative. We verify the effectiveness of our method on several public image benchmark datasets such as YaleB, Caltech-101 and CIFAR-10, as well as a challenging chicken feet dataset of our own...

Discriminative topological features reveal biological network mechanisms

Directory of Open Access Journals (Sweden)

Levovitz Chaya

2004-11-01

Full Text Available Abstract Background Recent genomic and bioinformatic advances have motivated the development of numerous network models intending to describe graphs of biological, technological, and sociological origin. In most cases the success of a model has been evaluated by how well it reproduces a few key features of the real-world data, such as degree distributions, mean geodesic lengths, and clustering coefficients. Often pairs of models can reproduce these features with indistinguishable fidelity despite being generated by vastly different mechanisms. In such cases, these few target features are insufficient to distinguish which of the different models best describes real world networks of interest; moreover, it is not clear a priori that any of the presently-existing algorithms for network generation offers a predictive description of the networks inspiring them. Results We present a method to assess systematically which of a set of proposed network generation algorithms gives the most accurate description of a given biological network. To derive discriminative classifiers, we construct a mapping from the set of all graphs to a high-dimensional (in principle infinite-dimensional "word space". This map defines an input space for classification schemes which allow us to state unambiguously which models are most descriptive of a given network of interest. Our training sets include networks generated from 17 models either drawn from the literature or introduced in this work. We show that different duplication-mutation schemes best describe the E. coli genetic network, the S. cerevisiae protein interaction network, and the C. elegans neuronal network, out of a set of network models including a linear preferential attachment model and a small-world model. Conclusions Our method is a first step towards systematizing network models and assessing their predictability, and we anticipate its usefulness for a number of communities.

A window-based time series feature extraction method.

Science.gov (United States)

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

2017-10-01

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.

Role of amygdala central nucleus in feature negative discriminations

Science.gov (United States)

Holland, Peter C.

2012-01-01

Consistent with a popular theory of associative learning, the Pearce-Hall (1980) model, the surprising omission of expected events enhances cue associability (the ease with which a cue may enter into new associations), across a wide variety of behavioral training procedures. Furthermore, previous experiments from this laboratory showed that these enhancements are absent in rats with impaired function of the amygdala central nucleus (CeA). A notable exception to these assertions is found in feature negative (FN) discrimination learning, in which a “target” stimulus is reinforced when it is presented alone but nonreinforced when it is presented in compound with another, “feature” stimulus. According to the Pearce-Hall model, reinforcer omission on compound trials should enhance the associability of the feature relative to control training conditions. However, prior experiments have shown no evidence that CeA lesions affect FN discrimination learning. Here we explored this apparent contradiction by evaluating the hypothesis that the surprising omission of an event confers enhanced associability on a cue only if that cue itself generates the disconfirmed prediction. Thus, in a FN discrimination, the surprising omission of the reinforcer on compound trials would enhance the associability of the target stimulus but not that of the feature. Our data confirmed this hypothesis, and showed this enhancement to depend on intact CeA function, as in other procedures. The results are consistent with modern reformulations of both cue and reward processing theories that assign roles for both individual and aggregate error terms in associative learning. PMID:22889308

Improving the Separability of Deep Features with Discriminative Convolution Filters for RSI Classification

Directory of Open Access Journals (Sweden)

Na Liu

2018-03-01

Full Text Available The extraction of activation vectors (or deep features from the fully connected layers of a convolutional neural network (CNN model is widely used for remote sensing image (RSI representation. In this study, we propose to learn discriminative convolution filter (DCF based on class-specific separability criteria for linear transformation of deep features. In particular, two types of pretrained CNN called CaffeNet and VGG-VD16 are introduced to illustrate the generality of the proposed DCF. The activation vectors extracted from the fully connected layers of a CNN are rearranged into the form of an image matrix, from which a spatial arrangement of local patches is extracted using sliding window strategy. DCF learning is then performed on each local patch individually to obtain the corresponding discriminative convolution kernel through generalized eigenvalue decomposition. The proposed DCF learning characterizes that a convolutional kernel with small size (e.g., 3 × 3 pixels can be effectively learned on a small-size local patch (e.g., 8 × 8 pixels, thereby ensuring that the linear transformation of deep features can maintain low computational complexity. Experiments on two RSI datasets demonstrate the effectiveness of DCF in improving the classification performances of deep features without increasing dimensionality.

A novel murmur-based heart sound feature extraction technique using envelope-morphological analysis

Science.gov (United States)

Yao, Hao-Dong; Ma, Jia-Li; Fu, Bin-Bin; Wang, Hai-Yang; Dong, Ming-Chui

2015-07-01

Auscultation of heart sound (HS) signals serves as an important primary approach to diagnose cardiovascular diseases (CVDs) for centuries. Confronting the intrinsic drawbacks of traditional HS auscultation, computer-aided automatic HS auscultation based on feature extraction technique has witnessed explosive development. Yet, most existing HS feature extraction methods adopt acoustic or time-frequency features which exhibit poor relationship with diagnostic information, thus restricting the performance of further interpretation and analysis. Tackling such a bottleneck problem, this paper innovatively proposes a novel murmur-based HS feature extraction method since murmurs contain massive pathological information and are regarded as the first indications of pathological occurrences of heart valves. Adapting discrete wavelet transform (DWT) and Shannon envelope, the envelope-morphological characteristics of murmurs are obtained and three features are extracted accordingly. Validated by discriminating normal HS and 5 various abnormal HS signals with extracted features, the proposed method provides an attractive candidate in automatic HS auscultation.

A Method to Measure the Bracelet Based on Feature Energy

Science.gov (United States)

Liu, Hongmin; Li, Lu; Wang, Zhiheng; Huo, Zhanqiang

2017-12-01

To measure the bracelet automatically, a novel method based on feature energy is proposed. Firstly, the morphological method is utilized to preprocess the image, and the contour consisting of a concentric circle is extracted. Then, a feature energy function, which is relevant to the distances from one pixel to the edge points, is defined taking into account the geometric properties of the concentric circle. The input image is subsequently transformed to the feature energy distribution map (FEDM) by computing the feature energy of each pixel. The center of the concentric circle is thus located by detecting the maximum on the FEDM; meanwhile, the radii of the concentric circle are determined according to the feature energy function of the center pixel. Finally, with the use of a calibration template, the internal diameter and thickness of the bracelet are measured. The experimental results show that the proposed method can measure the true sizes of the bracelet accurately with the simplicity, directness and robustness compared to the existing methods.

Combining features from ERP components in single-trial EEG for discriminating four-category visual objects

Science.gov (United States)

Wang, Changming; Xiong, Shi; Hu, Xiaoping; Yao, Li; Zhang, Jiacai

2012-10-01

Categorization of images containing visual objects can be successfully recognized using single-trial electroencephalograph (EEG) measured when subjects view images. Previous studies have shown that task-related information contained in event-related potential (ERP) components could discriminate two or three categories of object images. In this study, we investigated whether four categories of objects (human faces, buildings, cats and cars) could be mutually discriminated using single-trial EEG data. Here, the EEG waveforms acquired while subjects were viewing four categories of object images were segmented into several ERP components (P1, N1, P2a and P2b), and then Fisher linear discriminant analysis (Fisher-LDA) was used to classify EEG features extracted from ERP components. Firstly, we compared the classification results using features from single ERP components, and identified that the N1 component achieved the highest classification accuracies. Secondly, we discriminated four categories of objects using combining features from multiple ERP components, and showed that combination of ERP components improved four-category classification accuracies by utilizing the complementarity of discriminative information in ERP components. These findings confirmed that four categories of object images could be discriminated with single-trial EEG and could direct us to select effective EEG features for classifying visual objects.

Discrimination of Breast Tumors in Ultrasonic Images by Classifier Ensemble Trained with AdaBoost

Science.gov (United States)

Takemura, Atsushi; Shimizu, Akinobu; Hamamoto, Kazuhiko

In this paper, we propose a novel method for acurate automated discrimination of breast tumors (carcinoma, fibroadenoma, and cyst). We defined 199 features related to diagnositic observations noticed when a doctor judges breast tumors, such as internal echo, shape, and boundary echo. These features included novel features based on a parameter of log-compressed K distribution, which reflect physical characteristics of ultrasonic B-mode imaging. Furthermore, we propose a discrimination method of breast tumors by using an ensemble classifier based on the multi-class AdaBoost algorithm with effective features selection. Verification by analyzing 200 carcinomas, 30 fibroadenomas and 30 cycts showed the usefulness of the newly defined features and the effectiveness of the discrimination by using an ensemble classifier trained by AdaBoost.

SAR Target Recognition Based on Multi-feature Multiple Representation Classifier Fusion

Directory of Open Access Journals (Sweden)

Zhang Xinzheng

2017-10-01

Full Text Available In this paper, we present a Synthetic Aperture Radar (SAR image target recognition algorithm based on multi-feature multiple representation learning classifier fusion. First, it extracts three features from the SAR images, namely principal component analysis, wavelet transform, and Two-Dimensional Slice Zernike Moments (2DSZM features. Second, we harness the sparse representation classifier and the cooperative representation classifier with the above-mentioned features to get six predictive labels. Finally, we adopt classifier fusion to obtain the final recognition decision. We researched three different classifier fusion algorithms in our experiments, and the results demonstrate thatusing Bayesian decision fusion gives thebest recognition performance. The method based on multi-feature multiple representation learning classifier fusion integrates the discrimination of multi-features and combines the sparse and cooperative representation classification performance to gain complementary advantages and to improve recognition accuracy. The experiments are based on the Moving and Stationary Target Acquisition and Recognition (MSTAR database,and they demonstrate the effectiveness of the proposed approach.

An efficient approach for differentiating Alzheimer's disease from normal elderly based on multicenter MRI using gray-level invariant features.

Directory of Open Access Journals (Sweden)

Muwei Li

Full Text Available Machine learning techniques, along with imaging markers extracted from structural magnetic resonance images, have been shown to increase the accuracy to differentiate patients with Alzheimer's disease (AD from normal elderly controls. Several forms of anatomical features, such as cortical volume, shape, and thickness, have demonstrated discriminative capability. These approaches rely on accurate non-linear image transformation, which could invite several nuisance factors, such as dependency on transformation parameters and the degree of anatomical abnormality, and an unpredictable influence of residual registration errors. In this study, we tested a simple method to extract disease-related anatomical features, which is suitable for initial stratification of the heterogeneous patient populations often encountered in clinical data. The method employed gray-level invariant features, which were extracted from linearly transformed images, to characterize AD-specific anatomical features. The intensity information from a disease-specific spatial masking, which was linearly registered to each patient, was used to capture the anatomical features. We implemented a two-step feature selection for anatomic recognition. First, a statistic-based feature selection was implemented to extract AD-related anatomical features while excluding non-significant features. Then, seven knowledge-based ROIs were used to capture the local discriminative powers of selected voxels within areas that were sensitive to AD or mild cognitive impairment (MCI. The discriminative capability of the proposed feature was measured by its performance in differentiating AD or MCI from normal elderly controls (NC using a support vector machine. The statistic-based feature selection, together with the knowledge-based masks, provided a promising solution for capturing anatomical features of the brain efficiently. For the analysis of clinical populations, which are inherently heterogeneous

An automatic method to discriminate malignant masses from normal tissue in digital mammograms

International Nuclear Information System (INIS)

Brake, Guido M. te; Karssemeijer, Nico; Hendriks, Jan H.C.L.

2000-01-01

Specificity levels of automatic mass detection methods in mammography are generally rather low, because suspicious looking normal tissue is often hard to discriminate from real malignant masses. In this work a number of features were defined that are related to image characteristics that radiologists use to discriminate real lesions from normal tissue. An artificial neural network was used to map the computed features to a measure of suspiciousness for each region that was found suspicious by a mass detection method. Two data sets were used to test the method. The first set of 72 malignant cases (132 films) was a consecutive series taken from the Nijmegen screening programme, 208 normal films were added to improve the estimation of the specificity of the method. The second set was part of the new DDSM data set from the University of South Florida. A total of 193 cases (772 films) with 372 annotated malignancies was used. The measure of suspiciousness that was computed using the image characteristics was successful in discriminating tumours from false positive detections. Approximately 75% of all cancers were detected in at least one view at a specificity level of 0.1 false positive per image. (author)

Discrete Discriminant analysis based on tree-structured graphical models

DEFF Research Database (Denmark)

Perez de la Cruz, Gonzalo; Eslava, Guillermina

The purpose of this paper is to illustrate the potential use of discriminant analysis based on tree{structured graphical models for discrete variables. This is done by comparing its empirical performance using estimated error rates for real and simulated data. The results show that discriminant a...... analysis based on tree{structured graphical models is a simple nonlinear method competitive with, and sometimes superior to, other well{known linear methods like those assuming mutual independence between variables and linear logistic regression.......The purpose of this paper is to illustrate the potential use of discriminant analysis based on tree{structured graphical models for discrete variables. This is done by comparing its empirical performance using estimated error rates for real and simulated data. The results show that discriminant...

Identification of natural images and computer-generated graphics based on statistical and textural features.

Science.gov (United States)

Peng, Fei; Li, Jiao-ting; Long, Min

2015-03-01

To discriminate the acquisition pipelines of digital images, a novel scheme for the identification of natural images and computer-generated graphics is proposed based on statistical and textural features. First, the differences between them are investigated from the view of statistics and texture, and 31 dimensions of feature are acquired for identification. Then, LIBSVM is used for the classification. Finally, the experimental results are presented. The results show that it can achieve an identification accuracy of 97.89% for computer-generated graphics, and an identification accuracy of 97.75% for natural images. The analyses also demonstrate the proposed method has excellent performance, compared with some existing methods based only on statistical features or other features. The method has a great potential to be implemented for the identification of natural images and computer-generated graphics. © 2014 American Academy of Forensic Sciences.

Finger-vein and fingerprint recognition based on a feature-level fusion method

Science.gov (United States)

Yang, Jinfeng; Hong, Bofeng

2013-07-01

Multimodal biometrics based on the finger identification is a hot topic in recent years. In this paper, a novel fingerprint-vein based biometric method is proposed to improve the reliability and accuracy of the finger recognition system. First, the second order steerable filters are used here to enhance and extract the minutiae features of the fingerprint (FP) and finger-vein (FV). Second, the texture features of fingerprint and finger-vein are extracted by a bank of Gabor filter. Third, a new triangle-region fusion method is proposed to integrate all the fingerprint and finger-vein features in feature-level. Thus, the fusion features contain both the finger texture-information and the minutiae triangular geometry structure. Finally, experimental results performed on the self-constructed finger-vein and fingerprint databases are shown that the proposed method is reliable and precise in personal identification.

New Keypoint Matching Method Using Local Convolutional Features for Power Transmission Line Icing Monitoring

Directory of Open Access Journals (Sweden)

Qiangliang Guo

2018-02-01

Full Text Available Power transmission line icing (PTLI problems, which cause tremendous damage to the power grids, has drawn much attention. Existing three-dimensional measurement methods based on binocular stereo vision was recently introduced to measure the ice thickness in PTLI, but failed to meet requirements of practical applications due to inefficient keypoint matching in the complex PTLI scene. In this paper, a new keypoint matching method is proposed based on the local multi-layer convolutional neural network (CNN features, termed Local Convolutional Features (LCFs. LCFs are deployed to extract more discriminative features than the conventional CNNs. Particularly in LCFs, a multi-layer features fusion scheme is exploited to boost the matching performance. Together with a location constraint method, the correspondence of neighboring keypoints is further refined. Our approach achieves 1.5%, 5.3%, 13.1%, 27.3% improvement in the average matching precision compared with SIFT, SURF, ORB and MatchNet on the public Middlebury dataset, and the measurement accuracy of ice thickness can reach 90.9% compared with manual measurement on the collected PTLI dataset.

A circular feature-based pose measurement method for metal part grasping

International Nuclear Information System (INIS)

Wu, Chenrui; He, Zaixing; Zhang, Shuyou; Zhao, Xinyue

2017-01-01

The grasping of circular metal parts such as bearings and flanges is a common task in industry. Limited by low texture and repeated features, the point-feature-based method is not applicable in pose measurement of these parts. In this paper, we propose a novel pose measurement method for grasping circular metal parts. This method is based on cone degradation and involves a monocular camera. To achieve higher measurement accuracy, a position-based visual servoing method is presented to continuously control an eye-in-hand, six-degrees-of-freedom robot arm to grasp the part. The uncertainty of the part’s coordinate frame during the control process is solved by defining a fixed virtual coordinate frame. Experimental results are provided to illustrate the effectiveness of the proposed method and the factors that affect measurement accuracy are analyzed. (paper)

Discriminative phenomenological features of scale invariant models for electroweak symmetry breaking

Directory of Open Access Journals (Sweden)

Katsuya Hashino

2016-01-01

Full Text Available Classical scale invariance (CSI may be one of the solutions for the hierarchy problem. Realistic models for electroweak symmetry breaking based on CSI require extended scalar sectors without mass terms, and the electroweak symmetry is broken dynamically at the quantum level by the Coleman–Weinberg mechanism. We discuss discriminative features of these models. First, using the experimental value of the mass of the discovered Higgs boson h(125, we obtain an upper bound on the mass of the lightest additional scalar boson (≃543 GeV, which does not depend on its isospin and hypercharge. Second, a discriminative prediction on the Higgs-photon–photon coupling is given as a function of the number of charged scalar bosons, by which we can narrow down possible models using current and future data for the di-photon decay of h(125. Finally, for the triple Higgs boson coupling a large deviation (∼+70% from the SM prediction is universally predicted, which is independent of masses, quantum numbers and even the number of additional scalars. These models based on CSI can be well tested at LHC Run II and at future lepton colliders.

Efficient ConvNet Feature Extraction with Multiple RoI Pooling for Landmark-Based Visual Localization of Autonomous Vehicles

Directory of Open Access Journals (Sweden)

Yi Hou

2017-01-01

Full Text Available Efficient and robust visual localization is important for autonomous vehicles. By achieving impressive localization accuracy under conditions of significant changes, ConvNet landmark-based approach has attracted the attention of people in several research communities including autonomous vehicles. Such an approach relies heavily on the outstanding discrimination power of ConvNet features to match detected landmarks between images. However, a major challenge of this approach is how to extract discriminative ConvNet features efficiently. To address this challenging, inspired by the high efficiency of the region of interest (RoI pooling layer, we propose a Multiple RoI (MRoI pooling technique, an enhancement of RoI, and a simple yet efficient ConvNet feature extraction method. Our idea is to leverage MRoI pooling to exploit multilevel and multiresolution information from multiple convolutional layers and then fuse them to improve the discrimination capacity of the final ConvNet features. The main advantages of our method are (a high computational efficiency for real-time applications; (b GPU memory efficiency for mobile applications; and (c use of pretrained model without fine-tuning or retraining for easy implementation. Experimental results on four datasets have demonstrated not only the above advantages but also the high discriminating power of the extracted ConvNet features with state-of-the-art localization accuracy.

Forensic Automatic Speaker Recognition Based on Likelihood Ratio Using Acoustic-phonetic Features Measured Automatically

Directory of Open Access Journals (Sweden)

Huapeng Wang

2015-01-01

Full Text Available Forensic speaker recognition is experiencing a remarkable paradigm shift in terms of the evaluation framework and presentation of voice evidence. This paper proposes a new method of forensic automatic speaker recognition using the likelihood ratio framework to quantify the strength of voice evidence. The proposed method uses a reference database to calculate the within- and between-speaker variability. Some acoustic-phonetic features are extracted automatically using the software VoiceSauce. The effectiveness of the approach was tested using two Mandarin databases: A mobile telephone database and a landline database. The experiment's results indicate that these acoustic-phonetic features do have some discriminating potential and are worth trying in discrimination. The automatic acoustic-phonetic features have acceptable discriminative performance and can provide more reliable results in evidence analysis when fused with other kind of voice features.

Linear feature selection in texture analysis - A PLS based method

DEFF Research Database (Denmark)

Marques, Joselene; Igel, Christian; Lillholm, Martin

2013-01-01

We present a texture analysis methodology that combined uncommitted machine-learning techniques and partial least square (PLS) in a fully automatic framework. Our approach introduces a robust PLS-based dimensionality reduction (DR) step to specifically address outliers and high-dimensional feature...... and considering all CV groups, the methods selected 36 % of the original features available. The diagnosis evaluation reached a generalization area-under-the-ROC curve of 0.92, which was higher than established cartilage-based markers known to relate to OA diagnosis....

Street Lighting Infrastructure Assessment Using Discriminant and GIS Method on Mount Merapi Evacuation Road

Science.gov (United States)

Izdihar, R. P.; Maryono, M.; Widjonarko, W.; Rahayu, S.

2018-02-01

This research aims to assess street lighting infrastructure in rural-urban of Mount Merapi Evacuation road. Three evacuation road/corridor; Mriyan-Boyolali, Wonodoyo-Boyolali and Samiran-Boyolali are selected as case study. By using discriminant this study examine 6 variables namely type of lamp, physical component, height, time, power and cons consumption. In addition this study also using GIS method to assessing geographical feature as of previous result. According to the discriminant analysis, the characteristic of street lighting could be distinguished as two characteristic, while from the GIS assessment, the study found three characteristic of geographical street lighting feature.

Multimodal Discrimination of Schizophrenia Using Hybrid Weighted Feature Concatenation of Brain Functional Connectivity and Anatomical Features with an Extreme Learning Machine

Directory of Open Access Journals (Sweden)

Muhammad Naveed Iqbal Qureshi

2017-09-01

Full Text Available Multimodal features of structural and functional magnetic resonance imaging (MRI of the human brain can assist in the diagnosis of schizophrenia. We performed a classification study on age, sex, and handedness-matched subjects. The dataset we used is publicly available from the Center for Biomedical Research Excellence (COBRE and it consists of two groups: patients with schizophrenia and healthy controls. We performed an independent component analysis and calculated global averaged functional connectivity-based features from the resting-state functional MRI data for all the cortical and subcortical anatomical parcellation. Cortical thickness along with standard deviation, surface area, volume, curvature, white matter volume, and intensity measures from the cortical parcellation, as well as volume and intensity from sub-cortical parcellation and overall volume of cortex features were extracted from the structural MRI data. A novel hybrid weighted feature concatenation method was used to acquire maximal 99.29% (P < 0.0001 accuracy which preserves high discriminatory power through the weight of the individual feature type. The classification was performed by an extreme learning machine, and its efficiency was compared to linear and non-linear (radial basis function support vector machines, linear discriminant analysis, and random forest bagged tree ensemble algorithms. This article reports the predictive accuracy of both unimodal and multimodal features after 10-by-10-fold nested cross-validation. A permutation test followed the classification experiment to assess the statistical significance of the classification results. It was concluded that, from a clinical perspective, this feature concatenation approach may assist the clinicians in schizophrenia diagnosis.

Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling.

Science.gov (United States)

Keshtkaran, Mohammad Reza; Yang, Zhi

2017-06-01

Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. Most of the feature extraction and dimensionality reduction techniques that have been used for spike sorting give a projection subspace which is not necessarily the most discriminative one. Therefore, the clusters which appear inherently separable in some discriminative subspace may overlap if projected using conventional feature extraction approaches leading to a poor sorting accuracy especially when the noise level is high. In this paper, we propose a noise-robust and unsupervised spike sorting algorithm based on learning discriminative spike features for clustering. The proposed algorithm uses discriminative subspace learning to extract low dimensional and most discriminative features from the spike waveforms and perform clustering with automatic detection of the number of the clusters. The core part of the algorithm involves iterative subspace selection using linear discriminant analysis and clustering using Gaussian mixture model with outlier detection. A statistical test in the discriminative subspace is proposed to automatically detect the number of the clusters. Comparative results on publicly available simulated and real in vivo datasets demonstrate that our algorithm achieves substantially improved cluster distinction leading to higher sorting accuracy and more reliable detection of clusters which are highly overlapping and not detectable using conventional feature extraction techniques such as principal component analysis or wavelets. By providing more accurate information about the activity of more number of individual neurons with high robustness to neural noise and outliers, the proposed unsupervised spike sorting algorithm facilitates more detailed and accurate analysis of single- and multi-unit activities in neuroscience and brain machine interface studies.

Noise-robust unsupervised spike sorting based on discriminative subspace learning with outlier handling

Science.gov (United States)

Keshtkaran, Mohammad Reza; Yang, Zhi

2017-06-01

Objective. Spike sorting is a fundamental preprocessing step for many neuroscience studies which rely on the analysis of spike trains. Most of the feature extraction and dimensionality reduction techniques that have been used for spike sorting give a projection subspace which is not necessarily the most discriminative one. Therefore, the clusters which appear inherently separable in some discriminative subspace may overlap if projected using conventional feature extraction approaches leading to a poor sorting accuracy especially when the noise level is high. In this paper, we propose a noise-robust and unsupervised spike sorting algorithm based on learning discriminative spike features for clustering. Approach. The proposed algorithm uses discriminative subspace learning to extract low dimensional and most discriminative features from the spike waveforms and perform clustering with automatic detection of the number of the clusters. The core part of the algorithm involves iterative subspace selection using linear discriminant analysis and clustering using Gaussian mixture model with outlier detection. A statistical test in the discriminative subspace is proposed to automatically detect the number of the clusters. Main results. Comparative results on publicly available simulated and real in vivo datasets demonstrate that our algorithm achieves substantially improved cluster distinction leading to higher sorting accuracy and more reliable detection of clusters which are highly overlapping and not detectable using conventional feature extraction techniques such as principal component analysis or wavelets. Significance. By providing more accurate information about the activity of more number of individual neurons with high robustness to neural noise and outliers, the proposed unsupervised spike sorting algorithm facilitates more detailed and accurate analysis of single- and multi-unit activities in neuroscience and brain machine interface studies.

A pulse-shape discrimination method for improving Gamma-ray spectrometry based on a new digital shaping filter

Science.gov (United States)

Qin, Zhang-jian; Chen, Chuan; Luo, Jun-song; Xie, Xing-hong; Ge, Liang-quan; Wu, Qi-fan

2018-04-01

It is a usual practice for improving spectrum quality by the mean of designing a good shaping filter to improve signal-noise ratio in development of nuclear spectroscopy. Another method is proposed in the paper based on discriminating pulse-shape and discarding the bad pulse whose shape is distorted as a result of abnormal noise, unusual ballistic deficit or bad pulse pile-up. An Exponentially Decaying Pulse (EDP) generated in nuclear particle detectors can be transformed into a Mexican Hat Wavelet Pulse (MHWP) and the derivation process of the transform is given. After the transform is performed, the baseline drift is removed in the new MHWP. Moreover, the MHWP-shape can be discriminated with the three parameters: the time difference between the two minima of the MHWP, and the two ratios which are from the amplitude of the two minima respectively divided by the amplitude of the maximum in the MHWP. A new type of nuclear spectroscopy was implemented based on the new digital shaping filter and the Gamma-ray spectra were acquired with a variety of pulse-shape discrimination levels. It had manifested that the energy resolution and the peak-Compton ratio were both improved after the pulse-shape discrimination method was used.

Automatic building extraction from LiDAR data fusion of point and grid-based features

Science.gov (United States)

Du, Shouji; Zhang, Yunsheng; Zou, Zhengrong; Xu, Shenghua; He, Xue; Chen, Siyang

2017-08-01

This paper proposes a method for extracting buildings from LiDAR point cloud data by combining point-based and grid-based features. To accurately discriminate buildings from vegetation, a point feature based on the variance of normal vectors is proposed. For a robust building extraction, a graph cuts algorithm is employed to combine the used features and consider the neighbor contexture information. As grid feature computing and a graph cuts algorithm are performed on a grid structure, a feature-retained DSM interpolation method is proposed in this paper. The proposed method is validated by the benchmark ISPRS Test Project on Urban Classification and 3D Building Reconstruction and compared to the state-art-of-the methods. The evaluation shows that the proposed method can obtain a promising result both at area-level and at object-level. The method is further applied to the entire ISPRS dataset and to a real dataset of the Wuhan City. The results show a completeness of 94.9% and a correctness of 92.2% at the per-area level for the former dataset and a completeness of 94.4% and a correctness of 95.8% for the latter one. The proposed method has a good potential for large-size LiDAR data.

Cross-Modality 2D-3D Face Recognition via Multiview Smooth Discriminant Analysis Based on ELM

Directory of Open Access Journals (Sweden)

Yi Jin

2014-01-01

Full Text Available In recent years, 3D face recognition has attracted increasing attention from worldwide researchers. Rather than homogeneous face data, more and more applications require flexible input face data nowadays. In this paper, we propose a new approach for cross-modality 2D-3D face recognition (FR, which is called Multiview Smooth Discriminant Analysis (MSDA based on Extreme Learning Machines (ELM. Adding the Laplacian penalty constrain for the multiview feature learning, the proposed MSDA is first proposed to extract the cross-modality 2D-3D face features. The MSDA aims at finding a multiview learning based common discriminative feature space and it can then fully utilize the underlying relationship of features from different views. To speed up the learning phase of the classifier, the recent popular algorithm named Extreme Learning Machine (ELM is adopted to train the single hidden layer feedforward neural networks (SLFNs. To evaluate the effectiveness of our proposed FR framework, experimental results on a benchmark face recognition dataset are presented. Simulations show that our new proposed method generally outperforms several recent approaches with a fast training speed.

An Aerial Video Stabilization Method Based on SURF Feature

Directory of Open Access Journals (Sweden)

Wu Hao

2016-01-01

Full Text Available The video captured by Micro Aerial Vehicle is often degraded due to unexpected random trembling and jitter caused by wind and the shake of the aerial platform. An approach for stabilizing the aerial video based on SURF feature and Kalman filter is proposed. SURF feature points are extracted in each frame, and the feature points between adjacent frames are matched using Fast Library for Approximate Nearest Neighbors search method. Then Random Sampling Consensus matching algorithm and Least Squares Method are used to remove mismatching points pairs, and estimate the transformation between the adjacent images. Finally, Kalman filter is applied to smooth the motion parameters and separate Intentional Motion from Unwanted Motion to stabilize the aerial video. Experiments results show that the approach can stabilize aerial video efficiently with high accuracy, and it is robust to the translation, rotation and zooming motion of camera.

Absolute cosine-based SVM-RFE feature selection method for prostate histopathological grading.

Science.gov (United States)

Sahran, Shahnorbanun; Albashish, Dheeb; Abdullah, Azizi; Shukor, Nordashima Abd; Hayati Md Pauzi, Suria

2018-04-18

Feature selection (FS) methods are widely used in grading and diagnosing prostate histopathological images. In this context, FS is based on the texture features obtained from the lumen, nuclei, cytoplasm and stroma, all of which are important tissue components. However, it is difficult to represent the high-dimensional textures of these tissue components. To solve this problem, we propose a new FS method that enables the selection of features with minimal redundancy in the tissue components. We categorise tissue images based on the texture of individual tissue components via the construction of a single classifier and also construct an ensemble learning model by merging the values obtained by each classifier. Another issue that arises is overfitting due to the high-dimensional texture of individual tissue components. We propose a new FS method, SVM-RFE(AC), that integrates a Support Vector Machine-Recursive Feature Elimination (SVM-RFE) embedded procedure with an absolute cosine (AC) filter method to prevent redundancy in the selected features of the SV-RFE and an unoptimised classifier in the AC. We conducted experiments on H&E histopathological prostate and colon cancer images with respect to three prostate classifications, namely benign vs. grade 3, benign vs. grade 4 and grade 3 vs. grade 4. The colon benchmark dataset requires a distinction between grades 1 and 2, which are the most difficult cases to distinguish in the colon domain. The results obtained by both the single and ensemble classification models (which uses the product rule as its merging method) confirm that the proposed SVM-RFE(AC) is superior to the other SVM and SVM-RFE-based methods. We developed an FS method based on SVM-RFE and AC and successfully showed that its use enabled the identification of the most crucial texture feature of each tissue component. Thus, it makes possible the distinction between multiple Gleason grades (e.g. grade 3 vs. grade 4) and its performance is far superior to

Pleasant/Unpleasant Filtering for Affective Image Retrieval Based on Cross-Correlation of EEG Features

Directory of Open Access Journals (Sweden)

Keranmu Xielifuguli

2014-01-01

Full Text Available People often make decisions based on sensitivity rather than rationality. In the field of biological information processing, methods are available for analyzing biological information directly based on electroencephalogram: EEG to determine the pleasant/unpleasant reactions of users. In this study, we propose a sensitivity filtering technique for discriminating preferences (pleasant/unpleasant for images using a sensitivity image filtering system based on EEG. Using a set of images retrieved by similarity retrieval, we perform the sensitivity-based pleasant/unpleasant classification of images based on the affective features extracted from images with the maximum entropy method: MEM. In the present study, the affective features comprised cross-correlation features obtained from EEGs produced when an individual observed an image. However, it is difficult to measure the EEG when a subject visualizes an unknown image. Thus, we propose a solution where a linear regression method based on canonical correlation is used to estimate the cross-correlation features from image features. Experiments were conducted to evaluate the validity of sensitivity filtering compared with image similarity retrieval methods based on image features. We found that sensitivity filtering using color correlograms was suitable for the classification of preferred images, while sensitivity filtering using local binary patterns was suitable for the classification of unpleasant images. Moreover, sensitivity filtering using local binary patterns for unpleasant images had a 90% success rate. Thus, we conclude that the proposed method is efficient for filtering unpleasant images.

Perceptions of gender-based discrimination during surgical training and practice

OpenAIRE

Bruce, Adrienne N.; Battista, Alexis; Plankey, Michael W.; Johnson, Lynt B.; Marshall, M. Blair

2015-01-01

Background: Women represent 15% of practicing general surgeons. Gender-based discrimination has been implicated as discouraging women from surgery. We sought to determine women’s perceptions of gender-based discrimination in the surgical training and working environment.Methods: Following IRB approval, we fielded a pilot survey measuring perceptions and impact of gender-based discrimination in medical school, residency training, and surgical practice. It was sent electronically to 1,065 indiv...

A quantitative method for determining spatial discriminative capacity

Directory of Open Access Journals (Sweden)

Dennis Robert G

2008-03-01

Full Text Available Abstract Background The traditional two-point discrimination (TPD test, a widely used tactile spatial acuity measure, has been criticized as being imprecise because it is based on subjective criteria and involves a number of non-spatial cues. The results of a recent study showed that as two stimuli were delivered simultaneously, vibrotactile amplitude discrimination became worse when the two stimuli were positioned relatively close together and was significantly degraded when the probes were within a subject's two-point limen. The impairment of amplitude discrimination with decreasing inter-probe distance suggested that the metric of amplitude discrimination could possibly provide a means of objective and quantitative measurement of spatial discrimination capacity. Methods A two alternative forced-choice (2AFC tracking procedure was used to assess a subject's ability to discriminate the amplitude difference between two stimuli positioned at near-adjacent skin sites. Two 25 Hz flutter stimuli, identical except for a constant difference in amplitude, were delivered simultaneously to the hand dorsum. The stimuli were initially spaced 30 mm apart, and the inter-stimulus distance was modified on a trial-by-trial basis based on the subject's performance of discriminating the stimulus with higher intensity. The experiment was repeated via sequential, rather than simultaneous, delivery of the same vibrotactile stimuli. Results Results obtained from this study showed that the performance of the amplitude discrimination task was significantly degraded when the stimuli were delivered simultaneously and were near a subject's two-point limen. In contrast, subjects were able to correctly discriminate between the amplitudes of the two stimuli when they were sequentially delivered at all inter-probe distances (including those within the two-point limen, and improved when an adapting stimulus was delivered prior to simultaneously delivered stimuli. Conclusion

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.

Human listeners provide insights into echo features used by dolphins (Tursiops truncatus) to discriminate among objects.

Science.gov (United States)

Delong, Caroline M; Au, Whitlow W L; Harley, Heidi E; Roitblat, Herbert L; Pytka, Lisa

2007-08-01

Echolocating bottlenose dolphins (Tursiops truncatus) discriminate between objects on the basis of the echoes reflected by the objects. However, it is not clear which echo features are important for object discrimination. To gain insight into the salient features, the authors had a dolphin perform a match-to-sample task and then presented human listeners with echoes from the same objects used in the dolphin's task. In 2 experiments, human listeners performed as well or better than the dolphin at discriminating objects, and they reported the salient acoustic cues. The error patterns of the humans and the dolphin were compared to determine which acoustic features were likely to have been used by the dolphin. The results indicate that the dolphin did not appear to use overall echo amplitude, but that it attended to the pattern of changes in the echoes across different object orientations. Human listeners can quickly identify salient combinations of echo features that permit object discrimination, which can be used to generate hypotheses that can be tested using dolphins as subjects.

Perceptions of gender-based discrimination during surgical training and practice

Directory of Open Access Journals (Sweden)

Adrienne N. Bruce

2015-02-01

Full Text Available Background: Women represent 15% of practicing general surgeons. Gender-based discrimination has been implicated as discouraging women from surgery. We sought to determine women's perceptions of gender-based discrimination in the surgical training and working environment. Methods: Following IRB approval, we fielded a pilot survey measuring perceptions and impact of gender-based discrimination in medical school, residency training, and surgical practice. It was sent electronically to 1,065 individual members of the Association of Women Surgeons. Results: We received 334 responses from medical students, residents, and practicing physicians with a response rate of 31%. Eighty-seven percent experienced gender-based discrimination in medical school, 88% in residency, and 91% in practice. Perceived sources of gender-based discrimination included superiors, physician peers, clinical support staff, and patients, with 40% emanating from women and 60% from men. Conclusions: The majority of responses indicated perceived gender-based discrimination during medical school, residency, and practice. Gender-based discrimination comes from both sexes and has a significant impact on women surgeons.

Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification

Energy Technology Data Exchange (ETDEWEB)

Jing, Yaqi; Meng, Qinghao, E-mail: qh-meng@tju.edu.cn; Qi, Peifeng; Zeng, Ming; Li, Wei; Ma, Shugen [Tianjin Key Laboratory of Process Measurement and Control, Institute of Robotics and Autonomous Systems, School of Electrical Engineering and Automation, Tianjin University, Tianjin 300072 (China)

2014-05-15

An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classification rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively.

Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification

International Nuclear Information System (INIS)

Jing, Yaqi; Meng, Qinghao; Qi, Peifeng; Zeng, Ming; Li, Wei; Ma, Shugen

2014-01-01

An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classification rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively

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.

A Feature Subset Selection Method Based On High-Dimensional Mutual Information

Directory of Open Access Journals (Sweden)

Chee Keong Kwoh

2011-04-01

Full Text Available Feature selection is an important step in building accurate classifiers and provides better understanding of the data sets. In this paper, we propose a feature subset selection method based on high-dimensional mutual information. We also propose to use the entropy of the class attribute as a criterion to determine the appropriate subset of features when building classifiers. We prove that if the mutual information between a feature set X and the class attribute Y equals to the entropy of Y , then X is a Markov Blanket of Y . We show that in some cases, it is infeasible to approximate the high-dimensional mutual information with algebraic combinations of pairwise mutual information in any forms. In addition, the exhaustive searches of all combinations of features are prerequisite for finding the optimal feature subsets for classifying these kinds of data sets. We show that our approach outperforms existing filter feature subset selection methods for most of the 24 selected benchmark data sets.

A Feature Selection Method for Large-Scale Network Traffic Classification Based on Spark

Directory of Open Access Journals (Sweden)

Yong Wang

2016-02-01

Full Text Available Currently, with the rapid increasing of data scales in network traffic classifications, how to select traffic features efficiently is becoming a big challenge. Although a number of traditional feature selection methods using the Hadoop-MapReduce framework have been proposed, the execution time was still unsatisfactory with numeral iterative computations during the processing. To address this issue, an efficient feature selection method for network traffic based on a new parallel computing framework called Spark is proposed in this paper. In our approach, the complete feature set is firstly preprocessed based on Fisher score, and a sequential forward search strategy is employed for subsets. The optimal feature subset is then selected using the continuous iterations of the Spark computing framework. The implementation demonstrates that, on the precondition of keeping the classification accuracy, our method reduces the time cost of modeling and classification, and improves the execution efficiency of feature selection significantly.

Cloud field classification based on textural features

Science.gov (United States)

Sengupta, Sailes Kumar

1989-01-01

An essential component in global climate research is accurate cloud cover and type determination. Of the two approaches to texture-based classification (statistical and textural), only the former is effective in the classification of natural scenes such as land, ocean, and atmosphere. In the statistical approach that was adopted, parameters characterizing the stochastic properties of the spatial distribution of grey levels in an image are estimated and then used as features for cloud classification. Two types of textural measures were used. One is based on the distribution of the grey level difference vector (GLDV), and the other on a set of textural features derived from the MaxMin cooccurrence matrix (MMCM). The GLDV method looks at the difference D of grey levels at pixels separated by a horizontal distance d and computes several statistics based on this distribution. These are then used as features in subsequent classification. The MaxMin tectural features on the other hand are based on the MMCM, a matrix whose (I,J)th entry give the relative frequency of occurrences of the grey level pair (I,J) that are consecutive and thresholded local extremes separated by a given pixel distance d. Textural measures are then computed based on this matrix in much the same manner as is done in texture computation using the grey level cooccurrence matrix. The database consists of 37 cloud field scenes from LANDSAT imagery using a near IR visible channel. The classification algorithm used is the well known Stepwise Discriminant Analysis. The overall accuracy was estimated by the percentage or correct classifications in each case. It turns out that both types of classifiers, at their best combination of features, and at any given spatial resolution give approximately the same classification accuracy. A neural network based classifier with a feed forward architecture and a back propagation training algorithm is used to increase the classification accuracy, using these two classes

An Accurate Integral Method for Vibration Signal Based on Feature Information Extraction

Directory of Open Access Journals (Sweden)

Yong Zhu

2015-01-01

Full Text Available After summarizing the advantages and disadvantages of current integral methods, a novel vibration signal integral method based on feature information extraction was proposed. This method took full advantage of the self-adaptive filter characteristic and waveform correction feature of ensemble empirical mode decomposition in dealing with nonlinear and nonstationary signals. This research merged the superiorities of kurtosis, mean square error, energy, and singular value decomposition on signal feature extraction. The values of the four indexes aforementioned were combined into a feature vector. Then, the connotative characteristic components in vibration signal were accurately extracted by Euclidean distance search, and the desired integral signals were precisely reconstructed. With this method, the interference problem of invalid signal such as trend item and noise which plague traditional methods is commendably solved. The great cumulative error from the traditional time-domain integral is effectively overcome. Moreover, the large low-frequency error from the traditional frequency-domain integral is successfully avoided. Comparing with the traditional integral methods, this method is outstanding at removing noise and retaining useful feature information and shows higher accuracy and superiority.

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

International Nuclear Information System (INIS)

Wang Xiaojia; Mao Qirong; Zhan Yongzhao

2008-01-01

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

A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos.

Science.gov (United States)

Aghamohammadi, Amirhossein; Ang, Mei Choo; A Sundararajan, Elankovan; Weng, Ng Kok; Mogharrebi, Marzieh; Banihashem, Seyed Yashar

2018-01-01

Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods.

Polarimetric SAR image classification based on discriminative dictionary learning model

Science.gov (United States)

Sang, Cheng Wei; Sun, Hong

2018-03-01

Polarimetric SAR (PolSAR) image classification is one of the important applications of PolSAR remote sensing. It is a difficult high-dimension nonlinear mapping problem, the sparse representations based on learning overcomplete dictionary have shown great potential to solve such problem. The overcomplete dictionary plays an important role in PolSAR image classification, however for PolSAR image complex scenes, features shared by different classes will weaken the discrimination of learned dictionary, so as to degrade classification performance. In this paper, we propose a novel overcomplete dictionary learning model to enhance the discrimination of dictionary. The learned overcomplete dictionary by the proposed model is more discriminative and very suitable for PolSAR classification.

Identify Beta-Hairpin Motifs with Quadratic Discriminant Algorithm Based on the Chemical Shifts.

Directory of Open Access Journals (Sweden)

Feng YongE

Full Text Available Successful prediction of the beta-hairpin motif will be helpful for understanding the of the fold recognition. Some algorithms have been proposed for the prediction of beta-hairpin motifs. However, the parameters used by these methods were primarily based on the amino acid sequences. Here, we proposed a novel model for predicting beta-hairpin structure based on the chemical shift. Firstly, we analyzed the statistical distribution of chemical shifts of six nuclei in not beta-hairpin and beta-hairpin motifs. Secondly, we used these chemical shifts as features combined with three algorithms to predict beta-hairpin structure. Finally, we achieved the best prediction, namely sensitivity of 92%, the specificity of 94% with 0.85 of Mathew's correlation coefficient using quadratic discriminant analysis algorithm, which is clearly superior to the same method for the prediction of beta-hairpin structure from 20 amino acid compositions in the three-fold cross-validation. Our finding showed that the chemical shift is an effective parameter for beta-hairpin prediction, suggesting the quadratic discriminant analysis is a powerful algorithm for the prediction of beta-hairpin.

Biased discriminant euclidean embedding for content-based image retrieval.

Science.gov (United States)

Bian, Wei; Tao, Dacheng

2010-02-01

With many potential multimedia applications, content-based image retrieval (CBIR) has recently gained more attention for image management and web search. A wide variety of relevance feedback (RF) algorithms have been developed in recent years to improve the performance of CBIR systems. These RF algorithms capture user's preferences and bridge the semantic gap. However, there is still a big room to further the RF performance, because the popular RF algorithms ignore the manifold structure of image low-level visual features. In this paper, we propose the biased discriminative Euclidean embedding (BDEE) which parameterises samples in the original high-dimensional ambient space to discover the intrinsic coordinate of image low-level visual features. BDEE precisely models both the intraclass geometry and interclass discrimination and never meets the undersampled problem. To consider unlabelled samples, a manifold regularization-based item is introduced and combined with BDEE to form the semi-supervised BDEE, or semi-BDEE for short. To justify the effectiveness of the proposed BDEE and semi-BDEE, we compare them against the conventional RF algorithms and show a significant improvement in terms of accuracy and stability based on a subset of the Corel image gallery.

Learning discriminant face descriptor.

Science.gov (United States)

Lei, Zhen; Pietikäinen, Matti; Li, Stan Z

2014-02-01

Local feature descriptor is an important module for face recognition and those like Gabor and local binary patterns (LBP) have proven effective face descriptors. Traditionally, the form of such local descriptors is predefined in a handcrafted way. In this paper, we propose a method to learn a discriminant face descriptor (DFD) in a data-driven way. The idea is to learn the most discriminant local features that minimize the difference of the features between images of the same person and maximize that between images from different people. In particular, we propose to enhance the discriminative ability of face representation in three aspects. First, the discriminant image filters are learned. Second, the optimal neighborhood sampling strategy is soft determined. Third, the dominant patterns are statistically constructed. Discriminative learning is incorporated to extract effective and robust features. We further apply the proposed method to the heterogeneous (cross-modality) face recognition problem and learn DFD in a coupled way (coupled DFD or C-DFD) to reduce the gap between features of heterogeneous face images to improve the performance of this challenging problem. Extensive experiments on FERET, CAS-PEAL-R1, LFW, and HFB face databases validate the effectiveness of the proposed DFD learning on both homogeneous and heterogeneous face recognition problems. The DFD improves POEM and LQP by about 4.5 percent on LFW database and the C-DFD enhances the heterogeneous face recognition performance of LBP by over 25 percent.

Regularized generalized eigen-decomposition with applications to sparse supervised feature extraction and sparse discriminant analysis

DEFF Research Database (Denmark)

Han, Xixuan; Clemmensen, Line Katrine Harder

2015-01-01

We propose a general technique for obtaining sparse solutions to generalized eigenvalue problems, and call it Regularized Generalized Eigen-Decomposition (RGED). For decades, Fisher's discriminant criterion has been applied in supervised feature extraction and discriminant analysis, and it is for...

Gene features selection for three-class disease classification via multiple orthogonal partial least square discriminant analysis and S-plot using microarray data.

Science.gov (United States)

Yang, Mingxing; Li, Xiumin; Li, Zhibin; Ou, Zhimin; Liu, Ming; Liu, Suhuan; Li, Xuejun; Yang, Shuyu

2013-01-01

DNA microarray analysis is characterized by obtaining a large number of gene variables from a small number of observations. Cluster analysis is widely used to analyze DNA microarray data to make classification and diagnosis of disease. Because there are so many irrelevant and insignificant genes in a dataset, a feature selection approach must be employed in data analysis. The performance of cluster analysis of this high-throughput data depends on whether the feature selection approach chooses the most relevant genes associated with disease classes. Here we proposed a new method using multiple Orthogonal Partial Least Squares-Discriminant Analysis (mOPLS-DA) models and S-plots to select the most relevant genes to conduct three-class disease classification and prediction. We tested our method using Golub's leukemia microarray data. For three classes with subtypes, we proposed hierarchical orthogonal partial least squares-discriminant analysis (OPLS-DA) models and S-plots to select features for two main classes and their subtypes. For three classes in parallel, we employed three OPLS-DA models and S-plots to choose marker genes for each class. The power of feature selection to classify and predict three-class disease was evaluated using cluster analysis. Further, the general performance of our method was tested using four public datasets and compared with those of four other feature selection methods. The results revealed that our method effectively selected the most relevant features for disease classification and prediction, and its performance was better than that of the other methods.

Discrimination method of large log-likelihood study in differential diagnosis of pulmonary diffuse mild micro-nodule

International Nuclear Information System (INIS)

Chen Budong; Ma Daqing; He Wen; Tang Hongqu; Qian Linxue; Zhou Ronglin

2001-01-01

Objective: To analyze HRCT and thin-slice CT scan findings in 150 patients with pulmonary diffuse mild micro-nodule, and to find the features with the purpose of identifying random micro-nodule, peri-lymphatic micro-nodule, and centrilobular micro-nodule. Methods: The useful features i 150 patients with pulmonary diffuse mild micro-nodule were translated into scores by means of discrimination method of large log-likelihood to identify the micro-nodular category. Results: The accuracy of diagnosis was 94.0% for random micro-nodule, 76.0% for peri-lymphatic micro-nodule, and 90.0% for centrilobular micro-nodule. Conclusion: HRCT and thin-slice CT scans were helpful in differential diagnosis of pulmonary diffuse mild micro-nodule. The discrimination method of large log-likelihood was propitious to diagnosis and differential diagnosis

Optimum filter-based discrimination of neutrons and gamma rays

International Nuclear Information System (INIS)

Amiri, Moslem; Prenosil, Vaclav; Cvachovec, Frantisek

2015-01-01

An optimum filter-based method for discrimination of neutrons and gamma-rays in a mixed radiation field is presented. The existing filter-based implementations of discriminators require sample pulse responses in advance of the experiment run to build the filter coefficients, which makes them less practical. Our novel technique creates the coefficients during the experiment and improves their quality gradually. Applied to several sets of mixed neutron and photon signals obtained through different digitizers using stilbene scintillator, this approach is analyzed and its discrimination quality is measured. (authors)

Optimal Feature Space Selection in Detecting Epileptic Seizure based on Recurrent Quantification Analysis and Genetic Algorithm

Directory of Open Access Journals (Sweden)

Saleh LAshkari

2016-06-01

Full Text Available Selecting optimal features based on nature of the phenomenon and high discriminant ability is very important in the data classification problems. Since it doesn't require any assumption about stationary condition and size of the signal and the noise in Recurrent Quantification Analysis (RQA, it may be useful for epileptic seizure Detection. In this study, RQA was used to discriminate ictal EEG from the normal EEG where optimal features selected by combination of algorithm genetic and Bayesian Classifier. Recurrence plots of hundred samples in each two categories were obtained with five distance norms in this study: Euclidean, Maximum, Minimum, Normalized and Fixed Norm. In order to choose optimal threshold for each norm, ten threshold of ε was generated and then the best feature space was selected by genetic algorithm in combination with a bayesian classifier. The results shown that proposed method is capable of discriminating the ictal EEG from the normal EEG where for Minimum norm and 0.1˂ε˂1, accuracy was 100%. In addition, the sensitivity of proposed framework to the ε and the distance norm parameters was low. The optimal feature presented in this study is Trans which it was selected in most feature spaces with high accuracy.

Automatic brain MR image denoising based on texture feature-based artificial neural networks.

Science.gov (United States)

Chang, Yu-Ning; Chang, Herng-Hua

2015-01-01

Noise is one of the main sources of quality deterioration not only for visual inspection but also in computerized processing in brain magnetic resonance (MR) image analysis such as tissue classification, segmentation and registration. Accordingly, noise removal in brain MR images is important for a wide variety of subsequent processing applications. However, most existing denoising algorithms require laborious tuning of parameters that are often sensitive to specific image features and textures. Automation of these parameters through artificial intelligence techniques will be highly beneficial. In the present study, an artificial neural network associated with image texture feature analysis is proposed to establish a predictable parameter model and automate the denoising procedure. In the proposed approach, a total of 83 image attributes were extracted based on four categories: 1) Basic image statistics. 2) Gray-level co-occurrence matrix (GLCM). 3) Gray-level run-length matrix (GLRLM) and 4) Tamura texture features. To obtain the ranking of discrimination in these texture features, a paired-samples t-test was applied to each individual image feature computed in every image. Subsequently, the sequential forward selection (SFS) method was used to select the best texture features according to the ranking of discrimination. The selected optimal features were further incorporated into a back propagation neural network to establish a predictable parameter model. A wide variety of MR images with various scenarios were adopted to evaluate the performance of the proposed framework. Experimental results indicated that this new automation system accurately predicted the bilateral filtering parameters and effectively removed the noise in a number of MR images. Comparing to the manually tuned filtering process, our approach not only produced better denoised results but also saved significant processing time.

New theory of discriminant analysis after R. Fisher advanced research by the feature selection method for microarray data

CERN Document Server

Shinmura, Shuichi

2016-01-01

This is the first book to compare eight LDFs by different types of datasets, such as Fisher’s iris data, medical data with collinearities, Swiss banknote data that is a linearly separable data (LSD), student pass/fail determination using student attributes, 18 pass/fail determinations using exam scores, Japanese automobile data, and six microarray datasets (the datasets) that are LSD. We developed the 100-fold cross-validation for the small sample method (Method 1) instead of the LOO method. We proposed a simple model selection procedure to choose the best model having minimum M2 and Revised IP-OLDF based on MNM criterion was found to be better than other M2s in the above datasets. We compared two statistical LDFs and six MP-based LDFs. Those were Fisher’s LDF, logistic regression, three SVMs, Revised IP-OLDF, and another two OLDFs. Only a hard-margin SVM (H-SVM) and Revised IP-OLDF could discriminate LSD theoretically (Problem 2). We solved the defect of the generalized inverse matrices (Problem 3). For ...

A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos

Science.gov (United States)

2018-01-01

Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods. PMID:29438421

Automatic target recognition using a feature-based optical neural network

Science.gov (United States)

Chao, Tien-Hsin

1992-01-01

An optical neural network based upon the Neocognitron paradigm (K. Fukushima et al. 1983) is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstration of a two-layer neural network for space objects discrimination is also presented.

Fashion Evaluation Method for Clothing Recommendation Based on Weak Appearance Feature

Directory of Open Access Journals (Sweden)

Yan Zhang

2017-01-01

Full Text Available With the rapid rising of living standard, people gradually developed higher shopping enthusiasm and increasing demand for garment. Nowadays, an increasing number of people pursue fashion. However, facing too many types of garment, consumers need to try them on repeatedly, which is somewhat time- and energy-consuming. Besides, it is difficult for merchants to master the real-time demand of consumers. Herein, there is not enough cohesiveness between consumer information and merchants. Thus, a novel fashion evaluation method on the basis of the appearance weak feature is proposed in this paper. First of all, image database is established and three aspects of appearance weak feature are put forward to characterize the fashion level. Furthermore, the appearance weak features are extracted according to the characters’ facial feature localization method. Last but not least, consumers’ fashion level can be classified through support vector product, and the classification is verified with the hierarchical analysis method. The experimental results show that consumers’ fashion level can be accurately described based on the indexes of appearance weak feature and the approach has higher application value for the clothing recommendation system.

Weighted Discriminative Dictionary Learning based on Low-rank Representation

International Nuclear Information System (INIS)

Chang, Heyou; Zheng, Hao

2017-01-01

Low-rank representation has been widely used in the field of pattern classification, especially when both training and testing images are corrupted with large noise. Dictionary plays an important role in low-rank representation. With respect to the semantic dictionary, the optimal representation matrix should be block-diagonal. However, traditional low-rank representation based dictionary learning methods cannot effectively exploit the discriminative information between data and dictionary. To address this problem, this paper proposed weighted discriminative dictionary learning based on low-rank representation, where a weighted representation regularization term is constructed. The regularization associates label information of both training samples and dictionary atoms, and encourages to generate a discriminative representation with class-wise block-diagonal structure, which can further improve the classification performance where both training and testing images are corrupted with large noise. Experimental results demonstrate advantages of the proposed method over the state-of-the-art methods. (paper)

Simultaneous and Sequential Feature Negative Discriminations: Elemental Learning and Occasion Setting in Human Pavlovian Conditioning

Science.gov (United States)

Baeyens, Frank; Vervliet, Bram; Vansteenwegen, Debora; Beckers, Tom; Hermans, Dirk; Eelen, Paul

2004-01-01

Using a conditioned suppression task, we investigated simultaneous (XA-/A+) vs. sequential (X [right arrow] A-/A+) Feature Negative (FN) discrimination learning in humans. We expected the simultaneous discrimination to result in X (or alternatively the XA configuration) becoming an inhibitor acting directly on the US, and the sequential…

Fluid discrimination based on rock physics templates

International Nuclear Information System (INIS)

Liu, Qian; Yin, Xingyao; Li, Chao

2015-01-01

Reservoir fluid discrimination is an indispensable part of seismic exploration. Reliable fluid discrimination helps to decrease the risk of exploration and to increase the success ratio of drilling. There are many kinds of fluid indicators that are used in fluid discriminations, most of which are single indicators. But single indicators do not always work well under complicated reservoir conditions. Therefore, combined fluid indicators are needed to increase accuracies of discriminations. In this paper, we have proposed an alternative strategy for the combination of fluid indicators. An alternative fluid indicator, the rock physics template-based indicator (RPTI) has been derived to combine the advantages of two single indicators. The RPTI is more sensitive to the contents of fluid than traditional indicators. The combination is implemented based on the characteristic of the fluid trend in the rock physics template, which means few subjective factors are involved. We also propose an inversion method to assure the accuracy of the RPTI input data. The RPTI profile is an intuitionistic interpretation of fluid content. Real data tests demonstrate the applicability and validity. (paper)

Two-Level Evaluation on Sensor Interoperability of Features in Fingerprint Image Segmentation

Directory of Open Access Journals (Sweden)

Ya-Shuo Li

2012-03-01

Full Text Available Features used in fingerprint segmentation significantly affect the segmentation performance. Various features exhibit different discriminating abilities on fingerprint images derived from different sensors. One feature which has better discriminating ability on images derived from a certain sensor may not adapt to segment images derived from other sensors. This degrades the segmentation performance. This paper empirically analyzes the sensor interoperability problem of segmentation feature, which refers to the feature’s ability to adapt to the raw fingerprints captured by different sensors. To address this issue, this paper presents a two-level feature evaluation method, including the first level feature evaluation based on segmentation error rate and the second level feature evaluation based on decision tree. The proposed method is performed on a number of fingerprint databases which are obtained from various sensors. Experimental results show that the proposed method can effectively evaluate the sensor interoperability of features, and the features with good evaluation results acquire better segmentation accuracies of images originating from different sensors.

A Two-Dimensional Solar Tracking Stationary Guidance Method Based on Feature-Based Time Series

Directory of Open Access Journals (Sweden)

Keke Zhang

2018-01-01

Full Text Available The amount of satellite energy acquired has a direct impact on operational capacities of the satellite. As for practical high functional density microsatellites, solar tracking guidance design of solar panels plays an extremely important role. Targeted at stationary tracking problems incurred in a new system that utilizes panels mounted in the two-dimensional turntable to acquire energies to the greatest extent, a two-dimensional solar tracking stationary guidance method based on feature-based time series was proposed under the constraint of limited satellite attitude coupling control capability. By analyzing solar vector variation characteristics within an orbit period and solar vector changes within the whole life cycle, such a method could be adopted to establish a two-dimensional solar tracking guidance model based on the feature-based time series to realize automatic switching of feature-based time series and stationary guidance under the circumstance of different β angles and the maximum angular velocity control, which was applicable to near-earth orbits of all orbital inclination. It was employed to design a two-dimensional solar tracking stationary guidance system, and a mathematical simulation for guidance performance was carried out in diverse conditions under the background of in-orbit application. The simulation results show that the solar tracking accuracy of two-dimensional stationary guidance reaches 10∘ and below under the integrated constraints, which meet engineering application requirements.

Discrimination of single features and conjunctions by children.

Science.gov (United States)

Taylor, M J; Chevalier, H; Lobaugh, N J

2003-12-01

Stimuli that are discriminated by a conjunction of features can show more rapid early processing in adults. To determine how this facilitation effect develops, the processing of visual features and their conjunction was examined in 7-12-year-old children. The children completed a series of tasks in which they made a target-non-target judgement as a function of shape only, colour only or shape and colour features, while event-related potentials were recorded. To assess early stages of feature processing the posteriorly distributed P1 and N1 were analysed. Attentional effects were seen for both components. P1 had a shorter latency and P1 and N1 had larger amplitudes to targets than non-targets. Task effects were driven by the conjunction task. P1 amplitude was largest, while N1 amplitude was smallest for the conjunction targets. In contrast to larger left-sided N1 in adults, N1 had a symmetrical distribution in the children. N1 latency was shortest for the conjunction targets in the 9-10-year olds and 11-12-year olds, demonstrating facilitation in children, but which continued to develop over the pre-teen years. These data underline the sensitivity of early stages of processing to both top-down modulations and the parallel binding of non-spatial features in young children. Furthermore, facilitation effects, increased speed of processing when features need to be conjoined, mature in mid-childhood, arguing against a hierarchical model of visual processing, and supporting a rapid, integrated facilitative model.

Investigation on n/γ discrimination methods for liquid scintillator detector

International Nuclear Information System (INIS)

Li Kuinian; Li Yang; Zhang Mei; Zhang Zhongbing; Li Binkang; Zhang Xiaodong; Liu Jun; Zhang Xianpeng

2014-01-01

To obtain the n/γ discrimination ability of different digital pulse shape discrimination methods, four methods (rising time method, charge comparison method, pulse gradient analysis and frequency gradient analysis) in americium-beryllium mixed radiation fields were demonstrated. The signals from EJ-301 and BC501A scintillator detectors were digitized using oscilloscope. A comparison was taken among the four discrimination methods. The discrimination results of the four methods in liquid scintillator detectors show that the rising time method is the best and it provides a good choice in real-time n/γ discrimination system. (authors)

Spike detection, characterization, and discrimination using feature analysis software written in LabVIEW.

Science.gov (United States)

Stewart, C M; Newlands, S D; Perachio, A A

2004-12-01

Rapid and accurate discrimination of single units from extracellular recordings is a fundamental process for the analysis and interpretation of electrophysiological recordings. We present an algorithm that performs detection, characterization, discrimination, and analysis of action potentials from extracellular recording sessions. The program was entirely written in LabVIEW (National Instruments), and requires no external hardware devices or a priori information about action potential shapes. Waveform events are detected by scanning the digital record for voltages that exceed a user-adjustable trigger. Detected events are characterized to determine nine different time and voltage levels for each event. Various algebraic combinations of these waveform features are used as axis choices for 2-D Cartesian plots of events. The user selects axis choices that generate distinct clusters. Multiple clusters may be defined as action potentials by manually generating boundaries of arbitrary shape. Events defined as action potentials are validated by visual inspection of overlain waveforms. Stimulus-response relationships may be identified by selecting any recorded channel for comparison to continuous and average cycle histograms of binned unit data. The algorithm includes novel aspects of feature analysis and acquisition, including higher acquisition rates for electrophysiological data compared to other channels. The program confirms that electrophysiological data may be discriminated with high-speed and efficiency using algebraic combinations of waveform features derived from high-speed digital records.

Research on the Diagnosis of Rotor Coupling Fault Based on Wavelet Packet and Local Fisher Discriminant

Directory of Open Access Journals (Sweden)

Guangbin Wang

2014-09-01

Full Text Available this article is for the coupling fault diagnosis of rotor system, and does in-depth analysis of the rotor unbalance and misalignment, and the fault formed by the coupling of these two. Through research, Rotor Coupling was found filled with rich features. In this paper, Wavelet packet de- noising ideas being introduced to the local Fisher discriminant analysis (LFDA, a new method of fault diagnosis based on Wavelet Packet and Local Fisher Discriminant is proposed. The technology of information fusion is applied to the data processing with coupling faults. By comparing and analyzing the algorithms effect of LE, LPP, FDA, LFDA and IOLFA through experiment, it shows that LE and LPP are unable to identify the fault, while FDA, LFDA has better identification, and Wavelet Packet and Local Fisher discriminant has the best effect.

Discriminability and dimensionality effects in visual search for featural conjunctions: a functional pop-out.

Science.gov (United States)

Dehaene, S

1989-07-01

Treisman and Gelade's (1980) feature-integration theory of attention states that a scene must be serially scanned before the objects in it can be accurately perceived. Is serial scanning compatible with the speed observed in the perception of real-world scenes? Most real scenes consist of many more dimensions (color, size, shape, depth, etc.) than those generally found in search paradigms. Furthermore, real objects differ from each other along many of these dimensions. The present experiment assessed the influence of the total number of dimensions and target/distractor discriminability (the number of dimensions that suffice to separate a target from distractors) on search times for a conjunction of features. Search was always found to be serial. However, for the most discriminable targets, search rate was so fast that search times were in the same range as pop-out detection times. Apparently, greater discriminability enables subjects to direct attention at a faster rate and at only a fraction of the items in a scene.

Pulse shape discrimination and classification methods for continuous depth of interaction encoding PET detectors

International Nuclear Information System (INIS)

Roncali, Emilie; Phipps, Jennifer E; Marcu, Laura; Cherry, Simon R

2012-01-01

In previous work we demonstrated the potential of positron emission tomography (PET) detectors with depth-of-interaction (DOI) encoding capability based on phosphor-coated crystals. A DOI resolution of 8 mm full-width at half-maximum was obtained for 20 mm long scintillator crystals using a delayed charge integration linear regression method (DCI-LR). Phosphor-coated crystals modify the pulse shape to allow continuous DOI information determination, but the relationship between pulse shape and DOI is complex. We are therefore interested in developing a sensitive and robust method to estimate the DOI. Here, linear discriminant analysis (LDA) was implemented to classify the events based on information extracted from the pulse shape. Pulses were acquired with 2×2×20 mm 3 phosphor-coated crystals at five irradiation depths and characterized by their DCI values or Laguerre coefficients. These coefficients were obtained by expanding the pulses on a Laguerre basis set and constituted a unique signature for each pulse. The DOI of individual events was predicted using LDA based on Laguerre coefficients (Laguerre-LDA) or DCI values (DCI-LDA) as discriminant features. Predicted DOIs were compared to true irradiation depths. Laguerre-LDA showed higher sensitivity and accuracy than DCI-LDA and DCI-LR and was also more robust to predict the DOI of pulses with higher statistical noise due to low light levels (interaction depths further from the photodetector face). This indicates that Laguerre-LDA may be more suitable to DOI estimation in smaller crystals where lower collected light levels are expected. This novel approach is promising for calculating DOI using pulse shape discrimination in single-ended readout depth-encoding PET detectors. (paper)

Discrimination of nitrogen fertilizer levels of tea plant (Camellia sinensis) based on hyperspectral imaging.

Science.gov (United States)

Wang, Yujie; Hu, Xin; Hou, Zhiwei; Ning, Jingming; Zhang, Zhengzhu

2018-04-01

Nitrogen (N) fertilizer plays an important role in tea plantation management, with significant impacts on the photosynthetic capacity, productivity and nutrition status of tea plants. The present study aimed to establish a method for the discrimination of N fertilizer levels using hyperspectral imaging technique. Spectral data were extracted from the region of interest, followed by the first derivative to reduce background noise. Five optimal wavelengths were selected by principal component analysis. Texture features were extracted from the images at optimal wavelengths by gray-level gradient co-occurrence matrix. Support vector machine (SVM) and extreme learning machine were used to build classification models based on spectral data, optimal wavelengths, texture features and data fusion, respectively. The SVM model using fused data gave the best performance with highest correct classification rate of 100% for prediction set. The overall results indicated that visible and near-infrared hyperspectral imaging combined with SVM were effective in discriminating N fertilizer levels of tea plants. © 2018 Society of Chemical Industry. © 2018 Society of Chemical Industry.

Prototype selection based on FCM and its application in discrimination between nuclear explosion and earthquake

International Nuclear Information System (INIS)

Han Shaoqing; Li Xihai; Song Zibiao; Liu Daizhi

2007-01-01

The synergetic pattern recognition is a new way of pattern recognition with many excellent features such as noise resistance and deformity resistance. But when it is used in the discrimination between nuclear explosion and earthquake using existing methods of prototype selection, the results are not satisfying. A new method of prototype selection based on FCM is proposed in this paper. First, each group of training samples is clustered into c groups using FCM; then c barycenters or centers are chosen as prototypes. Experiment results show that compared with existing methods of prototype selection this new method is effective and it increases the recognition ratio greatly. (authors)

Multi-class parkinsonian disorders classification with quantitative MR markers and graph-based features using support vector machines.

Science.gov (United States)

Morisi, Rita; Manners, David Neil; Gnecco, Giorgio; Lanconelli, Nico; Testa, Claudia; Evangelisti, Stefania; Talozzi, Lia; Gramegna, Laura Ludovica; Bianchini, Claudio; Calandra-Buonaura, Giovanna; Sambati, Luisa; Giannini, Giulia; Cortelli, Pietro; Tonon, Caterina; Lodi, Raffaele

2018-02-01

In this study we attempt to automatically classify individual patients with different parkinsonian disorders, making use of pattern recognition techniques to distinguish among several forms of parkinsonisms (multi-class classification), based on a set of binary classifiers that discriminate each disorder from all others. We combine diffusion tensor imaging, proton spectroscopy and morphometric-volumetric data to obtain MR quantitative markers, which are provided to support vector machines with the aim of recognizing the different parkinsonian disorders. Feature selection is used to find the most important features for classification. We also exploit a graph-based technique on the set of quantitative markers to extract additional features from the dataset, and increase classification accuracy. When graph-based features are not used, the MR markers that are most frequently automatically extracted by the feature selection procedure reflect alterations in brain regions that are also usually considered to discriminate parkinsonisms in routine clinical practice. Graph-derived features typically increase the diagnostic accuracy, and reduce the number of features required. The results obtained in the work demonstrate that support vector machines applied to multimodal brain MR imaging and using graph-based features represent a novel and highly accurate approach to discriminate parkinsonisms, and a useful tool to assist the diagnosis. Copyright © 2017 Elsevier Ltd. All rights reserved.

Secondary iris recognition method based on local energy-orientation feature

Science.gov (United States)

Huo, Guang; Liu, Yuanning; Zhu, Xiaodong; Dong, Hongxing

2015-01-01

This paper proposes a secondary iris recognition based on local features. The application of the energy-orientation feature (EOF) by two-dimensional Gabor filter to the extraction of the iris goes before the first recognition by the threshold of similarity, which sets the whole iris database into two categories-a correctly recognized class and a class to be recognized. Therefore, the former are accepted and the latter are transformed by histogram to achieve an energy-orientation histogram feature (EOHF), which is followed by a second recognition with the chi-square distance. The experiment has proved that the proposed method, because of its higher correct recognition rate, could be designated as the most efficient and effective among its companion studies in iris recognition algorithms.

Subsidence feature discrimination using deep convolutional neral networks in synthetic aperture radar imagery

CSIR Research Space (South Africa)

Schwegmann, Colin P

2017-07-01

Full Text Available International Geoscience and Remote Sensing Symposium (IGARSS), 23-28 July 2017, Fort Worth, TX, USA SUBSIDENCE FEATURE DISCRIMINATION USING DEEP CONVOLUTIONAL NEURAL NETWORKS IN SYNTHETIC APERTURE RADAR IMAGERY Schwegmann, Colin P Kleynhans, Waldo...

Discriminative Projection Selection Based Face Image Hashing

Science.gov (United States)

Karabat, Cagatay; Erdogan, Hakan

Face image hashing is an emerging method used in biometric verification systems. In this paper, we propose a novel face image hashing method based on a new technique called discriminative projection selection. We apply the Fisher criterion for selecting the rows of a random projection matrix in a user-dependent fashion. Moreover, another contribution of this paper is to employ a bimodal Gaussian mixture model at the quantization step. Our simulation results on three different databases demonstrate that the proposed method has superior performance in comparison to previously proposed random projection based methods.

Fast Depiction Invariant Visual Similarity for Content Based Image Retrieval Based on Data-driven Visual Similarity using Linear Discriminant Analysis

Science.gov (United States)

Wihardi, Y.; Setiawan, W.; Nugraha, E.

2018-01-01

On this research we try to build CBIRS based on Learning Distance/Similarity Function using Linear Discriminant Analysis (LDA) and Histogram of Oriented Gradient (HoG) feature. Our method is invariant to depiction of image, such as similarity of image to image, sketch to image, and painting to image. LDA can decrease execution time compared to state of the art method, but it still needs an improvement in term of accuracy. Inaccuracy in our experiment happen because we did not perform sliding windows search and because of low number of negative samples as natural-world images.

Comparing writing style feature-based classification methods for estimating user reputations in social media.

Science.gov (United States)

Suh, Jong Hwan

2016-01-01

In recent years, the anonymous nature of the Internet has made it difficult to detect manipulated user reputations in social media, as well as to ensure the qualities of users and their posts. To deal with this, this study designs and examines an automatic approach that adopts writing style features to estimate user reputations in social media. Under varying ways of defining Good and Bad classes of user reputations based on the collected data, it evaluates the classification performance of the state-of-art methods: four writing style features, i.e. lexical, syntactic, structural, and content-specific, and eight classification techniques, i.e. four base learners-C4.5, Neural Network (NN), Support Vector Machine (SVM), and Naïve Bayes (NB)-and four Random Subspace (RS) ensemble methods based on the four base learners. When South Korea's Web forum, Daum Agora, was selected as a test bed, the experimental results show that the configuration of the full feature set containing content-specific features and RS-SVM combining RS and SVM gives the best accuracy for classification if the test bed poster reputations are segmented strictly into Good and Bad classes by portfolio approach. Pairwise t tests on accuracy confirm two expectations coming from the literature reviews: first, the feature set adding content-specific features outperform the others; second, ensemble learning methods are more viable than base learners. Moreover, among the four ways on defining the classes of user reputations, i.e. like, dislike, sum, and portfolio, the results show that the portfolio approach gives the highest accuracy.

Towards automated discrimination of lipids versus peptides from full scan mass spectra

Directory of Open Access Journals (Sweden)

Piotr Dittwald

2014-09-01

Full Text Available Although physicochemical fractionation techniques play a crucial role in the analysis of complex mixtures, they are not necessarily the best solution to separate specific molecular classes, such as lipids and peptides. Any physical fractionation step such as, for example, those based on liquid chromatography, will introduce its own variation and noise. In this paper we investigate to what extent the high sensitivity and resolution of contemporary mass spectrometers offers viable opportunities for computational separation of signals in full scan spectra. We introduce an automatic method that can discriminate peptide from lipid peaks in full scan mass spectra, based on their isotopic properties. We systematically evaluate which features maximally contribute to a peptide versus lipid classification. The selected features are subsequently used to build a random forest classifier that enables almost perfect separation between lipid and peptide signals without requiring ion fragmentation and classical tandem MS-based identification approaches. The classifier is trained on in silico data, but is also capable of discriminating signals in real world experiments. We evaluate the influence of typical data inaccuracies of common classes of mass spectrometry instruments on the optimal set of discriminant features. Finally, the method is successfully extended towards the classification of individual lipid classes from full scan mass spectral features, based on input data defined by the Lipid Maps Consortium.

A Time-Walk Correction Method for PET Detectors Based on Leading Edge Discriminators.

Science.gov (United States)

Du, Junwei; Schmall, Jeffrey P; Judenhofer, Martin S; Di, Kun; Yang, Yongfeng; Cherry, Simon R

2017-09-01

The leading edge timing pick-off technique is the simplest timing extraction method for PET detectors. Due to the inherent time-walk of the leading edge technique, corrections should be made to improve timing resolution, especially for time-of-flight PET. Time-walk correction can be done by utilizing the relationship between the threshold crossing time and the event energy on an event by event basis. In this paper, a time-walk correction method is proposed and evaluated using timing information from two identical detectors both using leading edge discriminators. This differs from other techniques that use an external dedicated reference detector, such as a fast PMT-based detector using constant fraction techniques to pick-off timing information. In our proposed method, one detector was used as reference detector to correct the time-walk of the other detector. Time-walk in the reference detector was minimized by using events within a small energy window (508.5 - 513.5 keV). To validate this method, a coincidence detector pair was assembled using two SensL MicroFB SiPMs and two 2.5 mm × 2.5 mm × 20 mm polished LYSO crystals. Coincidence timing resolutions using different time pick-off techniques were obtained at a bias voltage of 27.5 V and a fixed temperature of 20 °C. The coincidence timing resolution without time-walk correction were 389.0 ± 12.0 ps (425 -650 keV energy window) and 670.2 ± 16.2 ps (250-750 keV energy window). The timing resolution with time-walk correction improved to 367.3 ± 0.5 ps (425 - 650 keV) and 413.7 ± 0.9 ps (250 - 750 keV). For comparison, timing resolutions were 442.8 ± 12.8 ps (425 - 650 keV) and 476.0 ± 13.0 ps (250 - 750 keV) using constant fraction techniques, and 367.3 ± 0.4 ps (425 - 650 keV) and 413.4 ± 0.9 ps (250 - 750 keV) using a reference detector based on the constant fraction technique. These results show that the proposed leading edge based time-walk correction method works well. Timing resolution obtained

Subject-based feature extraction by using fisher WPD-CSP in brain-computer interfaces.

Science.gov (United States)

Yang, Banghua; Li, Huarong; Wang, Qian; Zhang, Yunyuan

2016-06-01

Feature extraction of electroencephalogram (EEG) plays a vital role in brain-computer interfaces (BCIs). In recent years, common spatial pattern (CSP) has been proven to be an effective feature extraction method. However, the traditional CSP has disadvantages of requiring a lot of input channels and the lack of frequency information. In order to remedy the defects of CSP, wavelet packet decomposition (WPD) and CSP are combined to extract effective features. But WPD-CSP method considers less about extracting specific features that are fitted for the specific subject. So a subject-based feature extraction method using fisher WPD-CSP is proposed in this paper. The idea of proposed method is to adapt fisher WPD-CSP to each subject separately. It mainly includes the following six steps: (1) original EEG signals from all channels are decomposed into a series of sub-bands using WPD; (2) average power values of obtained sub-bands are computed; (3) the specified sub-bands with larger values of fisher distance according to average power are selected for that particular subject; (4) each selected sub-band is reconstructed to be regarded as a new EEG channel; (5) all new EEG channels are used as input of the CSP and a six-dimensional feature vector is obtained by the CSP. The subject-based feature extraction model is so formed; (6) the probabilistic neural network (PNN) is used as the classifier and the classification accuracy is obtained. Data from six subjects are processed by the subject-based fisher WPD-CSP, the non-subject-based fisher WPD-CSP and WPD-CSP, respectively. Compared with non-subject-based fisher WPD-CSP and WPD-CSP, the results show that the proposed method yields better performance (sensitivity: 88.7±0.9%, and specificity: 91±1%) and the classification accuracy from subject-based fisher WPD-CSP is increased by 6-12% and 14%, respectively. The proposed subject-based fisher WPD-CSP method can not only remedy disadvantages of CSP by WPD but also discriminate

Classification of Carotid Plaque Echogenicity by Combining Texture Features and Morphologic Characteristics.

Science.gov (United States)

Huang, Xiaowei; Zhang, Yanling; Qian, Ming; Meng, Long; Xiao, Yang; Niu, Lili; Zheng, Rongqin; Zheng, Hairong

2016-10-01

Anechoic carotid plaques on sonography have been used to predict future cardiovascular or cerebrovascular events. The purpose of this study was to investigate whether carotid plaque echogenicity could be assessed objectively by combining texture features extracted by MaZda software (Institute of Electronics, Technical University of Lodz, Lodz, Poland) and morphologic characteristics, which may provide a promising method for early prediction of acute cardiovascular disease. A total of 268 plaque images were collected from 136 volunteers and classified into 85 hyperechoic, 83 intermediate, and 100 anechoic plaques. About 300 texture features were extracted from histogram, absolute gradient, run-length matrix, gray-level co-occurrence matrix, autoregressive model, and wavelet transform algorithms by MaZda. The morphologic characteristics, including degree of stenosis, maximum plaque intima-media thickness, and maximum plaque length, were measured by B-mode sonography. Statistically significant features were selected by analysis of covariance. The most discriminative features were obtained from statistically significant features by linear discriminant analysis. The K-nearest neighbor classifier was used to classify plaque echogenicity based on statistically significant and most discriminative features. A total of 30 statistically significant features were selected among the plaques, and 2 most discriminative features were obtained from the statistically significant features. The classification accuracy rates for 3 types of plaques based on statistically significant and most discriminative features were 72.03% (κ= 0.571; P MaZda and morphologic characteristics.

Using discrete wavelet transform features to discriminate between noise and phases in seismic waveforms

Science.gov (United States)

Forrest, R.; Ray, J.; Hansen, C. W.

2017-12-01

Currently, simple polarization metrics such as the horizontal-to-vertical ratio are used to discriminate between noise and various phases in three-component seismic waveform data collected at regional distances. Accurately establishing the identity and arrival of these waves in adverse signal-to-noise environments is helpful in detecting and locating the seismic events. In this work, we explore the use of multiresolution decompositions to discriminate between noise and event arrivals. A segment of the waveform lying inside a time-window that spans the coda of an arrival is subjected to a discrete wavelet decomposition. Multi-resolution classification features as well as statistical tests are derived from these wavelet decomposition quantities to quantify their discriminating power. Furthermore, we move to streaming data and address the problem of false positives by introducing ensembles of classifiers. We describe in detail results of these methods tuned from data obtained from Coronel Fontana, Argentina (CFAA), as well as Stephens Creek, Australia (STKA). Acknowledgement: Sandia National Laboratories is a multi-mission laboratory managed and operated by National Technology and Engineering Solutions of Sandia, LLC., a wholly owned subsidiary of Honeywell International, Inc., for the U.S. Department of Energy's National Nuclear Security Administration under contract DE-NA-0003525.

Discrete Biogeography Based Optimization for Feature Selection in Molecular Signatures.

Science.gov (United States)

Liu, Bo; Tian, Meihong; Zhang, Chunhua; Li, Xiangtao

2015-04-01

Biomarker discovery from high-dimensional data is a complex task in the development of efficient cancer diagnoses and classification. However, these data are usually redundant and noisy, and only a subset of them present distinct profiles for different classes of samples. Thus, selecting high discriminative genes from gene expression data has become increasingly interesting in the field of bioinformatics. In this paper, a discrete biogeography based optimization is proposed to select the good subset of informative gene relevant to the classification. In the proposed algorithm, firstly, the fisher-markov selector is used to choose fixed number of gene data. Secondly, to make biogeography based optimization suitable for the feature selection problem; discrete migration model and discrete mutation model are proposed to balance the exploration and exploitation ability. Then, discrete biogeography based optimization, as we called DBBO, is proposed by integrating discrete migration model and discrete mutation model. Finally, the DBBO method is used for feature selection, and three classifiers are used as the classifier with the 10 fold cross-validation method. In order to show the effective and efficiency of the algorithm, the proposed algorithm is tested on four breast cancer dataset benchmarks. Comparison with genetic algorithm, particle swarm optimization, differential evolution algorithm and hybrid biogeography based optimization, experimental results demonstrate that the proposed method is better or at least comparable with previous method from literature when considering the quality of the solutions obtained. © 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN.

Science.gov (United States)

Guo, Hao; Wu, Danni; An, Jubai

2017-08-09

Oil slicks and lookalikes (e.g., plant oil and oil emulsion) all appear as dark areas in polarimetric Synthetic Aperture Radar (SAR) images and are highly heterogeneous, so it is very difficult to use a single feature that can allow classification of dark objects in polarimetric SAR images as oil slicks or lookalikes. We established multi-feature fusion to support the discrimination of oil slicks and lookalikes. In the paper, simple discrimination analysis is used to rationalize a preferred features subset. The features analyzed include entropy, alpha, and Single-bounce Eigenvalue Relative Difference (SERD) in the C-band polarimetric mode. We also propose a novel SAR image discrimination method for oil slicks and lookalikes based on Convolutional Neural Network (CNN). The regions of interest are selected as the training and testing samples for CNN on the three kinds of polarimetric feature images. The proposed method is applied to a training data set of 5400 samples, including 1800 crude oil, 1800 plant oil, and 1800 oil emulsion samples. In the end, the effectiveness of the method is demonstrated through the analysis of some experimental results. The classification accuracy obtained using 900 samples of test data is 91.33%. It is here observed that the proposed method not only can accurately identify the dark spots on SAR images but also verify the ability of the proposed algorithm to classify unstructured features.

Material Discrimination Based on K-edge Characteristics

Directory of Open Access Journals (Sweden)

Peng He

2013-01-01

Full Text Available Spectral/multienergy CT employing the state-of-the-art energy-discriminative photon-counting detector can identify absorption features in the multiple ranges of photon energies and has the potential to distinguish different materials based on K-edge characteristics. K-edge characteristics involve the sudden attenuation increase in the attenuation profile of a relatively high atomic number material. Hence, spectral CT can utilize material K-edge characteristics (sudden attenuation increase to capture images in available energy bins (levels/windows to distinguish different material components. In this paper, we propose an imaging model based on K-edge characteristics for maximum material discrimination with spectral CT. The wider the energy bin width is, the lower the noise level is, but the poorer the reconstructed image contrast is. Here, we introduce the contrast-to-noise ratio (CNR criterion to optimize the energy bin width after the K-edge jump for the maximum CNR. In the simulation, we analyze the reconstructed image quality in different energy bins and demonstrate that our proposed optimization approach can maximize CNR between target region and background region in reconstructed image.

Robust infrared target tracking using discriminative and generative approaches

Science.gov (United States)

Asha, C. S.; Narasimhadhan, A. V.

2017-09-01

The process of designing an efficient tracker for thermal infrared imagery is one of the most challenging tasks in computer vision. Although a lot of advancement has been achieved in RGB videos over the decades, textureless and colorless properties of objects in thermal imagery pose hard constraints in the design of an efficient tracker. Tracking of an object using a single feature or a technique often fails to achieve greater accuracy. Here, we propose an effective method to track an object in infrared imagery based on a combination of discriminative and generative approaches. The discriminative technique makes use of two complementary methods such as kernelized correlation filter with spatial feature and AdaBoost classifier with pixel intesity features to operate in parallel. After obtaining optimized locations through discriminative approaches, the generative technique is applied to determine the best target location using a linear search method. Unlike the baseline algorithms, the proposed method estimates the scale of the target by Lucas-Kanade homography estimation. To evaluate the proposed method, extensive experiments are conducted on 17 challenging infrared image sequences obtained from LTIR dataset and a significant improvement of mean distance precision and mean overlap precision is accomplished as compared with the existing trackers. Further, a quantitative and qualitative assessment of the proposed approach with the state-of-the-art trackers is illustrated to clearly demonstrate an overall increase in performance.

SPEECH EMOTION RECOGNITION USING MODIFIED QUADRATIC DISCRIMINATION FUNCTION

Institute of Scientific and Technical Information of China (English)

无

2008-01-01

Quadratic Discrimination Function(QDF)is commonly used in speech emotion recognition,which proceeds on the premise that the input data is normal distribution.In this Paper,we propose a transformation to normalize the emotional features,then derivate a Modified QDF(MQDF) to speech emotion recognition.Features based on prosody and voice quality are extracted and Principal Component Analysis Neural Network (PCANN) is used to reduce dimension of the feature vectors.The results show that voice quality features are effective supplement for recognition.and the method in this paper could improve the recognition ratio effectively.

Atypical pattern of discriminating sound features in adults with Asperger syndrome as reflected by the mismatch negativity.

Science.gov (United States)

Kujala, T; Aho, E; Lepistö, T; Jansson-Verkasalo, E; Nieminen-von Wendt, T; von Wendt, L; Näätänen, R

2007-04-01

Asperger syndrome, which belongs to the autistic spectrum of disorders, is characterized by deficits of social interaction and abnormal perception, like hypo- or hypersensitivity in reacting to sounds and discriminating certain sound features. We determined auditory feature discrimination in adults with Asperger syndrome with the mismatch negativity (MMN), a neural response which is an index of cortical change detection. We recorded MMN for five different sound features (duration, frequency, intensity, location, and gap). Our results suggest hypersensitive auditory change detection in Asperger syndrome, as reflected in the enhanced MMN for deviant sounds with a gap or shorter duration, and speeded MMN elicitation for frequency changes.

Deep Salient Feature Based Anti-Noise Transfer Network for Scene Classification of Remote Sensing Imagery

Directory of Open Access Journals (Sweden)

Xi Gong

2018-03-01

Full Text Available Remote sensing (RS scene classification is important for RS imagery semantic interpretation. Although tremendous strides have been made in RS scene classification, one of the remaining open challenges is recognizing RS scenes in low quality variance (e.g., various scales and noises. This paper proposes a deep salient feature based anti-noise transfer network (DSFATN method that effectively enhances and explores the high-level features for RS scene classification in different scales and noise conditions. In DSFATN, a novel discriminative deep salient feature (DSF is introduced by saliency-guided DSF extraction, which conducts a patch-based visual saliency (PBVS algorithm using “visual attention” mechanisms to guide pre-trained CNNs for producing the discriminative high-level features. Then, an anti-noise network is proposed to learn and enhance the robust and anti-noise structure information of RS scene by directly propagating the label information to fully-connected layers. A joint loss is used to minimize the anti-noise network by integrating anti-noise constraint and a softmax classification loss. The proposed network architecture can be easily trained with a limited amount of training data. The experiments conducted on three different scale RS scene datasets show that the DSFATN method has achieved excellent performance and great robustness in different scales and noise conditions. It obtains classification accuracy of 98.25%, 98.46%, and 98.80%, respectively, on the UC Merced Land Use Dataset (UCM, the Google image dataset of SIRI-WHU, and the SAT-6 dataset, advancing the state-of-the-art substantially.

A Fourier-based textural feature extraction procedure

Science.gov (United States)

Stromberg, W. D.; Farr, T. G.

1986-01-01

A procedure is presented to discriminate and characterize regions of uniform image texture. The procedure utilizes textural features consisting of pixel-by-pixel estimates of the relative emphases of annular regions of the Fourier transform. The utility and derivation of the features are described through presentation of a theoretical justification of the concept followed by a heuristic extension to a real environment. Two examples are provided that validate the technique on synthetic images and demonstrate its applicability to the discrimination of geologic texture in a radar image of a tropical vegetated area.

A feature-based approach to modeling protein-DNA interactions.

Directory of Open Access Journals (Sweden)

Eilon Sharon

Full Text Available Transcription factor (TF binding to its DNA target site is a fundamental regulatory interaction. The most common model used to represent TF binding specificities is a position specific scoring matrix (PSSM, which assumes independence between binding positions. However, in many cases, this simplifying assumption does not hold. Here, we present feature motif models (FMMs, a novel probabilistic method for modeling TF-DNA interactions, based on log-linear models. Our approach uses sequence features to represent TF binding specificities, where each feature may span multiple positions. We develop the mathematical formulation of our model and devise an algorithm for learning its structural features from binding site data. We also developed a discriminative motif finder, which discovers de novo FMMs that are enriched in target sets of sequences compared to background sets. We evaluate our approach on synthetic data and on the widely used TF chromatin immunoprecipitation (ChIP dataset of Harbison et al. We then apply our algorithm to high-throughput TF ChIP data from mouse and human, reveal sequence features that are present in the binding specificities of mouse and human TFs, and show that FMMs explain TF binding significantly better than PSSMs. Our FMM learning and motif finder software are available at http://genie.weizmann.ac.il/.

Aberrant functional connectivity for diagnosis of major depressive disorder: a discriminant analysis.

Science.gov (United States)

Cao, Longlong; Guo, Shuixia; Xue, Zhimin; Hu, Yong; Liu, Haihong; Mwansisya, Tumbwene E; Pu, Weidan; Yang, Bo; Liu, Chang; Feng, Jianfeng; Chen, Eric Y H; Liu, Zhening

2014-02-01

Aberrant brain functional connectivity patterns have been reported in major depressive disorder (MDD). It is unknown whether they can be used in discriminant analysis for diagnosis of MDD. In the present study we examined the efficiency of discriminant analysis of MDD by individualized computer-assisted diagnosis. Based on resting-state functional magnetic resonance imaging data, a new approach was adopted to investigate functional connectivity changes in 39 MDD patients and 37 well-matched healthy controls. By using the proposed feature selection method, we identified significant altered functional connections in patients. They were subsequently applied to our analysis as discriminant features using a support vector machine classification method. Furthermore, the relative contribution of functional connectivity was estimated. After subset selection of high-dimension features, the support vector machine classifier reached up to approximately 84% with leave-one-out training during the discrimination process. Through summarizing the classification contribution of functional connectivities, we obtained four obvious contribution modules: inferior orbitofrontal module, supramarginal gyrus module, inferior parietal lobule-posterior cingulated gyrus module and middle temporal gyrus-inferior temporal gyrus module. The experimental results demonstrated that the proposed method is effective in discriminating MDD patients from healthy controls. Functional connectivities might be useful as new biomarkers to assist clinicians in computer auxiliary diagnosis of MDD. © 2013 The Authors. Psychiatry and Clinical Neurosciences © 2013 Japanese Society of Psychiatry and Neurology.

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.

Pairwise Constraint-Guided Sparse Learning for Feature Selection.

Science.gov (United States)

Liu, Mingxia; Zhang, Daoqiang

2016-01-01

Feature selection aims to identify the most informative features for a compact and accurate data representation. As typical supervised feature selection methods, Lasso and its variants using L1-norm-based regularization terms have received much attention in recent studies, most of which use class labels as supervised information. Besides class labels, there are other types of supervised information, e.g., pairwise constraints that specify whether a pair of data samples belong to the same class (must-link constraint) or different classes (cannot-link constraint). However, most of existing L1-norm-based sparse learning methods do not take advantage of the pairwise constraints that provide us weak and more general supervised information. For addressing that problem, we propose a pairwise constraint-guided sparse (CGS) learning method for feature selection, where the must-link and the cannot-link constraints are used as discriminative regularization terms that directly concentrate on the local discriminative structure of data. Furthermore, we develop two variants of CGS, including: 1) semi-supervised CGS that utilizes labeled data, pairwise constraints, and unlabeled data and 2) ensemble CGS that uses the ensemble of pairwise constraint sets. We conduct a series of experiments on a number of data sets from University of California-Irvine machine learning repository, a gene expression data set, two real-world neuroimaging-based classification tasks, and two large-scale attribute classification tasks. Experimental results demonstrate the efficacy of our proposed methods, compared with several established feature selection methods.

A Headset Method for Measuring the Visual Temporal Discrimination Threshold in Cervical Dystonia

Directory of Open Access Journals (Sweden)

Anna Molloy

2014-07-01

Full Text Available Background: The visual temporal discrimination threshold (TDT is the shortest time interval at which one can determine two stimuli to be asynchronous and meets criteria for a valid endophenotype in adult‐onset idiopathic focal dystonia, a poorly penetrant disorder. Temporal discrimination is assessed in the hospital laboratory; in unaffected relatives of multiplex adult‐onset dystonia patients distance from the hospital is a barrier to data acquisition. We devised a portable headset method for visual temporal discrimination determination and our aim was to validate this portable tool against the traditional laboratory‐based method in a group of patients and in a large cohort of healthy controls. Methods: Visual TDTs were examined in two groups 1 in 96 healthy control participants divided by age and gender, and 2 in 33 cervical dystonia patients, using two methods of data acquisition, the traditional table‐top laboratory‐based system, and the novel portable headset method. The order of assessment was randomized in the control group. The results obtained by each technique were compared. Results: Visual temporal discrimination in healthy control participants demonstrated similar age and gender effects by the headset method as found by the table‐top examination. There were no significant differences between visual TDTs obtained using the two methods, both for the control participants and for the cervical dystonia patients. Bland–Altman testing showed good concordance between the two methods in both patients and in controls.Discussion: The portable headset device is a reliable and accurate method for visual temporal discrimination testing for use outside the laboratory, and will facilitate increased TDT data collection outside of the hospital setting. This is of particular importance in multiplex families where data collection in all available members of the pedigree is important for exome sequencing studies.

Perceptual Discrimination of Basic Object Features Is Not Facilitated When Priming Stimuli Are Prevented From Reaching Awareness by Means of Visual Masking.

Science.gov (United States)

Peel, Hayden J; Sperandio, Irene; Laycock, Robin; Chouinard, Philippe A

2018-01-01

Our understanding of how form, orientation and size are processed within and outside of awareness is limited and requires further investigation. Therefore, we investigated whether or not the visual discrimination of basic object features can be influenced by subliminal processing of stimuli presented beforehand. Visual masking was used to render stimuli perceptually invisible. Three experiments examined if visible and invisible primes could facilitate the subsequent feature discrimination of visible targets. The experiments differed in the kind of perceptual discrimination that participants had to make. Namely, participants were asked to discriminate visual stimuli on the basis of their form, orientation, or size. In all three experiments, we demonstrated reliable priming effects when the primes were visible but not when the primes were made invisible. Our findings underscore the importance of conscious awareness in facilitating the perceptual discrimination of basic object features.

Perceptual Discrimination of Basic Object Features Is Not Facilitated When Priming Stimuli Are Prevented From Reaching Awareness by Means of Visual Masking

Science.gov (United States)

Peel, Hayden J.; Sperandio, Irene; Laycock, Robin; Chouinard, Philippe A.

2018-01-01

Our understanding of how form, orientation and size are processed within and outside of awareness is limited and requires further investigation. Therefore, we investigated whether or not the visual discrimination of basic object features can be influenced by subliminal processing of stimuli presented beforehand. Visual masking was used to render stimuli perceptually invisible. Three experiments examined if visible and invisible primes could facilitate the subsequent feature discrimination of visible targets. The experiments differed in the kind of perceptual discrimination that participants had to make. Namely, participants were asked to discriminate visual stimuli on the basis of their form, orientation, or size. In all three experiments, we demonstrated reliable priming effects when the primes were visible but not when the primes were made invisible. Our findings underscore the importance of conscious awareness in facilitating the perceptual discrimination of basic object features. PMID:29725292

Weight-based discrimination: an ubiquitary phenomenon?

Science.gov (United States)

Sikorski, C; Spahlholz, J; Hartlev, M; Riedel-Heller, S G

2016-02-01

Despite strong indications of a high prevalence of weight-related stigmatization in individuals with obesity, limited attention has been given to the role of weight discrimination in examining the stigma obesity. Studies, up to date, rely on a limited basis of data sets and additional studies are needed to confirm the findings of previous studies. In particular, data for Europe are lacking, and are needed in light of a recent ruling of the European Court of Justice that addressed weight-based discrimination. The data were derived from a large representative telephone survey in Germany (n=3003). The dependent variable, weight-based discrimination, was assessed with a one-item question. The lifetime prevalence of weight discrimination across different sociodemographic variables was determined. Logistic regression models were used to assess the association of independent and dependent variables. A sub-group analysis was conducted analyzing all participants with a body mass index ⩾25 kg m(-)(2). The overall prevalence of weight-based discrimination was 7.3%. Large differences, however, were observed regarding weight status. In normal weight and overweight participants the prevalence was 5.6%, but this number doubled in participants with obesity class I (10.2%), and quadrupled in participants with obesity class II (18.7%) and underweight (19.7%). In participants with obesity class III, every third participant reported accounts of weight-based discrimination (38%). In regression models, after adjustment, the associations of weight status and female gender (odds ratio: 2.59, PDiscrimination seems to be an ubiquitary phenomenon at least for some groups that are at special risk, such as heavier individuals and women. Our findings therefore emphasize the need for research and intervention on weight discrimination among adults with obesity, including anti-discrimination legislation.

A multilevel-ROI-features-based machine learning method for detection of morphometric biomarkers in Parkinson's disease.

Science.gov (United States)

Peng, Bo; Wang, Suhong; Zhou, Zhiyong; Liu, Yan; Tong, Baotong; Zhang, Tao; Dai, Yakang

2017-06-09

Machine learning methods have been widely used in recent years for detection of neuroimaging biomarkers in regions of interest (ROIs) and assisting diagnosis of neurodegenerative diseases. The innovation of this study is to use multilevel-ROI-features-based machine learning method to detect sensitive morphometric biomarkers in Parkinson's disease (PD). Specifically, the low-level ROI features (gray matter volume, cortical thickness, etc.) and high-level correlative features (connectivity between ROIs) are integrated to construct the multilevel ROI features. Filter- and wrapper- based feature selection method and multi-kernel support vector machine (SVM) are used in the classification algorithm. T1-weighted brain magnetic resonance (MR) images of 69 PD patients and 103 normal controls from the Parkinson's Progression Markers Initiative (PPMI) dataset are included in the study. The machine learning method performs well in classification between PD patients and normal controls with an accuracy of 85.78%, a specificity of 87.79%, and a sensitivity of 87.64%. The most sensitive biomarkers between PD patients and normal controls are mainly distributed in frontal lobe, parental lobe, limbic lobe, temporal lobe, and central region. The classification performance of our method with multilevel ROI features is significantly improved comparing with other classification methods using single-level features. The proposed method shows promising identification ability for detecting morphometric biomarkers in PD, thus confirming the potentiality of our method in assisting diagnosis of the disease. Copyright © 2017 Elsevier B.V. All rights reserved.

Appearance-based human gesture recognition using multimodal features for human computer interaction

Science.gov (United States)

Luo, Dan; Gao, Hua; Ekenel, Hazim Kemal; Ohya, Jun

2011-03-01

The use of gesture as a natural interface plays an utmost important role for achieving intelligent Human Computer Interaction (HCI). Human gestures include different components of visual actions such as motion of hands, facial expression, and torso, to convey meaning. So far, in the field of gesture recognition, most previous works have focused on the manual component of gestures. In this paper, we present an appearance-based multimodal gesture recognition framework, which combines the different groups of features such as facial expression features and hand motion features which are extracted from image frames captured by a single web camera. We refer 12 classes of human gestures with facial expression including neutral, negative and positive meanings from American Sign Languages (ASL). We combine the features in two levels by employing two fusion strategies. At the feature level, an early feature combination can be performed by concatenating and weighting different feature groups, and LDA is used to choose the most discriminative elements by projecting the feature on a discriminative expression space. The second strategy is applied on decision level. Weighted decisions from single modalities are fused in a later stage. A condensation-based algorithm is adopted for classification. We collected a data set with three to seven recording sessions and conducted experiments with the combination techniques. Experimental results showed that facial analysis improve hand gesture recognition, decision level fusion performs better than feature level fusion.

Stacked Denoise Autoencoder Based Feature Extraction and Classification for Hyperspectral Images

Directory of Open Access Journals (Sweden)

Chen Xing

2016-01-01

Full Text Available Deep learning methods have been successfully applied to learn feature representations for high-dimensional data, where the learned features are able to reveal the nonlinear properties exhibited in the data. In this paper, deep learning method is exploited for feature extraction of hyperspectral data, and the extracted features can provide good discriminability for classification task. Training a deep network for feature extraction and classification includes unsupervised pretraining and supervised fine-tuning. We utilized stacked denoise autoencoder (SDAE method to pretrain the network, which is robust to noise. In the top layer of the network, logistic regression (LR approach is utilized to perform supervised fine-tuning and classification. Since sparsity of features might improve the separation capability, we utilized rectified linear unit (ReLU as activation function in SDAE to extract high level and sparse features. Experimental results using Hyperion, AVIRIS, and ROSIS hyperspectral data demonstrated that the SDAE pretraining in conjunction with the LR fine-tuning and classification (SDAE_LR can achieve higher accuracies than the popular support vector machine (SVM classifier.

An improved discriminative filter bank selection approach for motor imagery EEG signal classification using mutual information.

Science.gov (United States)

Kumar, Shiu; Sharma, Alok; Tsunoda, Tatsuhiko

2017-12-28

Common spatial pattern (CSP) has been an effective technique for feature extraction in electroencephalography (EEG) based brain computer interfaces (BCIs). However, motor imagery EEG signal feature extraction using CSP generally depends on the selection of the frequency bands to a great extent. In this study, we propose a mutual information based frequency band selection approach. The idea of the proposed method is to utilize the information from all the available channels for effectively selecting the most discriminative filter banks. CSP features are extracted from multiple overlapping sub-bands. An additional sub-band has been introduced that cover the wide frequency band (7-30 Hz) and two different types of features are extracted using CSP and common spatio-spectral pattern techniques, respectively. Mutual information is then computed from the extracted features of each of these bands and the top filter banks are selected for further processing. Linear discriminant analysis is applied to the features extracted from each of the filter banks. The scores are fused together, and classification is done using support vector machine. The proposed method is evaluated using BCI Competition III dataset IVa, BCI Competition IV dataset I and BCI Competition IV dataset IIb, and it outperformed all other competing methods achieving the lowest misclassification rate and the highest kappa coefficient on all three datasets. Introducing a wide sub-band and using mutual information for selecting the most discriminative sub-bands, the proposed method shows improvement in motor imagery EEG signal classification.

Analysis of feature stability for laser-based determination of tissue thickness

Science.gov (United States)

Ernst, Floris; Schweikard, Achim; Stüber, Patrick; Bruder, Ralf; Wagner, Benjamin; Wissel, Tobias

2015-03-01

Localisation of the cranium is necessary for accurate stereotactic radiotherapy of malign lesions in the brain. This is achieved by immobilizing the patient's head (typically by using thermoplastic masks, bite blocks or combinations thereof) and x-ray imaging to determine the actual position of the patient with respect to the treatment device. In previous work we have developed a novel method for marker-less and non-invasive tracking of the skull using a combination of laser-based surface triangulation and the analysis of backscattered feature patterns of a tightly collimated NIR laser beam scanned over the patient's forehead. An HDR camera is coupled into the beam path of the laser scanning system to acquire one image per projected laser point. We have demonstrated that this setup is capable of accurately determining the tissue thickness for each triangulation point and consequently allows detecting the surface of the cranial bone with sub-millimetre accuracy. Typical clinical settings (treatment times of 15-90 min) require feature stability over time, since the determination of tissue thickness is achieved by machine learning methods trained on initial feature scans. We have collected initial scans of the forehead as well as long-term backscatter data (20 images per seconds over 30 min) from five subjects and extracted the relevant tissue features from the image streams. Based on the knowledge of the relationship between the tissue feature values and the tissue thickness, the analysis of the long-term data showed that the noise level is low enough to allow robust discrimination of tissue thicknesses of 0.5 mm.

Neutron spectrum measurement using rise-time discrimination method

International Nuclear Information System (INIS)

Luo Zhiping; Suzuki, C.; Kosako, T.; Ma Jizeng

2009-01-01

PSD method can be used to measure the fast neutron spectrum in n/γ mixed field. A set of assemblies for measuring the pulse height distribution of neutrons is built up,based on a large volume NE213 liquid scintillator and standard NIM circuits,through the rise-time discrimination method. After that,the response matrix is calculated using Monte Carlo method. The energy calibration of the pulse height distribution is accomplished using 60 Co radioisotope. The neutron spectrum of the mono-energetic accelerator neutron source is achieved by unfolding process. Suggestions for further improvement of the system are presented at last. (authors)

Bag-of-features based medical image retrieval via multiple assignment and visual words weighting

KAUST Repository

Wang, Jingyan

2011-11-01

Bag-of-features based approaches have become prominent for image retrieval and image classification tasks in the past decade. Such methods represent an image as a collection of local features, such as image patches and key points with scale invariant feature transform (SIFT) descriptors. To improve the bag-of-features methods, we first model the assignments of local descriptors as contribution functions, and then propose a novel multiple assignment strategy. Assuming the local features can be reconstructed by their neighboring visual words in a vocabulary, reconstruction weights can be solved by quadratic programming. The weights are then used to build contribution functions, resulting in a novel assignment method, called quadratic programming (QP) assignment. We further propose a novel visual word weighting method. The discriminative power of each visual word is analyzed by the sub-similarity function in the bin that corresponds to the visual word. Each sub-similarity function is then treated as a weak classifier. A strong classifier is learned by boosting methods that combine those weak classifiers. The weighting factors of the visual words are learned accordingly. We evaluate the proposed methods on medical image retrieval tasks. The methods are tested on three well-known data sets, i.e., the ImageCLEFmed data set, the 304 CT Set, and the basal-cell carcinoma image set. Experimental results demonstrate that the proposed QP assignment outperforms the traditional nearest neighbor assignment, the multiple assignment, and the soft assignment, whereas the proposed boosting based weighting strategy outperforms the state-of-the-art weighting methods, such as the term frequency weights and the term frequency-inverse document frequency weights. © 2011 IEEE.

Bag-of-features based medical image retrieval via multiple assignment and visual words weighting

KAUST Repository

Wang, Jingyan; Li, Yongping; Zhang, Ying; Wang, Chao; Xie, Honglan; Chen, Guoling; Gao, Xin

2011-01-01

Bag-of-features based approaches have become prominent for image retrieval and image classification tasks in the past decade. Such methods represent an image as a collection of local features, such as image patches and key points with scale invariant feature transform (SIFT) descriptors. To improve the bag-of-features methods, we first model the assignments of local descriptors as contribution functions, and then propose a novel multiple assignment strategy. Assuming the local features can be reconstructed by their neighboring visual words in a vocabulary, reconstruction weights can be solved by quadratic programming. The weights are then used to build contribution functions, resulting in a novel assignment method, called quadratic programming (QP) assignment. We further propose a novel visual word weighting method. The discriminative power of each visual word is analyzed by the sub-similarity function in the bin that corresponds to the visual word. Each sub-similarity function is then treated as a weak classifier. A strong classifier is learned by boosting methods that combine those weak classifiers. The weighting factors of the visual words are learned accordingly. We evaluate the proposed methods on medical image retrieval tasks. The methods are tested on three well-known data sets, i.e., the ImageCLEFmed data set, the 304 CT Set, and the basal-cell carcinoma image set. Experimental results demonstrate that the proposed QP assignment outperforms the traditional nearest neighbor assignment, the multiple assignment, and the soft assignment, whereas the proposed boosting based weighting strategy outperforms the state-of-the-art weighting methods, such as the term frequency weights and the term frequency-inverse document frequency weights. © 2011 IEEE.

nRC: non-coding RNA Classifier based on structural features.

Science.gov (United States)

Fiannaca, Antonino; La Rosa, Massimo; La Paglia, Laura; Rizzo, Riccardo; Urso, Alfonso

2017-01-01

Non-coding RNA (ncRNA) are small non-coding sequences involved in gene expression regulation of many biological processes and diseases. The recent discovery of a large set of different ncRNAs with biologically relevant roles has opened the way to develop methods able to discriminate between the different ncRNA classes. Moreover, the lack of knowledge about the complete mechanisms in regulative processes, together with the development of high-throughput technologies, has required the help of bioinformatics tools in addressing biologists and clinicians with a deeper comprehension of the functional roles of ncRNAs. In this work, we introduce a new ncRNA classification tool, nRC (non-coding RNA Classifier). Our approach is based on features extraction from the ncRNA secondary structure together with a supervised classification algorithm implementing a deep learning architecture based on convolutional neural networks. We tested our approach for the classification of 13 different ncRNA classes. We obtained classification scores, using the most common statistical measures. In particular, we reach an accuracy and sensitivity score of about 74%. The proposed method outperforms other similar classification methods based on secondary structure features and machine learning algorithms, including the RNAcon tool that, to date, is the reference classifier. nRC tool is freely available as a docker image at https://hub.docker.com/r/tblab/nrc/. The source code of nRC tool is also available at https://github.com/IcarPA-TBlab/nrc.

Cascaded face alignment via intimacy definition feature

Science.gov (United States)

Li, Hailiang; Lam, Kin-Man; Chiu, Man-Yau; Wu, Kangheng; Lei, Zhibin

2017-09-01

Recent years have witnessed the emerging popularity of regression-based face aligners, which directly learn mappings between facial appearance and shape-increment manifolds. We propose a random-forest based, cascaded regression model for face alignment by using a locally lightweight feature, namely intimacy definition feature. This feature is more discriminative than the pose-indexed feature, more efficient than the histogram of oriented gradients feature and the scale-invariant feature transform feature, and more compact than the local binary feature (LBF). Experimental validation of our algorithm shows that our approach achieves state-of-the-art performance when testing on some challenging datasets. Compared with the LBF-based algorithm, our method achieves about twice the speed, 20% improvement in terms of alignment accuracy and saves an order of magnitude on memory requirement.

RESEARCH ON FOREST FLAME RECOGNITION ALGORITHM BASED ON IMAGE FEATURE

Directory of Open Access Journals (Sweden)

Z. Wang

2017-09-01

Full Text Available In recent years, fire recognition based on image features has become a hotspot in fire monitoring. However, due to the complexity of forest environment, the accuracy of forest fireworks recognition based on image features is low. Based on this, this paper proposes a feature extraction algorithm based on YCrCb color space and K-means clustering. Firstly, the paper prepares and analyzes the color characteristics of a large number of forest fire image samples. Using the K-means clustering algorithm, the forest flame model is obtained by comparing the two commonly used color spaces, and the suspected flame area is discriminated and extracted. The experimental results show that the extraction accuracy of flame area based on YCrCb color model is higher than that of HSI color model, which can be applied in different scene forest fire identification, and it is feasible in practice.

A Spectrum Sensing Method Based on Signal Feature and Clustering Algorithm in Cognitive Wireless Multimedia Sensor Networks

Directory of Open Access Journals (Sweden)

Yongwei Zhang

2017-01-01

Full Text Available In order to solve the problem of difficulty in determining the threshold in spectrum sensing technologies based on the random matrix theory, a spectrum sensing method based on clustering algorithm and signal feature is proposed for Cognitive Wireless Multimedia Sensor Networks. Firstly, the wireless communication signal features are obtained according to the sampling signal covariance matrix. Then, the clustering algorithm is used to classify and test the signal features. Different signal features and clustering algorithms are compared in this paper. The experimental results show that the proposed method has better sensing performance.

Role of baseline nodule density and changes in density and nodule features in the discrimination between benign and malignant solid indeterminate pulmonary nodules

NARCIS (Netherlands)

Xu, D.M.; van Klaveren, R.J.; de Bock, G.H.; Leusveld, A.L.M.; Dorrius, M.D.; Zhao, Y.; Wang, Y.; de Koning, H.J.; Scholten, E.T.; Verschakelen, J.; Prokop, M.; Oudkerk, M.

Purpose: To retrospectively evaluate whether baseline nodule density or changes in density or nodule features could be used to discriminate between benign and malignant solid indeterminate nodules. Materials and methods: Solid indeterminate nodules between 50 and 500 mm(3) (4.6-9.8 mm) were assessed

Ship Detection in Optical Satellite Image Based on RX Method and PCAnet

Science.gov (United States)

Shao, Xiu; Li, Huali; Lin, Hui; Kang, Xudong; Lu, Ting

2017-12-01

In this paper, we present a novel method for ship detection in optical satellite image based on the ReedXiaoli (RX) method and the principal component analysis network (PCAnet). The proposed method consists of the following three steps. First, the spatially adjacent pixels in optical image are arranged into a vector, transforming the optical image into a 3D cube image. By taking this process, the contextual information of the spatially adjacent pixels can be integrated to magnify the discrimination between ship and background. Second, the RX anomaly detection method is adopted to preliminarily extract ship candidates from the produced 3D cube image. Finally, real ships are further confirmed among ship candidates by applying the PCAnet and the support vector machine (SVM). Specifically, the PCAnet is a simple deep learning network which is exploited to perform feature extraction, and the SVM is applied to achieve feature pooling and decision making. Experimental results demonstrate that our approach is effective in discriminating between ships and false alarms, and has a good ship detection performance.

Machinery fault diagnosis using joint global and local/nonlocal discriminant analysis with selective ensemble learning

Science.gov (United States)

Yu, Jianbo

2016-11-01

The vibration signals of faulty machine are generally non-stationary and nonlinear under those complicated working conditions. Thus, it is a big challenge to extract and select the effective features from vibration signals for machinery fault diagnosis. This paper proposes a new manifold learning algorithm, joint global and local/nonlocal discriminant analysis (GLNDA), which aims to extract effective intrinsic geometrical information from the given vibration data. Comparisons with other regular methods, principal component analysis (PCA), local preserving projection (LPP), linear discriminant analysis (LDA) and local LDA (LLDA), illustrate the superiority of GLNDA in machinery fault diagnosis. Based on the extracted information by GLNDA, a GLNDA-based Fisher discriminant rule (FDR) is put forward and applied to machinery fault diagnosis without additional recognizer construction procedure. By importing Bagging into GLNDA score-based feature selection and FDR, a novel manifold ensemble method (selective GLNDA ensemble, SE-GLNDA) is investigated for machinery fault diagnosis. The motivation for developing ensemble of manifold learning components is that it can achieve higher accuracy and applicability than single component in machinery fault diagnosis. The effectiveness of the SE-GLNDA-based fault diagnosis method has been verified by experimental results from bearing full life testers.

Spatio-temporal features for tracking and quadruped/biped discrimination

Science.gov (United States)

Rickman, Rick; Copsey, Keith; Bamber, David C.; Page, Scott F.

2012-05-01

Techniques such as SIFT and SURF facilitate efficient and robust image processing operations through the use of sparse and compact spatial feature descriptors and show much potential for defence and security applications. This paper considers the extension of such techniques to include information from the temporal domain, to improve utility in applications involving moving imagery within video data. In particular, the paper demonstrates how spatio-temporal descriptors can be used very effectively as the basis of a target tracking system and as target discriminators which can distinguish between bipeds and quadrupeds. Results using sequences of video imagery of walking humans and dogs are presented, and the relative merits of the approach are discussed.

Optical implementation of a feature-based neural network with application to automatic target recognition

Science.gov (United States)

Chao, Tien-Hsin; Stoner, William W.

1993-01-01

An optical neural network based on the neocognitron paradigm is introduced. A novel aspect of the architecture design is shift-invariant multichannel Fourier optical correlation within each processing layer. Multilayer processing is achieved by feeding back the ouput of the feature correlator interatively to the input spatial light modulator and by updating the Fourier filters. By training the neural net with characteristic features extracted from the target images, successful pattern recognition with intraclass fault tolerance and interclass discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space-object discrimination is also presented.

Water Extraction in High Resolution Remote Sensing Image Based on Hierarchical Spectrum and Shape Features

International Nuclear Information System (INIS)

Li, Bangyu; Zhang, Hui; Xu, Fanjiang

2014-01-01

This paper addresses the problem of water extraction from high resolution remote sensing images (including R, G, B, and NIR channels), which draws considerable attention in recent years. Previous work on water extraction mainly faced two difficulties. 1) It is difficult to obtain accurate position of water boundary because of using low resolution images. 2) Like all other image based object classification problems, the phenomena of ''different objects same image'' or ''different images same object'' affects the water extraction. Shadow of elevated objects (e.g. buildings, bridges, towers and trees) scattered in the remote sensing image is a typical noise objects for water extraction. In many cases, it is difficult to discriminate between water and shadow in a remote sensing image, especially in the urban region. We propose a water extraction method with two hierarchies: the statistical feature of spectral characteristic based on image segmentation and the shape feature based on shadow removing. In the first hierarchy, the Statistical Region Merging (SRM) algorithm is adopted for image segmentation. The SRM includes two key steps: one is sorting adjacent regions according to a pre-ascertained sort function, and the other one is merging adjacent regions based on a pre-ascertained merging predicate. The sort step is done one time during the whole processing without considering changes caused by merging which may cause imprecise results. Therefore, we modify the SRM with dynamic sort processing, which conducts sorting step repetitively when there is large adjacent region changes after doing merging. To achieve robust segmentation, we apply the merging region with six features (four remote sensing image bands, Normalized Difference Water Index (NDWI), and Normalized Saturation-value Difference Index (NSVDI)). All these features contribute to segment image into region of object. NDWI and NSVDI are discriminate between water and

A Sparsity-Promoted Method Based on Majorization-Minimization for Weak Fault Feature Enhancement.

Science.gov (United States)

Ren, Bangyue; Hao, Yansong; Wang, Huaqing; Song, Liuyang; Tang, Gang; Yuan, Hongfang

2018-03-28

Fault transient impulses induced by faulty components in rotating machinery usually contain substantial interference. Fault features are comparatively weak in the initial fault stage, which renders fault diagnosis more difficult. In this case, a sparse representation method based on the Majorzation-Minimization (MM) algorithm is proposed to enhance weak fault features and extract the features from strong background noise. However, the traditional MM algorithm suffers from two issues, which are the choice of sparse basis and complicated calculations. To address these challenges, a modified MM algorithm is proposed in which a sparse optimization objective function is designed firstly. Inspired by the Basis Pursuit (BP) model, the optimization function integrates an impulsive feature-preserving factor and a penalty function factor. Second, a modified Majorization iterative method is applied to address the convex optimization problem of the designed function. A series of sparse coefficients can be achieved through iterating, which only contain transient components. It is noteworthy that there is no need to select the sparse basis in the proposed iterative method because it is fixed as a unit matrix. Then the reconstruction step is omitted, which can significantly increase detection efficiency. Eventually, envelope analysis of the sparse coefficients is performed to extract weak fault features. Simulated and experimental signals including bearings and gearboxes are employed to validate the effectiveness of the proposed method. In addition, comparisons are made to prove that the proposed method outperforms the traditional MM algorithm in terms of detection results and efficiency.

Face-based recognition techniques: proposals for the metrological characterization of global and feature-based approaches

Science.gov (United States)

Betta, G.; Capriglione, D.; Crenna, F.; Rossi, G. B.; Gasparetto, M.; Zappa, E.; Liguori, C.; Paolillo, A.

2011-12-01

Security systems based on face recognition through video surveillance systems deserve great interest. Their use is important in several areas including airport security, identification of individuals and access control to critical areas. These systems are based either on the measurement of details of a human face or on a global approach whereby faces are considered as a whole. The recognition is then performed by comparing the measured parameters with reference values stored in a database. The result of this comparison is not deterministic because measurement results are affected by uncertainty due to random variations and/or to systematic effects. In these circumstances the recognition of a face is subject to the risk of a faulty decision. Therefore, a proper metrological characterization is needed to improve the performance of such systems. Suitable methods are proposed for a quantitative metrological characterization of face measurement systems, on which recognition procedures are based. The proposed methods are applied to three different algorithms based either on linear discrimination, on eigenface analysis, or on feature detection.

Face-based recognition techniques: proposals for the metrological characterization of global and feature-based approaches

International Nuclear Information System (INIS)

Betta, G; Capriglione, D; Crenna, F; Rossi, G B; Gasparetto, M; Zappa, E; Liguori, C; Paolillo, A

2011-01-01

Security systems based on face recognition through video surveillance systems deserve great interest. Their use is important in several areas including airport security, identification of individuals and access control to critical areas. These systems are based either on the measurement of details of a human face or on a global approach whereby faces are considered as a whole. The recognition is then performed by comparing the measured parameters with reference values stored in a database. The result of this comparison is not deterministic because measurement results are affected by uncertainty due to random variations and/or to systematic effects. In these circumstances the recognition of a face is subject to the risk of a faulty decision. Therefore, a proper metrological characterization is needed to improve the performance of such systems. Suitable methods are proposed for a quantitative metrological characterization of face measurement systems, on which recognition procedures are based. The proposed methods are applied to three different algorithms based either on linear discrimination, on eigenface analysis, or on feature detection

Discriminating bot accounts based solely on temporal features of microblog behavior

Science.gov (United States)

Pan, Junshan; Liu, Ying; Liu, Xiang; Hu, Hanping

2016-05-01

As the largest microblog service in China, Sina Weibo has attracted numerous automated applications (known as bots) due to its popularity and open architecture. We classify the active users from Sina Weibo into human, bot-based and hybrid groups based solely on the study of temporal features of their posting behavior. The anomalous burstiness parameter and time-interval entropy value are exploited to characterize automation. We also reveal different behavior patterns among the three types of users regarding their reposting ratio, daily rhythm and active days. Our findings may help Sina Weibo manage a better community and should be considered for dynamic models of microblog behaviors.

Face recognition algorithm using extended vector quantization histogram features.

Science.gov (United States)

Yan, Yan; Lee, Feifei; Wu, Xueqian; Chen, Qiu

2018-01-01

In this paper, we propose a face recognition algorithm based on a combination of vector quantization (VQ) and Markov stationary features (MSF). The VQ algorithm has been shown to be an effective method for generating features; it extracts a codevector histogram as a facial feature representation for face recognition. Still, the VQ histogram features are unable to convey spatial structural information, which to some extent limits their usefulness in discrimination. To alleviate this limitation of VQ histograms, we utilize Markov stationary features (MSF) to extend the VQ histogram-based features so as to add spatial structural information. We demonstrate the effectiveness of our proposed algorithm by achieving recognition results superior to those of several state-of-the-art methods on publicly available face databases.

A Learning-Based Steganalytic Method against LSB Matching Steganography

Directory of Open Access Journals (Sweden)

Z. Xia

2011-04-01

Full Text Available This paper considers the detection of spatial domain least significant bit (LSB matching steganography in gray images. Natural images hold some inherent properties, such as histogram, dependence between neighboring pixels, and dependence among pixels that are not adjacent to each other. These properties are likely to be disturbed by LSB matching. Firstly, histogram will become smoother after LSB matching. Secondly, the two kinds of dependence will be weakened by the message embedding. Accordingly, three features, which are respectively based on image histogram, neighborhood degree histogram and run-length histogram, are extracted at first. Then, support vector machine is utilized to learn and discriminate the difference of features between cover and stego images. Experimental results prove that the proposed method possesses reliable detection ability and outperforms the two previous state-of-the-art methods. Further more, the conclusions are drawn by analyzing the individual performance of three features and their fused feature.

A NEW STRATEGY FOR IMPROVING FEATURE SETS IN A DISCRETE HMM­BASED HANDWRITING RECOGNITION SYSTEM

NARCIS (Netherlands)

Grandidier, F.; Sabourin, R.; Suen, C.Y.; Gilloux, M.

2004-01-01

In this paper we introduce a new strategy for improving a discrete HMM­based handwriting recognition system, by integrating several information sources from specialized feature sets. For a given system, the basic idea is to keep the most discriminative features, and to replace the others with new

Reducing the n-gram feature space of class C GPCRs to subtype-discriminating patterns

Directory of Open Access Journals (Sweden)

König Caroline

2014-12-01

Full Text Available G protein-coupled receptors (GPCRs are a large and heterogeneous superfamily of receptors that are key cell players for their role as extracellular signal transmitters. Class C GPCRs, in particular, are of great interest in pharmacology. The lack of knowledge about their full 3-D structure prompts the use of their primary amino acid sequences for the construction of robust classifiers, capable of discriminating their different subtypes. In this paper, we investigate the use of feature selection techniques to build Support Vector Machine (SVM-based classification models from selected receptor subsequences described as n-grams. We show that this approach to classification is useful for finding class C GPCR subtype-specific motifs.

Discriminative kernel feature extraction and learning for object recognition and detection

DEFF Research Database (Denmark)

Pan, Hong; Olsen, Søren Ingvor; Zhu, Yaping

2015-01-01

Feature extraction and learning is critical for object recognition and detection. By embedding context cue of image attributes into the kernel descriptors, we propose a set of novel kernel descriptors called context kernel descriptors (CKD). The motivation of CKD is to use the spatial consistency...... even in high-dimensional space. In addition, the latent connection between Rényi quadratic entropy and the mapping data in kernel feature space further facilitates us to capture the geometric structure as well as the information about the underlying labels of the CKD using CSQMI. Thus the resulting...... codebook and reduced CKD are discriminative. We report superior performance of our algorithm for object recognition on benchmark datasets like Caltech-101 and CIFAR-10, as well as for detection on a challenging chicken feet dataset....

Action Recognition Using Discriminative Structured Trajectory Groups

KAUST Repository

Atmosukarto, Indriyati

2015-01-06

In this paper, we develop a novel framework for action recognition in videos. The framework is based on automatically learning the discriminative trajectory groups that are relevant to an action. Different from previous approaches, our method does not require complex computation for graph matching or complex latent models to localize the parts. We model a video as a structured bag of trajectory groups with latent class variables. We model action recognition problem in a weakly supervised setting and learn discriminative trajectory groups by employing multiple instance learning (MIL) based Support Vector Machine (SVM) using pre-computed kernels. The kernels depend on the spatio-temporal relationship between the extracted trajectory groups and their associated features. We demonstrate both quantitatively and qualitatively that the classification performance of our proposed method is superior to baselines and several state-of-the-art approaches on three challenging standard benchmark datasets.

Statistical methods of discrimination and classification advances in theory and applications

CERN Document Server

Choi, Sung C

1986-01-01

Statistical Methods of Discrimination and Classification: Advances in Theory and Applications is a collection of papers that tackles the multivariate problems of discriminating and classifying subjects into exclusive population. The book presents 13 papers that cover that advancement in the statistical procedure of discriminating and classifying. The studies in the text primarily focus on various methods of discriminating and classifying variables, such as multiple discriminant analysis in the presence of mixed continuous and categorical data; choice of the smoothing parameter and efficiency o

Discriminative sparse coding on multi-manifolds

KAUST Repository

Wang, J.J.-Y.; Bensmail, H.; Yao, N.; Gao, Xin

2013-01-01

Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics. However, the conventional sparse coding algorithms and their manifold-regularized variants (graph sparse coding and Laplacian sparse coding), learn codebooks and codes in an unsupervised manner and neglect class information that is available in the training set. To address this problem, we propose a novel discriminative sparse coding method based on multi-manifolds, that learns discriminative class-conditioned codebooks and sparse codes from both data feature spaces and class labels. First, the entire training set is partitioned into multiple manifolds according to the class labels. Then, we formulate the sparse coding as a manifold-manifold matching problem and learn class-conditioned codebooks and codes to maximize the manifold margins of different classes. Lastly, we present a data sample-manifold matching-based strategy to classify the unlabeled data samples. Experimental results on somatic mutations identification and breast tumor classification based on ultrasonic images demonstrate the efficacy of the proposed data representation and classification approach. 2013 The Authors. All rights reserved.

Discriminative sparse coding on multi-manifolds

KAUST Repository

Wang, J.J.-Y.

2013-09-26

Sparse coding has been popularly used as an effective data representation method in various applications, such as computer vision, medical imaging and bioinformatics. However, the conventional sparse coding algorithms and their manifold-regularized variants (graph sparse coding and Laplacian sparse coding), learn codebooks and codes in an unsupervised manner and neglect class information that is available in the training set. To address this problem, we propose a novel discriminative sparse coding method based on multi-manifolds, that learns discriminative class-conditioned codebooks and sparse codes from both data feature spaces and class labels. First, the entire training set is partitioned into multiple manifolds according to the class labels. Then, we formulate the sparse coding as a manifold-manifold matching problem and learn class-conditioned codebooks and codes to maximize the manifold margins of different classes. Lastly, we present a data sample-manifold matching-based strategy to classify the unlabeled data samples. Experimental results on somatic mutations identification and breast tumor classification based on ultrasonic images demonstrate the efficacy of the proposed data representation and classification approach. 2013 The Authors. All rights reserved.

Serum prolactin revisited: parametric reference intervals and cross platform evaluation of polyethylene glycol precipitation-based methods for discrimination between hyperprolactinemia and macroprolactinemia.

Science.gov (United States)

Overgaard, Martin; Pedersen, Susanne Møller

2017-10-26

Hyperprolactinemia diagnosis and treatment is often compromised by the presence of biologically inactive and clinically irrelevant higher-molecular-weight complexes of prolactin, macroprolactin. The objective of this study was to evaluate the performance of two macroprolactin screening regimes across commonly used automated immunoassay platforms. Parametric total and monomeric gender-specific reference intervals were determined for six immunoassay methods using female (n=96) and male sera (n=127) from healthy donors. The reference intervals were validated using 27 hyperprolactinemic and macroprolactinemic sera, whose presence of monomeric and macroforms of prolactin were determined using gel filtration chromatography (GFC). Normative data for six prolactin assays included the range of values (2.5th-97.5th percentiles). Validation sera (hyperprolactinemic and macroprolactinemic; n=27) showed higher discordant classification [mean=2.8; 95% confidence interval (CI) 1.2-4.4] for the monomer reference interval method compared to the post-polyethylene glycol (PEG) recovery cutoff method (mean=1.8; 95% CI 0.8-2.8). The two monomer/macroprolactin discrimination methods did not differ significantly (p=0.089). Among macroprolactinemic sera evaluated by both discrimination methods, the Cobas and Architect/Kryptor prolactin assays showed the lowest and the highest number of misclassifications, respectively. Current automated immunoassays for prolactin testing require macroprolactin screening methods based on PEG precipitation in order to discriminate truly from falsely elevated serum prolactin. While the recovery cutoff and monomeric reference interval macroprolactin screening methods demonstrate similar discriminative ability, the latter method also provides the clinician with an easy interpretable monomeric prolactin concentration along with a monomeric reference interval.

A line feature-based camera tracking method applicable to nuclear power plant environment

International Nuclear Information System (INIS)

Yan, Weida; Ishii, Hirotake; Shimoda, Hiroshi; Izumi, Masanori

2014-01-01

Augmented reality, which can support the maintenance and decommissioning work of an NPP to improve efficiency and reduce human error, is expected to be practically used in an NPP. AR has indispensable tracking technology that estimates the 3D position and orientation of users in real time, but because of the complication of the NPP environment, it is difficult for its practial use in the large space of an NPP. This study attempt to develop a tracking method for the practial use in an NPP. Marker tracking is a legacy tracking method, but the preparation work necessary for that method is onerous. Therefore, this study developed and evaluated a natural feature-based camera tracking method that demands less preparation and which is applicable in an NPP environment. This method registers natural features as landmarks. When tracking, the natural features existing in the NPP environment can be registered automatically as landmarks. It is therefore possible to expand the tracking area to cover a wide environment in theory. The evaluation result shows that the proposed tracking method has the possibility to support field work of some kinds in an NPP environment. It is possible to reduce the preparation work necessary for the marker tracking method. (author)

Rigorous assessment and integration of the sequence and structure based features to predict hot spots

Directory of Open Access Journals (Sweden)

Wang Yong

2011-07-01

Full Text Available Abstract Background Systematic mutagenesis studies have shown that only a few interface residues termed hot spots contribute significantly to the binding free energy of protein-protein interactions. Therefore, hot spots prediction becomes increasingly important for well understanding the essence of proteins interactions and helping narrow down the search space for drug design. Currently many computational methods have been developed by proposing different features. However comparative assessment of these features and furthermore effective and accurate methods are still in pressing need. Results In this study, we first comprehensively collect the features to discriminate hot spots and non-hot spots and analyze their distributions. We find that hot spots have lower relASA and larger relative change in ASA, suggesting hot spots tend to be protected from bulk solvent. In addition, hot spots have more contacts including hydrogen bonds, salt bridges, and atomic contacts, which favor complexes formation. Interestingly, we find that conservation score and sequence entropy are not significantly different between hot spots and non-hot spots in Ab+ dataset (all complexes. While in Ab- dataset (antigen-antibody complexes are excluded, there are significant differences in two features between hot pots and non-hot spots. Secondly, we explore the predictive ability for each feature and the combinations of features by support vector machines (SVMs. The results indicate that sequence-based feature outperforms other combinations of features with reasonable accuracy, with a precision of 0.69, a recall of 0.68, an F1 score of 0.68, and an AUC of 0.68 on independent test set. Compared with other machine learning methods and two energy-based approaches, our approach achieves the best performance. Moreover, we demonstrate the applicability of our method to predict hot spots of two protein complexes. Conclusion Experimental results show that support vector machine

Rigorous assessment and integration of the sequence and structure based features to predict hot spots

Science.gov (United States)

2011-01-01

Background Systematic mutagenesis studies have shown that only a few interface residues termed hot spots contribute significantly to the binding free energy of protein-protein interactions. Therefore, hot spots prediction becomes increasingly important for well understanding the essence of proteins interactions and helping narrow down the search space for drug design. Currently many computational methods have been developed by proposing different features. However comparative assessment of these features and furthermore effective and accurate methods are still in pressing need. Results In this study, we first comprehensively collect the features to discriminate hot spots and non-hot spots and analyze their distributions. We find that hot spots have lower relASA and larger relative change in ASA, suggesting hot spots tend to be protected from bulk solvent. In addition, hot spots have more contacts including hydrogen bonds, salt bridges, and atomic contacts, which favor complexes formation. Interestingly, we find that conservation score and sequence entropy are not significantly different between hot spots and non-hot spots in Ab+ dataset (all complexes). While in Ab- dataset (antigen-antibody complexes are excluded), there are significant differences in two features between hot pots and non-hot spots. Secondly, we explore the predictive ability for each feature and the combinations of features by support vector machines (SVMs). The results indicate that sequence-based feature outperforms other combinations of features with reasonable accuracy, with a precision of 0.69, a recall of 0.68, an F1 score of 0.68, and an AUC of 0.68 on independent test set. Compared with other machine learning methods and two energy-based approaches, our approach achieves the best performance. Moreover, we demonstrate the applicability of our method to predict hot spots of two protein complexes. Conclusion Experimental results show that support vector machine classifiers are quite

Colour-Based Binary Discrimination of Scarified Quercus robur Acorns under Varying Illumination

Directory of Open Access Journals (Sweden)

Mirosław Jabłoński

2016-08-01

Full Text Available Efforts to predict the germination ability of acorns using their shape, length, diameter and density are reported in the literature. These methods, however, are not efficient enough. As such, a visual assessment of the viability of seeds based on the appearance of cross-sections of seeds following their scarification is used. This procedure is more robust but demands significant effort from experienced employees over a short period of time. In this article an automated method of acorn scarification and assessment has been announced. This type of automation requires the specific setup of a machine vision system and application of image processing algorithms for evaluation of sections of seeds in order to predict their viability. In the stage of the analysis of pathological changes, it is important to point out image features that enable efficient classification of seeds in respect of viability. The article shows the results of the binary separation of seeds into two fractions (healthy or spoiled using average components of regular red-green-blue and perception-based hue-saturation-value colour space. Analysis of accuracy of discrimination was performed on sections of 400 scarified acorns acquired using two various setups: machine vision camera under uncontrolled varying illumination and commodity high-resolution camera under controlled illumination. The accuracy of automatic classification has been compared with predictions completed by experienced professionals. It has been shown that both automatic and manual methods reach an accuracy level of 84%, assuming that the images of the sections are properly normalised. The achieved recognition ratio was higher when referenced to predictions provided by professionals. Results of discrimination by means of Bayes classifier have been also presented as a reference.

Active Discriminative Dictionary Learning for Weather Recognition

Directory of Open Access Journals (Sweden)

Caixia Zheng

2016-01-01

Full Text Available Weather recognition based on outdoor images is a brand-new and challenging subject, which is widely required in many fields. This paper presents a novel framework for recognizing different weather conditions. Compared with other algorithms, the proposed method possesses the following advantages. Firstly, our method extracts both visual appearance features of the sky region and physical characteristics features of the nonsky region in images. Thus, the extracted features are more comprehensive than some of the existing methods in which only the features of sky region are considered. Secondly, unlike other methods which used the traditional classifiers (e.g., SVM and K-NN, we use discriminative dictionary learning as the classification model for weather, which could address the limitations of previous works. Moreover, the active learning procedure is introduced into dictionary learning to avoid requiring a large number of labeled samples to train the classification model for achieving good performance of weather recognition. Experiments and comparisons are performed on two datasets to verify the effectiveness of the proposed method.

Near infrared and visible face recognition based on decision fusion of LBP and DCT features

Science.gov (United States)

Xie, Zhihua; Zhang, Shuai; Liu, Guodong; Xiong, Jinquan

2018-03-01

Visible face recognition systems, being vulnerable to illumination, expression, and pose, can not achieve robust performance in unconstrained situations. Meanwhile, near infrared face images, being light- independent, can avoid or limit the drawbacks of face recognition in visible light, but its main challenges are low resolution and signal noise ratio (SNR). Therefore, near infrared and visible fusion face recognition has become an important direction in the field of unconstrained face recognition research. In order to extract the discriminative complementary features between near infrared and visible images, in this paper, we proposed a novel near infrared and visible face fusion recognition algorithm based on DCT and LBP features. Firstly, the effective features in near-infrared face image are extracted by the low frequency part of DCT coefficients and the partition histograms of LBP operator. Secondly, the LBP features of visible-light face image are extracted to compensate for the lacking detail features of the near-infrared face image. Then, the LBP features of visible-light face image, the DCT and LBP features of near-infrared face image are sent to each classifier for labeling. Finally, decision level fusion strategy is used to obtain the final recognition result. The visible and near infrared face recognition is tested on HITSZ Lab2 visible and near infrared face database. The experiment results show that the proposed method extracts the complementary features of near-infrared and visible face images and improves the robustness of unconstrained face recognition. Especially for the circumstance of small training samples, the recognition rate of proposed method can reach 96.13%, which has improved significantly than 92.75 % of the method based on statistical feature fusion.

Discrimination between biological interfaces and crystal-packing contacts

Directory of Open Access Journals (Sweden)

Yuko Tsuchiya

2008-11-01

Full Text Available Yuko Tsuchiya1, Haruki Nakamura2, Kengo Kinoshita1,31Institute of Medical Science, The University of Tokyo, 4-6-1 Shirokanedai, Minatoku, Tokyo, 108-8639, Japan; 2Institute for Protein Research, Osaka University, 3-2 Yamadaoka, Suita, Osaka, 565-0871, Japan; 3Bioinformatics Research and Development, JST, 4-1-8 Honcho, Kawaguchi, Saitama, 332-0012, JapanAbstract: A discrimination method between biologically relevant interfaces and artificial crystal-packing contacts in crystal structures was constructed. The method evaluates protein-protein interfaces in terms of complementarities for hydrophobicity, electrostatic potential and shape on the protein surfaces, and chooses the most probable biological interfaces among all possible contacts in the crystal. The method uses a discriminator named as “COMP”, which is a linear combination of the complementarities for the above three surface features and does not correlate with the contact area. The discrimination of homo-dimer interfaces from symmetry-related crystal-packing contacts based on the COMP value achieved the modest success rate. Subsequent detailed review of the discrimination results raised the success rate to about 88.8%. In addition, our discrimination method yielded some clues for understanding the interaction patterns in several examples in the PDB. Thus, the COMP discriminator can also be used as an indicator of the “biological-ness” of protein-protein interfaces.Keywords: protein-protein interaction, complementarity analysis, homo-dimer interface, crystal-packing contact, biological interfaces

Tolerance-Based Feature Transforms

NARCIS (Netherlands)

Reniers, Dennie; Telea, Alexandru

2007-01-01

Tolerance-based feature transforms (TFTs) assign to each pixel in an image not only the nearest feature pixels on the boundary (origins), but all origins from the minimum distance up to a user-defined tolerance. In this paper, we compare four simple-to-implement methods for computing TFTs on binary

Feature extraction for SAR target recognition based on supervised manifold learning

International Nuclear Information System (INIS)

Du, C; Zhou, S; Sun, J; Zhao, J

2014-01-01

On the basis of manifold learning theory, a new feature extraction method for Synthetic aperture radar (SAR) target recognition is proposed. First, the proposed algorithm estimates the within-class and between-class local neighbourhood surrounding each SAR sample. After computing the local tangent space for each neighbourhood, the proposed algorithm seeks for the optimal projecting matrix by preserving the local within-class property and simultaneously maximizing the local between-class separability. The use of uncorrelated constraint can also enhance the discriminating power of the optimal projecting matrix. Finally, the nearest neighbour classifier is applied to recognize SAR targets in the projected feature subspace. Experimental results on MSTAR datasets demonstrate that the proposed method can provide a higher recognition rate than traditional feature extraction algorithms in SAR target recognition

Neutron-gamma discrimination based on pulse shape discrimination in a Ce:LiCaAlF{sub 6} scintillator

Energy Technology Data Exchange (ETDEWEB)

Yamazaki, Atsushi, E-mail: a-yamazaki@nucl.nagoya-u.ac.jp [Department of Materials, Physics and Energy Engineering, Graduate School of Engineering, Nagoya University (Japan); Watanabe, Kenichi; Uritani, Akira [Department of Materials, Physics and Energy Engineering, Graduate School of Engineering, Nagoya University (Japan); Iguchi, Tetsuo [Department of Quantum Engineering, Graduate School of Engineering, Nagoya University (Japan); Kawaguchi, Noriaki [Tokuyama Corporation (Japan); Yanagida, Takayuki; Fujimoto, Yutaka; Yokota, Yuui; Kamada, Kei [Institute of Multidisciplinary Research for Advanced Materials (IMRAM), Tohoku University (Japan); Fukuda, Kentaro; Suyama, Toshihisa [Tokuyama Corporation (Japan); Yoshikawa, Akira [Institute of Multidisciplinary Research for Advanced Materials (IMRAM), Tohoku University (Japan); New Industry Creation Hatchery Center (NICHe), Tohoku University (Japan)

2011-10-01

We demonstrate neutron-gamma discrimination based on a pulse shape discrimination method in a Ce:LiCAF scintillator. We have tried neutron-gamma discrimination using a difference in the pulse shape or the decay time of the scintillation light pulse. The decay time is converted into the rise time through an integrating circuit. A {sup 252}Cf enclosed in a polyethylene container is used as the source of thermal neutrons and prompt gamma-rays. Obvious separation of neutron and gamma-ray events is achieved using the information of the rise time of the scintillation light pulse. In the separated neutron spectrum, the gamma-ray events are effectively suppressed with little loss of neutron events. The pulse shape discrimination is confirmed to be useful to detect neutrons with the Ce:LiCAF scintillator under an intense high-energy gamma-ray condition.

Predicting hot spots in protein interfaces based on protrusion index, pseudo hydrophobicity and electron-ion interaction pseudopotential features

Science.gov (United States)

Xia, Junfeng; Yue, Zhenyu; Di, Yunqiang; Zhu, Xiaolei; Zheng, Chun-Hou

2016-01-01

The identification of hot spots, a small subset of protein interfaces that accounts for the majority of binding free energy, is becoming more important for the research of drug design and cancer development. Based on our previous methods (APIS and KFC2), here we proposed a novel hot spot prediction method. For each hot spot residue, we firstly constructed a wide variety of 108 sequence, structural, and neighborhood features to characterize potential hot spot residues, including conventional ones and new one (pseudo hydrophobicity) exploited in this study. We then selected 3 top-ranking features that contribute the most in the classification by a two-step feature selection process consisting of minimal-redundancy-maximal-relevance algorithm and an exhaustive search method. We used support vector machines to build our final prediction model. When testing our model on an independent test set, our method showed the highest F1-score of 0.70 and MCC of 0.46 comparing with the existing state-of-the-art hot spot prediction methods. Our results indicate that these features are more effective than the conventional features considered previously, and that the combination of our and traditional features may support the creation of a discriminative feature set for efficient prediction of hot spots in protein interfaces. PMID:26934646

An effective method for cirrhosis recognition based on multi-feature fusion

Science.gov (United States)

Chen, Yameng; Sun, Gengxin; Lei, Yiming; Zhang, Jinpeng

2018-04-01

Liver disease is one of the main causes of human healthy problem. Cirrhosis, of course, is the critical phase during the development of liver lesion, especially the hepatoma. Many clinical cases are still influenced by the subjectivity of physicians in some degree, and some objective factors such as illumination, scale, edge blurring will affect the judgment of clinicians. Then the subjectivity will affect the accuracy of diagnosis and the treatment of patients. In order to solve the difficulty above and improve the recognition rate of liver cirrhosis, we propose a method of multi-feature fusion to obtain more robust representations of texture in ultrasound liver images, the texture features we extract include local binary pattern(LBP), gray level co-occurrence matrix(GLCM) and histogram of oriented gradient(HOG). In this paper, we firstly make a fusion of multi-feature to recognize cirrhosis and normal liver based on parallel combination concept, and the experimental results shows that the classifier is effective for cirrhosis recognition which is evaluated by the satisfying classification rate, sensitivity and specificity of receiver operating characteristic(ROC), and cost time. Through the method we proposed, it will be helpful to improve the accuracy of diagnosis of cirrhosis and prevent the development of liver lesion towards hepatoma.

Discriminative analysis of Parkinson's disease based on whole-brain functional connectivity.

Directory of Open Access Journals (Sweden)

Yongbin Chen

Full Text Available Recently, there has been an increasing emphasis on applications of pattern recognition and neuroimaging techniques in the effective and accurate diagnosis of psychiatric or neurological disorders. In the present study, we investigated the whole-brain resting-state functional connectivity patterns of Parkinson's disease (PD, which are expected to provide additional information for the clinical diagnosis and treatment of this disease. First, we computed the functional connectivity between each pair of 116 regions of interest derived from a prior atlas. The most discriminative features based on Kendall tau correlation coefficient were then selected. A support vector machine classifier was employed to classify 21 PD patients with 26 demographically matched healthy controls. This method achieved a classification accuracy of 93.62% using leave-one-out cross-validation, with a sensitivity of 90.47% and a specificity of 96.15%. The majority of the most discriminative functional connections were located within or across the default mode, cingulo-opercular and frontal-parietal networks and the cerebellum. These disease-related resting-state network alterations might play important roles in the pathophysiology of this disease. Our results suggest that analyses of whole-brain resting-state functional connectivity patterns have the potential to improve the clinical diagnosis and treatment evaluation of PD.

Testing for Statistical Discrimination based on Gender

OpenAIRE

Lesner, Rune Vammen

2016-01-01

This paper develops a model which incorporates the two most commonly cited strands of the literature on statistical discrimination, namely screening discrimination and stereotyping. The model is used to provide empirical evidence of statistical discrimination based on gender in the labour market. It is shown that the implications of both screening discrimination and stereotyping are consistent with observable wage dynamics. In addition, it is found that the gender wage gap decreases in tenure...

Selecting Feature Subsets Based on SVM-RFE and the Overlapping Ratio with Applications in Bioinformatics.

Science.gov (United States)

Lin, Xiaohui; Li, Chao; Zhang, Yanhui; Su, Benzhe; Fan, Meng; Wei, Hai

2017-12-26

Feature selection is an important topic in bioinformatics. Defining informative features from complex high dimensional biological data is critical in disease study, drug development, etc. Support vector machine-recursive feature elimination (SVM-RFE) is an efficient feature selection technique that has shown its power in many applications. It ranks the features according to the recursive feature deletion sequence based on SVM. In this study, we propose a method, SVM-RFE-OA, which combines the classification accuracy rate and the average overlapping ratio of the samples to determine the number of features to be selected from the feature rank of SVM-RFE. Meanwhile, to measure the feature weights more accurately, we propose a modified SVM-RFE-OA (M-SVM-RFE-OA) algorithm that temporally screens out the samples lying in a heavy overlapping area in each iteration. The experiments on the eight public biological datasets show that the discriminative ability of the feature subset could be measured more accurately by combining the classification accuracy rate with the average overlapping degree of the samples compared with using the classification accuracy rate alone, and shielding the samples in the overlapping area made the calculation of the feature weights more stable and accurate. The methods proposed in this study can also be used with other RFE techniques to define potential biomarkers from big biological data.

Selecting Feature Subsets Based on SVM-RFE and the Overlapping Ratio with Applications in Bioinformatics

Directory of Open Access Journals (Sweden)

Xiaohui Lin

2017-12-01

Full Text Available Feature selection is an important topic in bioinformatics. Defining informative features from complex high dimensional biological data is critical in disease study, drug development, etc. Support vector machine-recursive feature elimination (SVM-RFE is an efficient feature selection technique that has shown its power in many applications. It ranks the features according to the recursive feature deletion sequence based on SVM. In this study, we propose a method, SVM-RFE-OA, which combines the classification accuracy rate and the average overlapping ratio of the samples to determine the number of features to be selected from the feature rank of SVM-RFE. Meanwhile, to measure the feature weights more accurately, we propose a modified SVM-RFE-OA (M-SVM-RFE-OA algorithm that temporally screens out the samples lying in a heavy overlapping area in each iteration. The experiments on the eight public biological datasets show that the discriminative ability of the feature subset could be measured more accurately by combining the classification accuracy rate with the average overlapping degree of the samples compared with using the classification accuracy rate alone, and shielding the samples in the overlapping area made the calculation of the feature weights more stable and accurate. The methods proposed in this study can also be used with other RFE techniques to define potential biomarkers from big biological data.

Discriminating electromagnetic radiation based on angle of incidence

Science.gov (United States)

Hamam, Rafif E.; Bermel, Peter; Celanovic, Ivan; Soljacic, Marin; Yeng, Adrian Y. X.; Ghebrebrhan, Michael; Joannopoulos, John D.

2015-06-16

The present invention provides systems, articles, and methods for discriminating electromagnetic radiation based upon the angle of incidence of the electromagnetic radiation. In some cases, the materials and systems described herein can be capable of inhibiting reflection of electromagnetic radiation (e.g., the materials and systems can be capable of transmitting and/or absorbing electromagnetic radiation) within a given range of angles of incidence at a first incident surface, while substantially reflecting electromagnetic radiation outside the range of angles of incidence at a second incident surface (which can be the same as or different from the first incident surface). A photonic material comprising a plurality of periodically occurring separate domains can be used, in some cases, to selectively transmit and/or selectively absorb one portion of incoming electromagnetic radiation while reflecting another portion of incoming electromagnetic radiation, based upon the angle of incidence. In some embodiments, one domain of the photonic material can include an isotropic dielectric function, while another domain of the photonic material can include an anisotropic dielectric function. In some instances, one domain of the photonic material can include an isotropic magnetic permeability, while another domain of the photonic material can include an anisotropic magnetic permeability. In some embodiments, non-photonic materials (e.g., materials with relatively large scale features) can be used to selectively absorb incoming electromagnetic radiation based on angle of incidence.

Novel Digital Features Discriminate Between Drought Resistant and Drought Sensitive Rice Under Controlled and Field Conditions

Directory of Open Access Journals (Sweden)

Lingfeng Duan

2018-04-01

Full Text Available Dynamic quantification of drought response is a key issue both for variety selection and for functional genetic study of rice drought resistance. Traditional assessment of drought resistance traits, such as stay-green and leaf-rolling, has utilized manual measurements, that are often subjective, error-prone, poorly quantified and time consuming. To relieve this phenotyping bottleneck, we demonstrate a feasible, robust and non-destructive method that dynamically quantifies response to drought, under both controlled and field conditions. Firstly, RGB images of individual rice plants at different growth points were analyzed to derive 4 features that were influenced by imposition of drought. These include a feature related to the ability to stay green, which we termed greenness plant area ratio (GPAR and 3 shape descriptors [total plant area/bounding rectangle area ratio (TBR, perimeter area ratio (PAR and total plant area/convex hull area ratio (TCR]. Experiments showed that these 4 features were capable of discriminating reliably between drought resistant and drought sensitive accessions, and dynamically quantifying the drought response under controlled conditions across time (at either daily or half hourly time intervals. We compared the 3 shape descriptors and concluded that PAR was more robust and sensitive to leaf-rolling than the other shape descriptors. In addition, PAR and GPAR proved to be effective in quantification of drought response in the field. Moreover, the values obtained in field experiments using the collection of rice varieties were correlated with those derived from pot-based experiments. The general applicability of the algorithms is demonstrated by their ability to probe archival Miscanthus data previously collected on an independent platform. In conclusion, this image-based technology is robust providing a platform-independent tool for quantifying drought response that should be of general utility for breeding and functional

Common spatial pattern combined with kernel linear discriminate and generalized radial basis function for motor imagery-based brain computer interface applications

Science.gov (United States)

Hekmatmanesh, Amin; Jamaloo, Fatemeh; Wu, Huapeng; Handroos, Heikki; Kilpeläinen, Asko

2018-04-01

Brain Computer Interface (BCI) can be a challenge for developing of robotic, prosthesis and human-controlled systems. This work focuses on the implementation of a common spatial pattern (CSP) base algorithm to detect event related desynchronization patterns. Utilizing famous previous work in this area, features are extracted by filter bank with common spatial pattern (FBCSP) method, and then weighted by a sensitive learning vector quantization (SLVQ) algorithm. In the current work, application of the radial basis function (RBF) as a mapping kernel of linear discriminant analysis (KLDA) method on the weighted features, allows the transfer of data into a higher dimension for more discriminated data scattering by RBF kernel. Afterwards, support vector machine (SVM) with generalized radial basis function (GRBF) kernel is employed to improve the efficiency and robustness of the classification. Averagely, 89.60% accuracy and 74.19% robustness are achieved. BCI Competition III, Iva data set is used to evaluate the algorithm for detecting right hand and foot imagery movement patterns. Results show that combination of KLDA with SVM-GRBF classifier makes 8.9% and 14.19% improvements in accuracy and robustness, respectively. For all the subjects, it is concluded that mapping the CSP features into a higher dimension by RBF and utilization GRBF as a kernel of SVM, improve the accuracy and reliability of the proposed method.

Fault feature analysis of cracked gear based on LOD and analytical-FE method

Science.gov (United States)

Wu, Jiateng; Yang, Yu; Yang, Xingkai; Cheng, Junsheng

2018-01-01

At present, there are two main ideas for gear fault diagnosis. One is the model-based gear dynamic analysis; the other is signal-based gear vibration diagnosis. In this paper, a method for fault feature analysis of gear crack is presented, which combines the advantages of dynamic modeling and signal processing. Firstly, a new time-frequency analysis method called local oscillatory-characteristic decomposition (LOD) is proposed, which has the attractive feature of extracting fault characteristic efficiently and accurately. Secondly, an analytical-finite element (analytical-FE) method which is called assist-stress intensity factor (assist-SIF) gear contact model, is put forward to calculate the time-varying mesh stiffness (TVMS) under different crack states. Based on the dynamic model of the gear system with 6 degrees of freedom, the dynamic simulation response was obtained for different tooth crack depths. For the dynamic model, the corresponding relation between the characteristic parameters and the degree of the tooth crack is established under a specific condition. On the basis of the methods mentioned above, a novel gear tooth root crack diagnosis method which combines the LOD with the analytical-FE is proposed. Furthermore, empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD) are contrasted with the LOD by gear crack fault vibration signals. The analysis results indicate that the proposed method performs effectively and feasibility for the tooth crack stiffness calculation and the gear tooth crack fault diagnosis.

Perceptions about gender-based discrimination in a selection of South African companies / Renier Steyn

OpenAIRE

Steyn, Renier

2014-01-01

Introduction: From a legal point of view, gender-based discrimination is not condoned in the workplace. However, perceptions that such discrimination exists persist. Understanding the extent and nature of the phenomenon may contribute to the management thereof. Aim: The aim of this research was to report on the nature and level of workplace gender-based discrimination from the perspective of managers and employees, as well as by making use of objective measures. Method: Interviews were conduc...

Tensor Rank Preserving Discriminant Analysis for Facial Recognition.

Science.gov (United States)

Tao, Dapeng; Guo, Yanan; Li, Yaotang; Gao, Xinbo

2017-10-12

Facial recognition, one of the basic topics in computer vision and pattern recognition, has received substantial attention in recent years. However, for those traditional facial recognition algorithms, the facial images are reshaped to a long vector, thereby losing part of the original spatial constraints of each pixel. In this paper, a new tensor-based feature extraction algorithm termed tensor rank preserving discriminant analysis (TRPDA) for facial image recognition is proposed; the proposed method involves two stages: in the first stage, the low-dimensional tensor subspace of the original input tensor samples was obtained; in the second stage, discriminative locality alignment was utilized to obtain the ultimate vector feature representation for subsequent facial recognition. On the one hand, the proposed TRPDA algorithm fully utilizes the natural structure of the input samples, and it applies an optimization criterion that can directly handle the tensor spectral analysis problem, thereby decreasing the computation cost compared those traditional tensor-based feature selection algorithms. On the other hand, the proposed TRPDA algorithm extracts feature by finding a tensor subspace that preserves most of the rank order information of the intra-class input samples. Experiments on the three facial databases are performed here to determine the effectiveness of the proposed TRPDA algorithm.

Non-destructive Testing of Wood Defects Based on Discriminant Analysis Method

Directory of Open Access Journals (Sweden)

Wenshu LIN

2015-09-01

Full Text Available The defects of wood samples were tested by the technique of stress wave and ultrasonic technology, and the testing results were comparatively analyzed by using the Fisher discriminant analysis in the statistic software of SPSS. The differences of defect detection sensitivity and accuracy for stress wave and ultrasonic under different wood properties and defects were concluded. Therefore, in practical applications, according to different situations the corresponding wood non- destructive testing method should be used, or the two detection methods are applied at the same time in order to compensate for its shortcomings with each other to improve the ability to distinguish the timber defects. The results can provide a reference for further improvement of the reliability of timber defects detection.

Chinese License Plates Recognition Method Based on A Robust and Efficient Feature Extraction and BPNN Algorithm

Science.gov (United States)

Zhang, Ming; Xie, Fei; Zhao, Jing; Sun, Rui; Zhang, Lei; Zhang, Yue

2018-04-01

The prosperity of license plate recognition technology has made great contribution to the development of Intelligent Transport System (ITS). In this paper, a robust and efficient license plate recognition method is proposed which is based on a combined feature extraction model and BPNN (Back Propagation Neural Network) algorithm. Firstly, the candidate region of the license plate detection and segmentation method is developed. Secondly, a new feature extraction model is designed considering three sets of features combination. Thirdly, the license plates classification and recognition method using the combined feature model and BPNN algorithm is presented. Finally, the experimental results indicate that the license plate segmentation and recognition both can be achieved effectively by the proposed algorithm. Compared with three traditional methods, the recognition accuracy of the proposed method has increased to 95.7% and the consuming time has decreased to 51.4ms.

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.

Bloodstain detection and discrimination impacted by spectral shift when using an interference filter-based visible and near-infrared multispectral crime scene imaging system

Science.gov (United States)

Yang, Jie; Messinger, David W.; Dube, Roger R.

2018-03-01

Bloodstain detection and discrimination from nonblood substances on various substrates are critical in forensic science as bloodstains are a critical source for confirmatory DNA tests. Conventional bloodstain detection methods often involve time-consuming sample preparation, a chance of harm to investigators, the possibility of destruction of blood samples, and acquisition of too little data at crime scenes either in the field or in the laboratory. An imaging method has the advantages of being nondestructive, noncontact, real-time, and covering a large field-of-view. The abundant spectral information provided by multispectral imaging makes it a potential presumptive bloodstain detection and discrimination method. This article proposes an interference filter (IF) based area scanning three-spectral-band crime scene imaging system used for forensic bloodstain detection and discrimination. The impact of large angle of views on the spectral shift of calibrated IFs is determined, for both detecting and discriminating bloodstains from visually similar substances on multiple substrates. Spectral features in the visible and near-infrared portion employed by the relative band depth method are used. This study shows that 1 ml bloodstain on black felt, gray felt, red felt, white cotton, white polyester, and raw wood can be detected. Bloodstains on the above substrates can be discriminated from cola, coffee, ketchup, orange juice, red wine, and green tea.

Feature Selection and Blind Source Separation in an EEG-Based Brain-Computer Interface

Directory of Open Access Journals (Sweden)

Michael H. Thaut

2005-11-01

Full Text Available Most EEG-based BCI systems make use of well-studied patterns of brain activity. However, those systems involve tasks that indirectly map to simple binary commands such as “yes” or “no” or require many weeks of biofeedback training. We hypothesized that signal processing and machine learning methods can be used to discriminate EEG in a direct “yes”/“no” BCI from a single session. Blind source separation (BSS and spectral transformations of the EEG produced a 180-dimensional feature space. We used a modified genetic algorithm (GA wrapped around a support vector machine (SVM classifier to search the space of feature subsets. The GA-based search found feature subsets that outperform full feature sets and random feature subsets. Also, BSS transformations of the EEG outperformed the original time series, particularly in conjunction with a subset search of both spaces. The results suggest that BSS and feature selection can be used to improve the performance of even a “direct,” single-session BCI.

Testing for Statistical Discrimination based on Gender

DEFF Research Database (Denmark)

Lesner, Rune Vammen

. It is shown that the implications of both screening discrimination and stereotyping are consistent with observable wage dynamics. In addition, it is found that the gender wage gap decreases in tenure but increases in job transitions and that the fraction of women in high-ranking positions within a firm does......This paper develops a model which incorporates the two most commonly cited strands of the literature on statistical discrimination, namely screening discrimination and stereotyping. The model is used to provide empirical evidence of statistical discrimination based on gender in the labour market...... not affect the level of statistical discrimination by gender....

Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning.

Science.gov (United States)

Wang, Jinhua; Yang, Xi; Cai, Hongmin; Tan, Wanchang; Jin, Cangzheng; Li, Li

2016-06-07

Microcalcification is an effective indicator of early breast cancer. To improve the diagnostic accuracy of microcalcifications, this study evaluates the performance of deep learning-based models on large datasets for its discrimination. A semi-automated segmentation method was used to characterize all microcalcifications. A discrimination classifier model was constructed to assess the accuracies of microcalcifications and breast masses, either in isolation or combination, for classifying breast lesions. Performances were compared to benchmark models. Our deep learning model achieved a discriminative accuracy of 87.3% if microcalcifications were characterized alone, compared to 85.8% with a support vector machine. The accuracies were 61.3% for both methods with masses alone and improved to 89.7% and 85.8% after the combined analysis with microcalcifications. Image segmentation with our deep learning model yielded 15, 26 and 41 features for the three scenarios, respectively. Overall, deep learning based on large datasets was superior to standard methods for the discrimination of microcalcifications. Accuracy was increased by adopting a combinatorial approach to detect microcalcifications and masses simultaneously. This may have clinical value for early detection and treatment of breast cancer.

Discriminant method for the optimization of radionuclide activity in studies of nuclear medicine

International Nuclear Information System (INIS)

Perez Diaz, Marlen

2003-01-01

It is presented a method for the optimization of the radionuclidic activity to administer to mature patients in studies of Nuclear Medicine. The method is based in technical of discriminant analysis to build a function that discriminates groups with image quality differed on the base of physical parameters as they are the contrast image and the aleatory noise. The image quality is the dependent variable and it is selected by means of experts' evaluation and technical of clustering. The function is a lineal combination of a reduced group of variables physical-medical, able to discriminate the groups starting from a big group of variables measures. The method allows, also, to establish the relative weight of each discriminant variable selected . The behavior of the same ones is analyzed among studies carried out with different administered activity, with the objective of determining the minimum value of this that still allows good results in the image quality (Approach of activity optimization). It is validated the method by means of results comparison with the grateful Curved ROC in studies carried out with the Mannequins of Jaszczak (for planar studies) and of Insert Heart (for studies of SPECT). The optim activity value of the 99mTc, obtained with the application of the method, was coincident with the one obtained after the application of the method ROC to 6 expert observers as much in planar studies as in SPECT for two different cameras gamma. The method was applied later on in static, dynamic studies and of SPECT carried out with camera gamma to a mature population of 210 patient. The decisive variables of the quality of the image were obtained in the nuclear venticulography in rest, the bony gammagraphy, the nuclear renogram, the renal gammagraphy and the cerebral SPECT, as well as some activity values optimized for the equipment conditions and available radiopharmac in the country, allowing to establish a better commitment relationship between image quality

A CNN-Based Fusion Method for Feature Extraction from Sentinel Data

Directory of Open Access Journals (Sweden)

Giuseppe Scarpa

2018-02-01

Full Text Available Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative is to benefit from weather-insensitive synthetic aperture radar (SAR images. In many real-world applications, critical decisions are made based on some informative optical or radar features related to items such as water, vegetation or soil. Under cloudy conditions, however, optical-based features are not available, and they are commonly reconstructed through linear interpolation between data available at temporally-close time instants. In this work, we propose to estimate missing optical features through data fusion and deep-learning. Several sources of information are taken into account—optical sequences, SAR sequences, digital elevation model—so as to exploit both temporal and cross-sensor dependencies. Based on these data and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI, using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May–November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baseline methods according to all performance indicators.

Feature-based Alignment of Volumetric Multi-modal Images

Science.gov (United States)

Toews, Matthew; Zöllei, Lilla; Wells, William M.

2014-01-01

This paper proposes a method for aligning image volumes acquired from different imaging modalities (e.g. MR, CT) based on 3D scale-invariant image features. A novel method for encoding invariant feature geometry and appearance is developed, based on the assumption of locally linear intensity relationships, providing a solution to poor repeatability of feature detection in different image modalities. The encoding method is incorporated into a probabilistic feature-based model for multi-modal image alignment. The model parameters are estimated via a group-wise alignment algorithm, that iteratively alternates between estimating a feature-based model from feature data, then realigning feature data to the model, converging to a stable alignment solution with few pre-processing or pre-alignment requirements. The resulting model can be used to align multi-modal image data with the benefits of invariant feature correspondence: globally optimal solutions, high efficiency and low memory usage. The method is tested on the difficult RIRE data set of CT, T1, T2, PD and MP-RAGE brain images of subjects exhibiting significant inter-subject variability due to pathology. PMID:24683955

Narrowing down the conditions for extinction of Pavlovian feature-positive discriminations in humans.

Science.gov (United States)

van Vooren, Priya R; Franssen, Mathijs; Beckers, Tom; Hermans, Dirk; Baeyens, Frank

2012-12-01

The aim of this study was to delineate the minimal conditions for extinction of Pavlovian modulation in humans. Previous experiments at our lab showed that, after X-- A+/A- acquisition training, X- trials did not extinguish differential X-- A+/A- responding, while X-- A- trials did. Additionally, X-- A- extinction training seemed only to extinguish differential X-- A+/A- responding, while leaving differential responding on a concurrently trained Y [Symbol: see text] B+/B- discrimination intact. It thus seemed that the X-- A+/A- discrimination can only be extinguished by X-- A- extinction trials. (Rescorla, Journal of Experimental Psychology: Animal Behavior Processes 12, 16-24, 1986), on the other hand, found that the minimal conditions for extinction were broader in pigeons: Namely, he found that an acquired X-- A+/A- discrimination could be extinguished by presenting the original feature X in combination with a different target (B) that was minimally trained as an exciter. We thus wanted to examine whether this was also the case in humans. We found that nonreinforced X-- B- presentations did not abolish discriminative X-- A/A responding when target B was a nonreinforced stimulus. Nonreinforced X-- B- trials did extinguish the X-- A+/A- discrimination when target B had previously been trained as a target for modulation (X-- B+/B- or Y [Symbol: see text] B+/B- training) or as a reinforced exciter (B+). Our results thusf parallel and extend those in nonhuman animals (Rescorla, Journal of Experimental Psychology: Animal Behavior Processes 12, 16-24, 1986).

Perceptions of gender-based discrimination during surgical training and practice.

Science.gov (United States)

Bruce, Adrienne N; Battista, Alexis; Plankey, Michael W; Johnson, Lynt B; Marshall, M Blair

2015-01-01

Women represent 15% of practicing general surgeons. Gender-based discrimination has been implicated as discouraging women from surgery. We sought to determine women's perceptions of gender-based discrimination in the surgical training and working environment. Following IRB approval, we fielded a pilot survey measuring perceptions and impact of gender-based discrimination in medical school, residency training, and surgical practice. It was sent electronically to 1,065 individual members of the Association of Women Surgeons. We received 334 responses from medical students, residents, and practicing physicians with a response rate of 31%. Eighty-seven percent experienced gender-based discrimination in medical school, 88% in residency, and 91% in practice. Perceived sources of gender-based discrimination included superiors, physician peers, clinical support staff, and patients, with 40% emanating from women and 60% from men. The majority of responses indicated perceived gender-based discrimination during medical school, residency, and practice. Gender-based discrimination comes from both sexes and has a significant impact on women surgeons.

Classification of Error-Diffused Halftone Images Based on Spectral Regression Kernel Discriminant Analysis

Directory of Open Access Journals (Sweden)

Zhigao Zeng

2016-01-01

Full Text Available This paper proposes a novel algorithm to solve the challenging problem of classifying error-diffused halftone images. We firstly design the class feature matrices, after extracting the image patches according to their statistics characteristics, to classify the error-diffused halftone images. Then, the spectral regression kernel discriminant analysis is used for feature dimension reduction. The error-diffused halftone images are finally classified using an idea similar to the nearest centroids classifier. As demonstrated by the experimental results, our method is fast and can achieve a high classification accuracy rate with an added benefit of robustness in tackling noise.

A Thin Plate Spline-Based Feature-Preserving Method for Reducing Elevation Points Derived from LiDAR

Directory of Open Access Journals (Sweden)

Chuanfa Chen

2015-09-01

Full Text Available Light detection and ranging (LiDAR technique is currently one of the most important tools for collecting elevation points with a high density in the context of digital elevation model (DEM construction. However, the high density data always leads to serious time and memory consumption problems in data processing. In this paper, we have developed a thin plate spline (TPS-based feature-preserving (TPS-F method for LiDAR-derived ground data reduction by selecting a certain amount of significant terrain points and by extracting geomorphological features from the raw dataset to maintain the accuracy of constructed DEMs as high as possible, while maximally keeping terrain features. We employed four study sites with different topographies (i.e., flat, undulating, hilly and mountainous terrains to analyze the performance of TPS-F for LiDAR data reduction in the context of DEM construction. These results were compared with those of the TPS-based algorithm without features (TPS-W and two classical data selection methods including maximum z-tolerance (Max-Z and the random method. Results show that irrespective of terrain characteristic, the two versions of TPS-based approaches (i.e., TPS-F and TPS-W are always more accurate than the classical methods in terms of error range and root means square error. Moreover, in terms of streamline matching rate (SMR, TPS-F has a better ability of preserving geomorphological features, especially for the mountainous terrain. For example, the average SMR of TPS-F is 89.2% in the mountainous area, while those of TPS-W, max-Z and the random method are 56.6%, 34.7% and 35.3%, respectively.

A model for abnormal activity recognition and alert generation system for elderly care by hidden conditional random fields using R-transform and generalized discriminant analysis features.

Science.gov (United States)

Khan, Zafar Ali; Sohn, Won

2012-10-01

The growing population of elderly people living alone increases the need for automatic healthcare monitoring systems for elderly care. Automatic vision sensor-based systems are increasingly used for human activity recognition (HAR) in recent years. This study presents an improved model, tested using actors, of a sensor-based HAR system to recognize daily life activities of elderly people at home and generate an alert in case of abnormal HAR. Datasets consisting of six abnormal activities (falling backward, falling forward, falling rightward, falling leftward, chest pain, and fainting) and four normal activities (walking, rushing, sitting down, and standing up) are generated from different view angles (90°, -90°, 45°, -45°). Feature extraction and dimensions reduction are performed by R-transform followed by generalized discriminant analysis (GDA) methods. R-transform extracts symmetric, scale, and translation-invariant features from the sequences of activities. GDA increases the discrimination between different classes of highly similar activities. Silhouette sequences are quantified by the Linde-Buzo-Gray algorithm and recognized by hidden conditional random fields. Experimental results provide an average recognition rate of 94.2% for abnormal activities and 92.7% for normal activities. The recognition rate for the highly similar activities from different view angles shows the flexibility and efficacy of the proposed abnormal HAR and alert generation system for elderly care.

A stereo remote sensing feature selection method based on artificial bee colony algorithm

Science.gov (United States)

Yan, Yiming; Liu, Pigang; Zhang, Ye; Su, Nan; Tian, Shu; Gao, Fengjiao; Shen, Yi

2014-05-01

To improve the efficiency of stereo information for remote sensing classification, a stereo remote sensing feature selection method is proposed in this paper presents, which is based on artificial bee colony algorithm. Remote sensing stereo information could be described by digital surface model (DSM) and optical image, which contain information of the three-dimensional structure and optical characteristics, respectively. Firstly, three-dimensional structure characteristic could be analyzed by 3D-Zernike descriptors (3DZD). However, different parameters of 3DZD could descript different complexity of three-dimensional structure, and it needs to be better optimized selected for various objects on the ground. Secondly, features for representing optical characteristic also need to be optimized. If not properly handled, when a stereo feature vector composed of 3DZD and image features, that would be a lot of redundant information, and the redundant information may not improve the classification accuracy, even cause adverse effects. To reduce information redundancy while maintaining or improving the classification accuracy, an optimized frame for this stereo feature selection problem is created, and artificial bee colony algorithm is introduced for solving this optimization problem. Experimental results show that the proposed method can effectively improve the computational efficiency, improve the classification accuracy.

In silico and experimental evaluation of DNA-based detection methods for the ability to discriminate almond from other Prunus spp.

Science.gov (United States)

Brežná, Barbara; Šmíd, Jiří; Costa, Joana; Radvanszky, Jan; Mafra, Isabel; Kuchta, Tomáš

2015-04-01

Ten published DNA-based analytical methods aiming at detecting material of almond (Prunus dulcis) were in silico evaluated for potential cross-reactivity with other stone fruits (Prunus spp.), including peach, apricot, plum, cherry, sour cherry and Sargent cherry. For most assays, the analysis of nucleotide databases suggested none or insufficient discrimination of at least some stone fruits. On the other hand, the assay targeting non-specific lipid transfer protein (Röder et al., 2011, Anal Chim Acta 685:74-83) was sufficiently discriminative, judging from nucleotide alignments. Empirical evaluation was performed for three of the published methods, one modification of a commercial kit (SureFood allergen almond) and one attempted novel method targeting thaumatin-like protein gene. Samples of leaves and kernels were used in the experiments. The empirical results were favourable for the method from Röder et al. (2011) and a modification of SureFood allergen almond kit, both showing cross-reactivity <10(-3) compared to the model almond. Copyright © 2014 Elsevier Ltd. All rights reserved.

Classification of passive auditory event-related potentials using discriminant analysis and self-organizing feature maps.

Science.gov (United States)

Schönweiler, R; Wübbelt, P; Tolloczko, R; Rose, C; Ptok, M

2000-01-01

Discriminant analysis (DA) and self-organizing feature maps (SOFM) were used to classify passively evoked auditory event-related potentials (ERP) P(1), N(1), P(2) and N(2). Responses from 16 children with severe behavioral auditory perception deficits, 16 children with marked behavioral auditory perception deficits, and 14 controls were examined. Eighteen ERP amplitude parameters were selected for examination of statistical differences between the groups. Different DA methods and SOFM configurations were trained to the values. SOFM had better classification results than DA methods. Subsequently, measures on another 37 subjects that were unknown for the trained SOFM were used to test the reliability of the system. With 10-dimensional vectors, reliable classifications were obtained that matched behavioral auditory perception deficits in 96%, implying central auditory processing disorder (CAPD). The results also support the assumption that CAPD includes a 'non-peripheral' auditory processing deficit. Copyright 2000 S. Karger AG, Basel.

Bias and Stability of Single Variable Classifiers for Feature Ranking and Selection.

Science.gov (United States)

Fakhraei, Shobeir; Soltanian-Zadeh, Hamid; Fotouhi, Farshad

2014-11-01

Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices.

An Application of Discriminant Analysis to Pattern Recognition of Selected Contaminated Soil Features in Thin Sections

DEFF Research Database (Denmark)

Ribeiro, Alexandra B.; Nielsen, Allan Aasbjerg

1997-01-01

qualitative microprobe results: present elements Al, Si, Cr, Fe, As (associated with others). Selected groups of calibrated images (same light conditions and magnification) submitted to discriminant analysis, in order to find a pattern of recognition in the soil features corresponding to contamination already...

KFC2: a knowledge-based hot spot prediction method based on interface solvation, atomic density, and plasticity features.

Science.gov (United States)

Zhu, Xiaolei; Mitchell, Julie C

2011-09-01

Hot spots constitute a small fraction of protein-protein interface residues, yet they account for a large fraction of the binding affinity. Based on our previous method (KFC), we present two new methods (KFC2a and KFC2b) that outperform other methods at hot spot prediction. A number of improvements were made in developing these new methods. First, we created a training data set that contained a similar number of hot spot and non-hot spot residues. In addition, we generated 47 different features, and different numbers of features were used to train the models to avoid over-fitting. Finally, two feature combinations were selected: One (used in KFC2a) is composed of eight features that are mainly related to solvent accessible surface area and local plasticity; the other (KFC2b) is composed of seven features, only two of which are identical to those used in KFC2a. The two models were built using support vector machines (SVM). The two KFC2 models were then tested on a mixed independent test set, and compared with other methods such as Robetta, FOLDEF, HotPoint, MINERVA, and KFC. KFC2a showed the highest predictive accuracy for hot spot residues (True Positive Rate: TPR = 0.85); however, the false positive rate was somewhat higher than for other models. KFC2b showed the best predictive accuracy for hot spot residues (True Positive Rate: TPR = 0.62) among all methods other than KFC2a, and the False Positive Rate (FPR = 0.15) was comparable with other highly predictive methods. Copyright © 2011 Wiley-Liss, Inc.

The use of the discriminant analysis method for e π μ separation in BES

International Nuclear Information System (INIS)

Jiang Zhijin; Wang Taijie; Xie Yigang; Huang Tao

1994-01-01

We use the discriminant analysis method in multivariate statistical theory to handle the e π μ separation in BES, describing the principle of the discriminant analysis method, deriving the unstandardized discriminant functions (responsible for particle separation), giving the discriminant efficiency for e π μ and comparing the results from the discriminant analysis method with those obtained in a conventional way. ((orig.))

Discriminative Multi-View Interactive Image Re-Ranking.

Science.gov (United States)

Li, Jun; Xu, Chang; Yang, Wankou; Sun, Changyin; Tao, Dacheng

2017-07-01

Given an unreliable visual patterns and insufficient query information, content-based image retrieval is often suboptimal and requires image re-ranking using auxiliary information. In this paper, we propose a discriminative multi-view interactive image re-ranking (DMINTIR), which integrates user relevance feedback capturing users' intentions and multiple features that sufficiently describe the images. In DMINTIR, heterogeneous property features are incorporated in the multi-view learning scheme to exploit their complementarities. In addition, a discriminatively learned weight vector is obtained to reassign updated scores and target images for re-ranking. Compared with other multi-view learning techniques, our scheme not only generates a compact representation in the latent space from the redundant multi-view features but also maximally preserves the discriminative information in feature encoding by the large-margin principle. Furthermore, the generalization error bound of the proposed algorithm is theoretically analyzed and shown to be improved by the interactions between the latent space and discriminant function learning. Experimental results on two benchmark data sets demonstrate that our approach boosts baseline retrieval quality and is competitive with the other state-of-the-art re-ranking strategies.

Automatic discrimination between safe and unsafe swallowing using a reputation-based classifier

Directory of Open Access Journals (Sweden)

Nikjoo Mohammad S

2011-11-01

Full Text Available Abstract Background Swallowing accelerometry has been suggested as a potential non-invasive tool for bedside dysphagia screening. Various vibratory signal features and complementary measurement modalities have been put forth in the literature for the potential discrimination between safe and unsafe swallowing. To date, automatic classification of swallowing accelerometry has exclusively involved a single-axis of vibration although a second axis is known to contain additional information about the nature of the swallow. Furthermore, the only published attempt at automatic classification in adult patients has been based on a small sample of swallowing vibrations. Methods In this paper, a large corpus of dual-axis accelerometric signals were collected from 30 older adults (aged 65.47 ± 13.4 years, 15 male referred to videofluoroscopic examination on the suspicion of dysphagia. We invoked a reputation-based classifier combination to automatically categorize the dual-axis accelerometric signals into safe and unsafe swallows, as labeled via videofluoroscopic review. From these participants, a total of 224 swallowing samples were obtained, 164 of which were labeled as unsafe swallows (swallows where the bolus entered the airway and 60 as safe swallows. Three separate support vector machine (SVM classifiers and eight different features were selected for classification. Results With selected time, frequency and information theoretic features, the reputation-based algorithm distinguished between safe and unsafe swallowing with promising accuracy (80.48 ± 5.0%, high sensitivity (97.1 ± 2% and modest specificity (64 ± 8.8%. Interpretation of the most discriminatory features revealed that in general, unsafe swallows had lower mean vibration amplitude and faster autocorrelation decay, suggestive of decreased hyoid excursion and compromised coordination, respectively. Further, owing to its performance-based weighting of component classifiers, the static

Multiview Discriminative Geometry Preserving Projection for Image Classification

Directory of Open Access Journals (Sweden)

Ziqiang Wang

2014-01-01

Full Text Available In many image classification applications, it is common to extract multiple visual features from different views to describe an image. Since different visual features have their own specific statistical properties and discriminative powers for image classification, the conventional solution for multiple view data is to concatenate these feature vectors as a new feature vector. However, this simple concatenation strategy not only ignores the complementary nature of different views, but also ends up with “curse of dimensionality.” To address this problem, we propose a novel multiview subspace learning algorithm in this paper, named multiview discriminative geometry preserving projection (MDGPP for feature extraction and classification. MDGPP can not only preserve the intraclass geometry and interclass discrimination information under a single view, but also explore the complementary property of different views to obtain a low-dimensional optimal consensus embedding by using an alternating-optimization-based iterative algorithm. Experimental results on face recognition and facial expression recognition demonstrate the effectiveness of the proposed algorithm.

Identification of discriminant proteins through antibody profiling, methods and apparatus for identifying an individual

Science.gov (United States)

Thompson, Vicki S; Lacey, Jeffrey A; Gentillon, Cynthia A; Apel, William A

2015-03-03

A method for determining a plurality of proteins for discriminating and positively identifying an individual based from a biological sample. The method may include profiling a biological sample from a plurality of individuals against a protein array including a plurality of proteins. The protein array may include proteins attached to a support in a preselected pattern such that locations of the proteins are known. The biological sample may be contacted with the protein array such that a portion of antibodies in the biological sample reacts with and binds to the proteins forming immune complexes. A statistical analysis method, such as discriminant analysis, may be performed to determine discriminating proteins for distinguishing individuals. Proteins of interest may be used to form a protein array. Such a protein array may be used, for example, to compare a forensic sample from an unknown source with a sample from a known source.

Identification of discriminant proteins through antibody profiling, methods and apparatus for identifying an individual

Energy Technology Data Exchange (ETDEWEB)

Apel, William A.; Thompson, Vicki S; Lacey, Jeffrey A.; Gentillon, Cynthia A.

2016-08-09

A method for determining a plurality of proteins for discriminating and positively identifying an individual based from a biological sample. The method may include profiling a biological sample from a plurality of individuals against a protein array including a plurality of proteins. The protein array may include proteins attached to a support in a preselected pattern such that locations of the proteins are known. The biological sample may be contacted with the protein array such that a portion of antibodies in the biological sample reacts with and binds to the proteins forming immune complexes. A statistical analysis method, such as discriminant analysis, may be performed to determine discriminating proteins for distinguishing individuals. Proteins of interest may be used to form a protein array. Such a protein array may be used, for example, to compare a forensic sample from an unknown source with a sample from a known source.

Low-Resolution Tactile Image Recognition for Automated Robotic Assembly Using Kernel PCA-Based Feature Fusion and Multiple Kernel Learning-Based Support Vector Machine

Directory of Open Access Journals (Sweden)

Yi-Hung Liu

2014-01-01

Full Text Available In this paper, we propose a robust tactile sensing image recognition scheme for automatic robotic assembly. First, an image reprocessing procedure is designed to enhance the contrast of the tactile image. In the second layer, geometric features and Fourier descriptors are extracted from the image. Then, kernel principal component analysis (kernel PCA is applied to transform the features into ones with better discriminating ability, which is the kernel PCA-based feature fusion. The transformed features are fed into the third layer for classification. In this paper, we design a classifier by combining the multiple kernel learning (MKL algorithm and support vector machine (SVM. We also design and implement a tactile sensing array consisting of 10-by-10 sensing elements. Experimental results, carried out on real tactile images acquired by the designed tactile sensing array, show that the kernel PCA-based feature fusion can significantly improve the discriminating performance of the geometric features and Fourier descriptors. Also, the designed MKL-SVM outperforms the regular SVM in terms of recognition accuracy. The proposed recognition scheme is able to achieve a high recognition rate of over 85% for the classification of 12 commonly used metal parts in industrial applications.

Orthogonal sparse linear discriminant analysis

Science.gov (United States)

Liu, Zhonghua; Liu, Gang; Pu, Jiexin; Wang, Xiaohong; Wang, Haijun

2018-03-01

Linear discriminant analysis (LDA) is a linear feature extraction approach, and it has received much attention. On the basis of LDA, researchers have done a lot of research work on it, and many variant versions of LDA were proposed. However, the inherent problem of LDA cannot be solved very well by the variant methods. The major disadvantages of the classical LDA are as follows. First, it is sensitive to outliers and noises. Second, only the global discriminant structure is preserved, while the local discriminant information is ignored. In this paper, we present a new orthogonal sparse linear discriminant analysis (OSLDA) algorithm. The k nearest neighbour graph is first constructed to preserve the locality discriminant information of sample points. Then, L2,1-norm constraint on the projection matrix is used to act as loss function, which can make the proposed method robust to outliers in data points. Extensive experiments have been performed on several standard public image databases, and the experiment results demonstrate the performance of the proposed OSLDA algorithm.

Quantification of organ motion based on an adaptive image-based scale invariant feature method

Energy Technology Data Exchange (ETDEWEB)

Paganelli, Chiara [Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, piazza L. Da Vinci 32, Milano 20133 (Italy); Peroni, Marta [Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, piazza L. Da Vinci 32, Milano 20133, Italy and Paul Scherrer Institut, Zentrum für Protonentherapie, WMSA/C15, CH-5232 Villigen PSI (Italy); Baroni, Guido; Riboldi, Marco [Dipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, piazza L. Da Vinci 32, Milano 20133, Italy and Bioengineering Unit, Centro Nazionale di Adroterapia Oncologica, strada Campeggi 53, Pavia 27100 (Italy)

2013-11-15

Purpose: The availability of corresponding landmarks in IGRT image series allows quantifying the inter and intrafractional motion of internal organs. In this study, an approach for the automatic localization of anatomical landmarks is presented, with the aim of describing the nonrigid motion of anatomo-pathological structures in radiotherapy treatments according to local image contrast.Methods: An adaptive scale invariant feature transform (SIFT) was developed from the integration of a standard 3D SIFT approach with a local image-based contrast definition. The robustness and invariance of the proposed method to shape-preserving and deformable transforms were analyzed in a CT phantom study. The application of contrast transforms to the phantom images was also tested, in order to verify the variation of the local adaptive measure in relation to the modification of image contrast. The method was also applied to a lung 4D CT dataset, relying on manual feature identification by an expert user as ground truth. The 3D residual distance between matches obtained in adaptive-SIFT was then computed to verify the internal motion quantification with respect to the expert user. Extracted corresponding features in the lungs were used as regularization landmarks in a multistage deformable image registration (DIR) mapping the inhale vs exhale phase. The residual distances between the warped manual landmarks and their reference position in the inhale phase were evaluated, in order to provide a quantitative indication of the registration performed with the three different point sets.Results: The phantom study confirmed the method invariance and robustness properties to shape-preserving and deformable transforms, showing residual matching errors below the voxel dimension. The adapted SIFT algorithm on the 4D CT dataset provided automated and accurate motion detection of peak to peak breathing motion. The proposed method resulted in reduced residual errors with respect to standard SIFT

Automatic detection of suspicious behavior of pickpockets with track-based features in a shopping mall

Science.gov (United States)

Bouma, Henri; Baan, Jan; Burghouts, Gertjan J.; Eendebak, Pieter T.; van Huis, Jasper R.; Dijk, Judith; van Rest, Jeroen H. C.

2014-10-01

Proactive detection of incidents is required to decrease the cost of security incidents. This paper focusses on the automatic early detection of suspicious behavior of pickpockets with track-based features in a crowded shopping mall. Our method consists of several steps: pedestrian tracking, feature computation and pickpocket recognition. This is challenging because the environment is crowded, people move freely through areas which cannot be covered by a single camera, because the actual snatch is a subtle action, and because collaboration is complex social behavior. We carried out an experiment with more than 20 validated pickpocket incidents. We used a top-down approach to translate expert knowledge in features and rules, and a bottom-up approach to learn discriminating patterns with a classifier. The classifier was used to separate the pickpockets from normal passers-by who are shopping in the mall. We performed a cross validation to train and evaluate our system. In this paper, we describe our method, identify the most valuable features, and analyze the results that were obtained in the experiment. We estimate the quality of these features and the performance of automatic detection of (collaborating) pickpockets. The results show that many of the pickpockets can be detected at a low false alarm rate.

Invariant Feature Matching for Image Registration Application Based on New Dissimilarity of Spatial Features

Science.gov (United States)

Mousavi Kahaki, Seyed Mostafa; Nordin, Md Jan; Ashtari, Amir H.; J. Zahra, Sophia

2016-01-01

An invariant feature matching method is proposed as a spatially invariant feature matching approach. Deformation effects, such as affine and homography, change the local information within the image and can result in ambiguous local information pertaining to image points. New method based on dissimilarity values, which measures the dissimilarity of the features through the path based on Eigenvector properties, is proposed. Evidence shows that existing matching techniques using similarity metrics—such as normalized cross-correlation, squared sum of intensity differences and correlation coefficient—are insufficient for achieving adequate results under different image deformations. Thus, new descriptor’s similarity metrics based on normalized Eigenvector correlation and signal directional differences, which are robust under local variation of the image information, are proposed to establish an efficient feature matching technique. The method proposed in this study measures the dissimilarity in the signal frequency along the path between two features. Moreover, these dissimilarity values are accumulated in a 2D dissimilarity space, allowing accurate corresponding features to be extracted based on the cumulative space using a voting strategy. This method can be used in image registration applications, as it overcomes the limitations of the existing approaches. The output results demonstrate that the proposed technique outperforms the other methods when evaluated using a standard dataset, in terms of precision-recall and corner correspondence. PMID:26985996

Invariant Feature Matching for Image Registration Application Based on New Dissimilarity of Spatial Features.

Directory of Open Access Journals (Sweden)

Seyed Mostafa Mousavi Kahaki

Full Text Available An invariant feature matching method is proposed as a spatially invariant feature matching approach. Deformation effects, such as affine and homography, change the local information within the image and can result in ambiguous local information pertaining to image points. New method based on dissimilarity values, which measures the dissimilarity of the features through the path based on Eigenvector properties, is proposed. Evidence shows that existing matching techniques using similarity metrics--such as normalized cross-correlation, squared sum of intensity differences and correlation coefficient--are insufficient for achieving adequate results under different image deformations. Thus, new descriptor's similarity metrics based on normalized Eigenvector correlation and signal directional differences, which are robust under local variation of the image information, are proposed to establish an efficient feature matching technique. The method proposed in this study measures the dissimilarity in the signal frequency along the path between two features. Moreover, these dissimilarity values are accumulated in a 2D dissimilarity space, allowing accurate corresponding features to be extracted based on the cumulative space using a voting strategy. This method can be used in image registration applications, as it overcomes the limitations of the existing approaches. The output results demonstrate that the proposed technique outperforms the other methods when evaluated using a standard dataset, in terms of precision-recall and corner correspondence.

Perceived ethnic and language-based discrimination and Latina immigrant women's health.

Science.gov (United States)

Halim, May Ling; Moy, Keith H; Yoshikawa, Hirokazu

2017-01-01

Perceiving ethnic discrimination can have aversive consequences for health. However, little is known about whether perceiving language-based (how one speaks a second language) discrimination poses the same risks. This study examined whether perceptions of language-based and ethnic discrimination are associated with mental and physical health. Among 132 Mexican and Dominican immigrant women, perceiving ethnic and language-based discrimination each predicted psychological distress and poorer physical health. When examined together, only ethnic discrimination remained a significant predictor. These results emphasize the importance of understanding how perceived ethnic and language-based discrimination play an integral role in the health of Latina immigrant women.

Joint probability discrimination between stationary tissue and blood velocity signals

DEFF Research Database (Denmark)

Schlaikjer, Malene; Jensen, Jørgen Arendt

2001-01-01

before and after echo-canceling, and (b) the amplitude variations between samples in consecutive RF-signals before and after echo-canceling. The statistical discriminator was obtained by computing the probability density functions (PDFs) for each feature through histogram analysis of data....... This study presents a new statistical discriminator. Investigation of the RF-signals reveals that features can be derived that distinguish the segments of the signal, which do an do not carry information on the blood flow. In this study 4 features, have been determined: (a) the energy content in the segments....... The discrimination is performed by determining the joint probability of the features for the segment under investigation and choosing the segment type that is most likely. The method was tested on simulated data resembling RF-signals from the carotid artery....

Pulse discrimination of scintillator detector with artificial neural network

International Nuclear Information System (INIS)

Chen Man; Cai Yuerong; Yang Chaowen

2006-01-01

The features of signal for scintillator detectors are analyzed. According to the difference in the fraction of slow and fast scintillation for different particles, three intrinsic parameters (signal amplitude, integration of signal during rinsing, integration of frequency spectrum of signals in middle frequencies) of signals are defined. The artificial neural network method for pulse discrimination of scintillator detector is studied. The signals with different shapes under real condition are simulated with computer, and discriminated by the method. Results of discrimination are gotten and discussed. (authors)

Selective Sensing of Gas Mixture via a Temperature Modulation Approach: New Strategy for Potentiometric Gas Sensor Obtaining Satisfactory Discriminating Features.

Science.gov (United States)

Li, Fu-An; Jin, Han; Wang, Jinxia; Zou, Jie; Jian, Jiawen

2017-03-12

A new strategy to discriminate four types of hazardous gases is proposed in this research. Through modulating the operating temperature and the processing response signal with a pattern recognition algorithm, a gas sensor consisting of a single sensing electrode, i.e., ZnO/In₂O₃ composite, is designed to differentiate NO₂, NH₃, C₃H₆, CO within the level of 50-400 ppm. Results indicate that with adding 15 wt.% ZnO to In₂O₃, the sensor fabricated at 900 °C shows optimal sensing characteristics in detecting all the studied gases. Moreover, with the aid of the principle component analysis (PCA) algorithm, the sensor operating in the temperature modulation mode demonstrates acceptable discrimination features. The satisfactory discrimination features disclose the future that it is possible to differentiate gas mixture efficiently through operating a single electrode sensor at temperature modulation mode.

Local labor markets and taste-based discrimination

Directory of Open Access Journals (Sweden)

Clémence Berson

2016-04-01

Full Text Available Abstract This article appeals to heterogeneity in workers’ non-wage preferences to model taste-based discrimination. Firms hire both types of workers and pay lower wages to minority workers, whatever their taste for discrimination. A single prejudiced firm in the market produces a substantial wage gap in all firms. Consequently, discrimination allows unprejudiced firms to make non-zero profits, so that they have little incentive to drive out prejudiced firms. As the market does not eliminate discrimination, state intervention is required. Indirect policies do not affect the absolute wage gap between the two groups, but may be more likely to be used than direct policies.

NetProt: Complex-based Feature Selection.

Science.gov (United States)

Goh, Wilson Wen Bin; Wong, Limsoon

2017-08-04

Protein complex-based feature selection (PCBFS) provides unparalleled reproducibility with high phenotypic relevance on proteomics data. Currently, there are five PCBFS paradigms, but not all representative methods have been implemented or made readily available. To allow general users to take advantage of these methods, we developed the R-package NetProt, which provides implementations of representative feature-selection methods. NetProt also provides methods for generating simulated differential data and generating pseudocomplexes for complex-based performance benchmarking. The NetProt open source R package is available for download from https://github.com/gohwils/NetProt/releases/ , and online documentation is available at http://rpubs.com/gohwils/204259 .

Discriminative clustering on manifold for adaptive transductive classification.

Science.gov (United States)

Zhang, Zhao; Jia, Lei; Zhang, Min; Li, Bing; Zhang, Li; Li, Fanzhang

2017-10-01

In this paper, we mainly propose a novel adaptive transductive label propagation approach by joint discriminative clustering on manifolds for representing and classifying high-dimensional data. Our framework seamlessly combines the unsupervised manifold learning, discriminative clustering and adaptive classification into a unified model. Also, our method incorporates the adaptive graph weight construction with label propagation. Specifically, our method is capable of propagating label information using adaptive weights over low-dimensional manifold features, which is different from most existing studies that usually predict the labels and construct the weights in the original Euclidean space. For transductive classification by our formulation, we first perform the joint discriminative K-means clustering and manifold learning to capture the low-dimensional nonlinear manifolds. Then, we construct the adaptive weights over the learnt manifold features, where the adaptive weights are calculated through performing the joint minimization of the reconstruction errors over features and soft labels so that the graph weights can be joint-optimal for data representation and classification. Using the adaptive weights, we can easily estimate the unknown labels of samples. After that, our method returns the updated weights for further updating the manifold features. Extensive simulations on image classification and segmentation show that our proposed algorithm can deliver the state-of-the-art performance on several public datasets. Copyright © 2017 Elsevier Ltd. All rights reserved.

W-transform method for feature-oriented multiresolution image retrieval

Energy Technology Data Exchange (ETDEWEB)

Kwong, M.K.; Lin, B. [Argonne National Lab., IL (United States). Mathematics and Computer Science Div.

1995-07-01

Image database management is important in the development of multimedia technology. Since an enormous amount of digital images is likely to be generated within the next few decades in order to integrate computers, television, VCR, cables, telephone and various imaging devices. Effective image indexing and retrieval systems are urgently needed so that images can be easily organized, searched, transmitted, and presented. Here, the authors present a local-feature-oriented image indexing and retrieval method based on Kwong, and Tang`s W-transform. Multiresolution histogram comparison is an effective method for content-based image indexing and retrieval. However, most recent approaches perform multiresolution analysis for whole images but do not exploit the local features present in the images. Since W-transform is featured by its ability to handle images of arbitrary size, with no periodicity assumptions, it provides a natural tool for analyzing local image features and building indexing systems based on such features. In this approach, the histograms of the local features of images are used in the indexing, system. The system not only can retrieve images that are similar or identical to the query images but also can retrieve images that contain features specified in the query images, even if the retrieved images as a whole might be very different from the query images. The local-feature-oriented method also provides a speed advantage over the global multiresolution histogram comparison method. The feature-oriented approach is expected to be applicable in managing large-scale image systems such as video databases and medical image databases.

A New Feature Extraction Method Based on EEMD and Multi-Scale Fuzzy Entropy for Motor Bearing

Directory of Open Access Journals (Sweden)

Huimin Zhao

2016-12-01

Full Text Available Feature extraction is one of the most important, pivotal, and difficult problems in mechanical fault diagnosis, which directly relates to the accuracy of fault diagnosis and the reliability of early fault prediction. Therefore, a new fault feature extraction method, called the EDOMFE method based on integrating ensemble empirical mode decomposition (EEMD, mode selection, and multi-scale fuzzy entropy is proposed to accurately diagnose fault in this paper. The EEMD method is used to decompose the vibration signal into a series of intrinsic mode functions (IMFs with a different physical significance. The correlation coefficient analysis method is used to calculate and determine three improved IMFs, which are close to the original signal. The multi-scale fuzzy entropy with the ability of effective distinguishing the complexity of different signals is used to calculate the entropy values of the selected three IMFs in order to form a feature vector with the complexity measure, which is regarded as the inputs of the support vector machine (SVM model for training and constructing a SVM classifier (EOMSMFD based on EDOMFE and SVM for fulfilling fault pattern recognition. Finally, the effectiveness of the proposed method is validated by real bearing vibration signals of the motor with different loads and fault severities. The experiment results show that the proposed EDOMFE method can effectively extract fault features from the vibration signal and that the proposed EOMSMFD method can accurately diagnose the fault types and fault severities for the inner race fault, the outer race fault, and rolling element fault of the motor bearing. Therefore, the proposed method provides a new fault diagnosis technology for rotating machinery.

A New Method for Weak Fault Feature Extraction Based on Improved MED

Directory of Open Access Journals (Sweden)

Junlin Li

2018-01-01

Full Text Available Because of the characteristics of weak signal and strong noise, the low-speed vibration signal fault feature extraction has been a hot spot and difficult problem in the field of equipment fault diagnosis. Moreover, the traditional minimum entropy deconvolution (MED method has been proved to be used to detect such fault signals. The MED uses objective function method to design the filter coefficient, and the appropriate threshold value should be set in the calculation process to achieve the optimal iteration effect. It should be pointed out that the improper setting of the threshold will cause the target function to be recalculated, and the resulting error will eventually affect the distortion of the target function in the background of strong noise. This paper presents an improved MED based method of fault feature extraction from rolling bearing vibration signals that originate in high noise environments. The method uses the shuffled frog leaping algorithm (SFLA, finds the set of optimal filter coefficients, and eventually avoids the artificial error influence of selecting threshold parameter. Therefore, the fault bearing under the two rotating speeds of 60 rpm and 70 rpm is selected for verification with typical low-speed fault bearing as the research object; the results show that SFLA-MED extracts more obvious bearings and has a higher signal-to-noise ratio than the prior MED method.

Dysphonic Voice Pattern Analysis of Patients in Parkinson’s Disease Using Minimum Interclass Probability Risk Feature Selection and Bagging Ensemble Learning Methods

Directory of Open Access Journals (Sweden)

Yunfeng Wu

2017-01-01

Full Text Available Analysis of quantified voice patterns is useful in the detection and assessment of dysphonia and related phonation disorders. In this paper, we first study the linear correlations between 22 voice parameters of fundamental frequency variability, amplitude variations, and nonlinear measures. The highly correlated vocal parameters are combined by using the linear discriminant analysis method. Based on the probability density functions estimated by the Parzen-window technique, we propose an interclass probability risk (ICPR method to select the vocal parameters with small ICPR values as dominant features and compare with the modified Kullback-Leibler divergence (MKLD feature selection approach. The experimental results show that the generalized logistic regression analysis (GLRA, support vector machine (SVM, and Bagging ensemble algorithm input with the ICPR features can provide better classification results than the same classifiers with the MKLD selected features. The SVM is much better at distinguishing normal vocal patterns with a specificity of 0.8542. Among the three classification methods, the Bagging ensemble algorithm with ICPR features can identify 90.77% vocal patterns, with the highest sensitivity of 0.9796 and largest area value of 0.9558 under the receiver operating characteristic curve. The classification results demonstrate the effectiveness of our feature selection and pattern analysis methods for dysphonic voice detection and measurement.

Discrimination of the rare medicinal plant Dendrobium officinale based on naringenin, bibenzyl, and polysaccharides.

Science.gov (United States)

Chen, Xiaomei; Wang, Fangfei; Wang, Yunqiang; Li, Xuelan; Wang, Airong; Wang, Chunlan; Guo, Shunxing

2012-12-01

The aim of this study was to establish a method for discriminating Dendrobium officinale from four of its close relatives Dendrobium chrysanthum, Dendrobium crystallinum, Dendrobium aphyllum and Dendrobium devonianum based on chemical composition analysis. We analyzed 62 samples of 24 Dendrobium species. High performance liquid chromatography analysis confirmed that the four low molecular weight compounds 4',5,7-trihydroxyflavanone (naringenin), 3,4-dihydroxy-4',5-dime-thoxybibenzyl (DDB-2), 3',4-dihydroxy-3,5'-dimethoxybibenzyl (gigantol), and 4,4'-dihydroxy-3,3',5-trimethoxybibenzy (moscatilin), were common in the genus. The phenol-sulfuric acid method was used to quantify polysaccharides, and the monosaccharide composition of the polysaccharides was determined by gas chromatography. Stepwise discriminant analysis was used to differentiate among the five closely related species based on the chemical composition analysis. This proved to be a simple and accurate approach for discriminating among these species. The results also showed that the polysaccharide content, the amounts of the four low molecular weight compounds, and the mannose to glucose ratio, were important factors for species discriminant. Therefore, we propose that a chemical analysis based on quantification of naringenin, bibenzyl, and polysaccharides is effective for identifying D. officinale.

Classification of Alzheimer's disease patients with hippocampal shape wrapper-based feature selection and support vector machine

Science.gov (United States)

Young, Jonathan; Ridgway, Gerard; Leung, Kelvin; Ourselin, Sebastien

2012-02-01

It is well known that hippocampal atrophy is a marker of the onset of Alzheimer's disease (AD) and as a result hippocampal volumetry has been used in a number of studies to provide early diagnosis of AD and predict conversion of mild cognitive impairment patients to AD. However, rates of atrophy are not uniform across the hippocampus making shape analysis a potentially more accurate biomarker. This study studies the hippocampi from 226 healthy controls, 148 AD patients and 330 MCI patients obtained from T1 weighted structural MRI images from the ADNI database. The hippocampi are anatomically segmented using the MAPS multi-atlas segmentation method, and the resulting binary images are then processed with SPHARM software to decompose their shapes as a weighted sum of spherical harmonic basis functions. The resulting parameterizations are then used as feature vectors in Support Vector Machine (SVM) classification. A wrapper based feature selection method was used as this considers the utility of features in discriminating classes in combination, fully exploiting the multivariate nature of the data and optimizing the selected set of features for the type of classifier that is used. The leave-one-out cross validated accuracy obtained on training data is 88.6% for classifying AD vs controls and 74% for classifying MCI-converters vs MCI-stable with very compact feature sets, showing that this is a highly promising method. There is currently a considerable fall in accuracy on unseen data indicating that the feature selection is sensitive to the data used, however feature ensemble methods may overcome this.

[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.

Video Scene Parsing with Predictive Feature Learning

OpenAIRE

Jin, Xiaojie; Li, Xin; Xiao, Huaxin; Shen, Xiaohui; Lin, Zhe; Yang, Jimei; Chen, Yunpeng; Dong, Jian; Liu, Luoqi; Jie, Zequn; Feng, Jiashi; Yan, Shuicheng

2016-01-01

In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing framework. (1) \\textbf{Predictive feature learning}} from nearly unlimited unlabeled video data. Different from existing methods learning features from single frame parsing, we learn spatiotemporal discriminative features by enforcing a parsing network to ...

Selection of morphological features of pollen grains for chosen tree taxa

Directory of Open Access Journals (Sweden)

Agnieszka Kubik-Komar

2018-05-01

Full Text Available The basis of aerobiological studies is to monitor airborne pollen concentrations and pollen season timing. This task is performed by appropriately trained staff and is difficult and time consuming. The goal of this research is to select morphological characteristics of grains that are the most discriminative for distinguishing between birch, hazel and alder taxa and are easy to determine automatically from microscope images. This selection is based on the split attributes of the J4.8 classification trees built for different subsets of features. Determining the discriminative features by this method, we provide specific rules for distinguishing between individual taxa, at the same time obtaining a high percentage of correct classification. The most discriminative among the 13 morphological characteristics studied are the following: number of pores, maximum axis, minimum axis, axes difference, maximum oncus width, and number of lateral pores. The classification result of the tree based on this subset is better than the one built on the whole feature set and it is almost 94%. Therefore, selection of attributes before tree building is recommended. The classification results for the features easiest to obtain from the image, i.e. maximum axis, minimum axis, axes difference, and number of lateral pores, are only 2.09 pp lower than those obtained for the complete set, but 3.23 pp lower than the results obtained for the selected most discriminating attributes only.

Comparison of n-γ discrimination by zero-crossing and digital charge comparison methods

International Nuclear Information System (INIS)

Wolski, D.; Moszynski, M.; Ludziejewski, T.; Johnson, A.; Klamra, W.; Skeppstedt, Oe.

1995-01-01

A comparative study of the n-γ discrimination done by the digital charge comparison and zero-crossing methods was carried out for a 130 mm in diameter and 130 mm high BC501A liquid scintillator coupled to a 130 mm diameter XP4512B photomultiplier. The high quality of the tested detector was reflected in a photoelectron yield of 2300±100 phe/MeV and excellent n-γ discrimination properties with energy discrimination thresholds corresponding to very low neutron (or electron) energies. The superiority of the Z/C method was demonstrated for the n-γ discrimination method alone, as well as, for the simultaneous separation by the pulse shape discrimination and the time-of-flight methods down to about 30 keV recoil electron energy. The digital charge comparison method fails for a large dynamic range of energy and its separation is weakly improved by time-of-flight method for low energies. (orig.)

Comparison of features response in texture-based iris segmentation

CSIR Research Space (South Africa)

Bachoo, A

2009-03-01

Full Text Available the Fisher linear discriminant and the iris region of interest is extracted. Four texture description methods are compared for segmenting iris texture using a region based pattern classification approach: Grey Level Co-occurrence Matrix (GLCM), Discrete...

Stego Keys Performance on Feature Based Coding Method in Text Domain

Directory of Open Access Journals (Sweden)

Din Roshidi

2017-01-01

Full Text Available A main critical factor on embedding process in any text steganography method is a key used known as stego key. This factor will be influenced the success of the embedding process of text steganography method to hide a message from third party or any adversary. One of the important aspects on embedding process in text steganography method is the fitness performance of the stego key. Three parameters of the fitness performance of the stego key have been identified such as capacity ratio, embedded fitness ratio and saving space ratio. It is because a better as capacity ratio, embedded fitness ratio and saving space ratio offers of any stego key; a more message can be hidden. Therefore, main objective of this paper is to analyze three features coding based namely CALP, VERT and QUAD of stego keys in text steganography on their capacity ratio, embedded fitness ratio and saving space ratio. It is found that CALP method give a good effort performance compared to VERT and QUAD methods.

Face Recognition Performance Improvement using a Similarity Score of Feature Vectors based on Probabilistic Histograms

Directory of Open Access Journals (Sweden)

SRIKOTE, G.

2016-08-01

Full Text Available This paper proposes an improved performance algorithm of face recognition to identify two face mismatch pairs in cases of incorrect decisions. The primary feature of this method is to deploy the similarity score with respect to Gaussian components between two previously unseen faces. Unlike the conventional classical vector distance measurement, our algorithms also consider the plot of summation of the similarity index versus face feature vector distance. A mixture of Gaussian models of labeled faces is also widely applicable to different biometric system parameters. By comparative evaluations, it has been shown that the efficiency of the proposed algorithm is superior to that of the conventional algorithm by an average accuracy of up to 1.15% and 16.87% when compared with 3x3 Multi-Region Histogram (MRH direct-bag-of-features and Principal Component Analysis (PCA-based face recognition systems, respectively. The experimental results show that similarity score consideration is more discriminative for face recognition compared to feature distance. Experimental results of Labeled Face in the Wild (LFW data set demonstrate that our algorithms are suitable for real applications probe-to-gallery identification of face recognition systems. Moreover, this proposed method can also be applied to other recognition systems and therefore additionally improves recognition scores.

Hybrid generative-discriminative approach to age-invariant face recognition

Science.gov (United States)

Sajid, Muhammad; Shafique, Tamoor

2018-03-01

Age-invariant face recognition is still a challenging research problem due to the complex aging process involving types of facial tissues, skin, fat, muscles, and bones. Most of the related studies that have addressed the aging problem are focused on generative representation (aging simulation) or discriminative representation (feature-based approaches). Designing an appropriate hybrid approach taking into account both the generative and discriminative representations for age-invariant face recognition remains an open problem. We perform a hybrid matching to achieve robustness to aging variations. This approach automatically segments the eyes, nose-bridge, and mouth regions, which are relatively less sensitive to aging variations compared with the rest of the facial regions that are age-sensitive. The aging variations of age-sensitive facial parts are compensated using a demographic-aware generative model based on a bridged denoising autoencoder. The age-insensitive facial parts are represented by pixel average vector-based local binary patterns. Deep convolutional neural networks are used to extract relative features of age-sensitive and age-insensitive facial parts. Finally, the feature vectors of age-sensitive and age-insensitive facial parts are fused to achieve the recognition results. Extensive experimental results on morphological face database II (MORPH II), face and gesture recognition network (FG-NET), and Verification Subset of cross-age celebrity dataset (CACD-VS) demonstrate the effectiveness of the proposed method for age-invariant face recognition well.

A new digital method for high precision neutron-gamma discrimination with liquid scintillation detectors

International Nuclear Information System (INIS)

Nakhostin, M

2013-01-01

A new pulse-shape discrimination algorithm for neutron and gamma (n/γ) discrimination with liquid scintillation detectors has been developed, leading to a considerable improvement of n/γ separation quality. The method is based on triangular pulse shaping which offers a high sensitivity to the shape of input pulses, as well as, excellent noise filtering characteristics. A clear separation of neutrons and γ-rays down to a scintillation light yield of about 65 keVee (electron equivalent energy) with a dynamic range of 45:1 was achieved. The method can potentially operate at high counting rates and is well suited for real-time measurements.

Support vector machine-based facial-expression recognition method combining shape and appearance

Science.gov (United States)

Han, Eun Jung; Kang, Byung Jun; Park, Kang Ryoung; Lee, Sangyoun

2010-11-01

Facial expression recognition can be widely used for various applications, such as emotion-based human-machine interaction, intelligent robot interfaces, face recognition robust to expression variation, etc. Previous studies have been classified as either shape- or appearance-based recognition. The shape-based method has the disadvantage that the individual variance of facial feature points exists irrespective of similar expressions, which can cause a reduction of the recognition accuracy. The appearance-based method has a limitation in that the textural information of the face is very sensitive to variations in illumination. To overcome these problems, a new facial-expression recognition method is proposed, which combines both shape and appearance information, based on the support vector machine (SVM). This research is novel in the following three ways as compared to previous works. First, the facial feature points are automatically detected by using an active appearance model. From these, the shape-based recognition is performed by using the ratios between the facial feature points based on the facial-action coding system. Second, the SVM, which is trained to recognize the same and different expression classes, is proposed to combine two matching scores obtained from the shape- and appearance-based recognitions. Finally, a single SVM is trained to discriminate four different expressions, such as neutral, a smile, anger, and a scream. By determining the expression of the input facial image whose SVM output is at a minimum, the accuracy of the expression recognition is much enhanced. The experimental results showed that the recognition accuracy of the proposed method was better than previous researches and other fusion methods.

Spatial mode discriminator based on leaky waveguides

Science.gov (United States)

Xu, Jing; Liu, Jialing; Shi, Hongkang; Chen, Yuntian

2018-06-01

We propose a conceptually simple and experimentally compatible configuration to discriminate the spatial mode based on leaky waveguides, which are inserted in-between the transmission link. The essence of such a spatial mode discriminator is to introduce the leakage of the power flux on purpose for detection. Importantly, the leaky angle of each individual spatial mode with respect to the propagation direction are different for non-degenerated modes, while the radiation patterns of the degenerated spatial modes in the plane perpendicular to the propagation direction are also distinguishable. Based on these two facts, we illustrate the operation principle of the spatial mode discriminators via two concrete examples; a w-type slab leaky waveguide without degeneracy, and a cylindrical leaky waveguide with degeneracy. The correlation between the leakage angle and the spatial mode distribution for a slab leaky waveguide, as well as differences between the in-plane radiation patterns of degenerated modes in a cylindrical leaky waveguide, are verified numerically and analytically. Such findings can be readily useful in discriminating the spatial modes for optical communication or optical sensing.

Dimensionality Reduction of Hyperspectral Image with Graph-Based Discriminant Analysis Considering Spectral Similarity

Directory of Open Access Journals (Sweden)

Fubiao Feng

2017-03-01

Full Text Available Recently, graph embedding has drawn great attention for dimensionality reduction in hyperspectral imagery. For example, locality preserving projection (LPP utilizes typical Euclidean distance in a heat kernel to create an affinity matrix and projects the high-dimensional data into a lower-dimensional space. However, the Euclidean distance is not sufficiently correlated with intrinsic spectral variation of a material, which may result in inappropriate graph representation. In this work, a graph-based discriminant analysis with spectral similarity (denoted as GDA-SS measurement is proposed, which fully considers curves changing description among spectral bands. Experimental results based on real hyperspectral images demonstrate that the proposed method is superior to traditional methods, such as supervised LPP, and the state-of-the-art sparse graph-based discriminant analysis (SGDA.

Image segmentation-based robust feature extraction for color image watermarking

Science.gov (United States)

Li, Mianjie; Deng, Zeyu; Yuan, Xiaochen

2018-04-01

This paper proposes a local digital image watermarking method based on Robust Feature Extraction. The segmentation is achieved by Simple Linear Iterative Clustering (SLIC) based on which an Image Segmentation-based Robust Feature Extraction (ISRFE) method is proposed for feature extraction. Our method can adaptively extract feature regions from the blocks segmented by SLIC. This novel method can extract the most robust feature region in every segmented image. Each feature region is decomposed into low-frequency domain and high-frequency domain by Discrete Cosine Transform (DCT). Watermark images are then embedded into the coefficients in the low-frequency domain. The Distortion-Compensated Dither Modulation (DC-DM) algorithm is chosen as the quantization method for embedding. The experimental results indicate that the method has good performance under various attacks. Furthermore, the proposed method can obtain a trade-off between high robustness and good image quality.

Abnormality detection of mammograms by discriminative dictionary learning on DSIFT descriptors.

Science.gov (United States)

Tavakoli, Nasrin; Karimi, Maryam; Nejati, Mansour; Karimi, Nader; Reza Soroushmehr, S M; Samavi, Shadrokh; Najarian, Kayvan

2017-07-01

Detection and classification of breast lesions using mammographic images are one of the most difficult studies in medical image processing. A number of learning and non-learning methods have been proposed for detecting and classifying these lesions. However, the accuracy of the detection/classification still needs improvement. In this paper we propose a powerful classification method based on sparse learning to diagnose breast cancer in mammograms. For this purpose, a supervised discriminative dictionary learning approach is applied on dense scale invariant feature transform (DSIFT) features. A linear classifier is also simultaneously learned with the dictionary which can effectively classify the sparse representations. Our experimental results show the superior performance of our method compared to existing approaches.

Multi-dimension feature fusion for action recognition

Science.gov (United States)

Dong, Pei; Li, Jie; Dong, Junyu; Qi, Lin

2018-04-01

Typical human actions last several seconds and exhibit characteristic spatio-temporal structure. The challenge for action recognition is to capture and fuse the multi-dimension information in video data. In order to take into account these characteristics simultaneously, we present a novel method that fuses multiple dimensional features, such as chromatic images, depth and optical flow fields. We built our model based on the multi-stream deep convolutional networks with the help of temporal segment networks and extract discriminative spatial and temporal features by fusing ConvNets towers multi-dimension, in which different feature weights are assigned in order to take full advantage of this multi-dimension information. Our architecture is trained and evaluated on the currently largest and most challenging benchmark NTU RGB-D dataset. The experiments demonstrate that the performance of our method outperforms the state-of-the-art methods.

Gadolinium-Based GaN for Neutron Detection with Gamma Discrimination

Science.gov (United States)

2016-06-01

Gadolinium-Based GaN for Neutron Detection with Gamma Discrimination Distribution Statement A. Approved for public release; distribution is...Final Technical Report BRBAA08-Per5-Y-1-2-0030 Title: “Gadolinium-Based GaN for Neutron Detection with Gamma Discrimination ” Grant...Analysis  .............................................................................................  23   6.   Gamma-ray Discrimination

Identification of DNA-Binding Proteins Using Mixed Feature Representation Methods.

Science.gov (United States)

Qu, Kaiyang; Han, Ke; Wu, Song; Wang, Guohua; Wei, Leyi

2017-09-22

DNA-binding proteins play vital roles in cellular processes, such as DNA packaging, replication, transcription, regulation, and other DNA-associated activities. The current main prediction method is based on machine learning, and its accuracy mainly depends on the features extraction method. Therefore, using an efficient feature representation method is important to enhance the classification accuracy. However, existing feature representation methods cannot efficiently distinguish DNA-binding proteins from non-DNA-binding proteins. In this paper, a multi-feature representation method, which combines three feature representation methods, namely, K-Skip-N-Grams, Information theory, and Sequential and structural features (SSF), is used to represent the protein sequences and improve feature representation ability. In addition, the classifier is a support vector machine. The mixed-feature representation method is evaluated using 10-fold cross-validation and a test set. Feature vectors, which are obtained from a combination of three feature extractions, show the best performance in 10-fold cross-validation both under non-dimensional reduction and dimensional reduction by max-relevance-max-distance. Moreover, the reduced mixed feature method performs better than the non-reduced mixed feature technique. The feature vectors, which are a combination of SSF and K-Skip-N-Grams, show the best performance in the test set. Among these methods, mixed features exhibit superiority over the single features.

Identification of DNA-Binding Proteins Using Mixed Feature Representation Methods

Directory of Open Access Journals (Sweden)

Kaiyang Qu

2017-09-01

Full Text Available DNA-binding proteins play vital roles in cellular processes, such as DNA packaging, replication, transcription, regulation, and other DNA-associated activities. The current main prediction method is based on machine learning, and its accuracy mainly depends on the features extraction method. Therefore, using an efficient feature representation method is important to enhance the classification accuracy. However, existing feature representation methods cannot efficiently distinguish DNA-binding proteins from non-DNA-binding proteins. In this paper, a multi-feature representation method, which combines three feature representation methods, namely, K-Skip-N-Grams, Information theory, and Sequential and structural features (SSF, is used to represent the protein sequences and improve feature representation ability. In addition, the classifier is a support vector machine. The mixed-feature representation method is evaluated using 10-fold cross-validation and a test set. Feature vectors, which are obtained from a combination of three feature extractions, show the best performance in 10-fold cross-validation both under non-dimensional reduction and dimensional reduction by max-relevance-max-distance. Moreover, the reduced mixed feature method performs better than the non-reduced mixed feature technique. The feature vectors, which are a combination of SSF and K-Skip-N-Grams, show the best performance in the test set. Among these methods, mixed features exhibit superiority over the single features.

Discrimination of neutrons and γ-rays in liquid scintillators based of fuzzy c-means clustering

International Nuclear Information System (INIS)

Luo Xiaoliang; Liu Guofu; Yang Jun

2011-01-01

A novel method based on fuzzy c-means (FCM) clustering for the discrimination of neutrons and γ-rays in liquid scintillators was presented. The neutrons and γ-rays in the environment were firstly acquired by the portable real-time n-γ discriminator and then discriminated using fuzzy c-means clustering and pulse gradient analysis, respectively. By comparing the results with each other, it is shown that the discrimination results of the fuzzy c-means clustering are consistent with those of the pulse gradient analysis. The decrease in uncertainty and the improvement in discrimination performance of the fuzzy c-means clustering were also observed. (authors)

Functional discrimination of membrane proteins using machine learning techniques

Directory of Open Access Journals (Sweden)

Yabuki Yukimitsu

2008-03-01

Full Text Available Abstract Background Discriminating membrane proteins based on their functions is an important task in genome annotation. In this work, we have analyzed the characteristic features of amino acid residues in membrane proteins that perform major functions, such as channels/pores, electrochemical potential-driven transporters and primary active transporters. Results We observed that the residues Asp, Asn and Tyr are dominant in channels/pores whereas the composition of hydrophobic residues, Phe, Gly, Ile, Leu and Val is high in electrochemical potential-driven transporters. The composition of all the amino acids in primary active transporters lies in between other two classes of proteins. We have utilized different machine learning algorithms, such as, Bayes rule, Logistic function, Neural network, Support vector machine, Decision tree etc. for discriminating these classes of proteins. We observed that most of the algorithms have discriminated them with similar accuracy. The neural network method discriminated the channels/pores, electrochemical potential-driven transporters and active transporters with the 5-fold cross validation accuracy of 64% in a data set of 1718 membrane proteins. The application of amino acid occurrence improved the overall accuracy to 68%. In addition, we have discriminated transporters from other α-helical and β-barrel membrane proteins with the accuracy of 85% using k-nearest neighbor method. The classification of transporters and all other proteins (globular and membrane showed the accuracy of 82%. Conclusion The performance of discrimination with amino acid occurrence is better than that with amino acid composition. We suggest that this method could be effectively used to discriminate transporters from all other globular and membrane proteins, and classify them into channels/pores, electrochemical and active transporters.

The formation method of the feature space for the identification of fatigued bills

Science.gov (United States)

Kang, Dongshik; Oshiro, Ayumu; Ozawa, Kenji; Mitsui, Ikugo

2014-10-01

Fatigued bills make a trouble such as the paper jam in a bill handling machine. In the discrimination of fatigued bills using an acoustic signal, the variation of an observed bill sound is considered to be one of causes in misclassification. Therefore a technique has demanded in order to make the classification of fatigued bills more efficient. In this paper, we proposed the algorithm that extracted feature quantity of bill sound from acoustic signal using the frequency difference, and carried out discrimination experiment of fatigued bill money by Support Vector Machine(SVM). The feature quantity of frequency difference can represent the frequency components of an acoustic signal is varied by the fatigued degree of bill money. The generalization performance of SVM does not depend on the size of dimensions of the feature space, even in a high dimensional feature space such as bill-acoustic signals. Furthermore, SVM can induce an optimal classifier which considers the combination of features by the virtue of polynomial kernel functions.

Wearable Sensor-Based Human Activity Recognition Method with Multi-Features Extracted from Hilbert-Huang Transform.

Science.gov (United States)

Xu, Huile; Liu, Jinyi; Hu, Haibo; Zhang, Yi

2016-12-02

Wearable sensors-based human activity recognition introduces many useful applications and services in health care, rehabilitation training, elderly monitoring and many other areas of human interaction. Existing works in this field mainly focus on recognizing activities by using traditional features extracted from Fourier transform (FT) or wavelet transform (WT). However, these signal processing approaches are suitable for a linear signal but not for a nonlinear signal. In this paper, we investigate the characteristics of the Hilbert-Huang transform (HHT) for dealing with activity data with properties such as nonlinearity and non-stationarity. A multi-features extraction method based on HHT is then proposed to improve the effect of activity recognition. The extracted multi-features include instantaneous amplitude (IA) and instantaneous frequency (IF) by means of empirical mode decomposition (EMD), as well as instantaneous energy density (IE) and marginal spectrum (MS) derived from Hilbert spectral analysis. Experimental studies are performed to verify the proposed approach by using the PAMAP2 dataset from the University of California, Irvine for wearable sensors-based activity recognition. Moreover, the effect of combining multi-features vs. a single-feature are investigated and discussed in the scenario of a dependent subject. The experimental results show that multi-features combination can further improve the performance measures. Finally, we test the effect of multi-features combination in the scenario of an independent subject. Our experimental results show that we achieve four performance indexes: recall, precision, F-measure, and accuracy to 0.9337, 0.9417, 0.9353, and 0.9377 respectively, which are all better than the achievements of related works.

Characterization of mammographic masses based on level set segmentation with new image features and patient information

International Nuclear Information System (INIS)

Shi Jiazheng; Sahiner, Berkman; Chan Heangping; Ge Jun; Hadjiiski, Lubomir; Helvie, Mark A.; Nees, Alexis; Wu Yita; Wei Jun; Zhou Chuan; Zhang Yiheng; Cui Jing

2008-01-01

Computer-aided diagnosis (CAD) for characterization of mammographic masses as malignant or benign has the potential to assist radiologists in reducing the biopsy rate without increasing false negatives. The purpose of this study was to develop an automated method for mammographic mass segmentation and explore new image based features in combination with patient information in order to improve the performance of mass characterization. The authors' previous CAD system, which used the active contour segmentation, and morphological, textural, and spiculation features, has achieved promising results in mass characterization. The new CAD system is based on the level set method and includes two new types of image features related to the presence of microcalcifications with the mass and abruptness of the mass margin, and patient age. A linear discriminant analysis (LDA) classifier with stepwise feature selection was used to merge the extracted features into a classification score. The classification accuracy was evaluated using the area under the receiver operating characteristic curve. The authors' primary data set consisted of 427 biopsy-proven masses (200 malignant and 227 benign) in 909 regions of interest (ROIs) (451 malignant and 458 benign) from multiple mammographic views. Leave-one-case-out resampling was used for training and testing. The new CAD system based on the level set segmentation and the new mammographic feature space achieved a view-based A z value of 0.83±0.01. The improvement compared to the previous CAD system was statistically significant (p=0.02). When patient age was included in the new CAD system, view-based and case-based A z values were 0.85±0.01 and 0.87±0.02, respectively. The study also demonstrated the consistency of the newly developed CAD system by evaluating the statistics of the weights of the LDA classifiers in leave-one-case-out classification. Finally, an independent test on the publicly available digital database for screening

Analysis of the discriminative methods for diagnosis of benign and malignant solitary pulmonary nodules based on serum markers.

Science.gov (United States)

Wang, Wanping; Liu, Mingyue; Wang, Jing; Tian, Rui; Dong, Junqiang; Liu, Qi; Zhao, Xianping; Wang, Yuanfang

2014-01-01

Screening indexes of tumor serum markers for benign and malignant solitary pulmonary nodules (SPNs) were analyzed to find the optimum method for diagnosis. Enzyme-linked immunosorbent assays, an automatic immune analyzer and radioimmunoassay methods were used to examine the levels of 8 serum markers in 164 SPN patients, and the sensitivity for differential diagnosis of malignant or benign SPN was compared for detection using a single plasma marker or a combination of markers. The results for serological indicators that closely relate to benign and malignant SPNs were screened using the Fisher discriminant analysis and a non-conditional logistic regression analysis method, respectively. The results were then verified by the k-means clustering analysis method. The sensitivity when using a combination of serum markers to detect SPN was higher than that using a single marker. By Fisher discriminant analysis, cytokeratin 19 fragments (CYFRA21-1), carbohydrate antigen 125 (CA125), squamous cell carcinoma antigen (SCC) and breast cancer antigen (CA153), which relate to the benign and malignant SPNs, were screened. Through non-conditional logistic regression analysis, CYFRA21-1, SCC and CA153 were obtained. Using the k-means clustering analysis, the cophenetic correlation coefficient (0.940) obtained by the Fisher discriminant analysis was higher than that obtained with logistic regression analysis (0.875). This study indicated that the Fisher discriminant analysis functioned better in screening out serum markers to recognize the benign and malignant SPN. The combined detection of CYFRA21-1, CA125, SCC and CA153 is an effective way to distinguish benign and malignant SPN, and will find an important clinical application in the early diagnosis of SPN. © 2014 S. Karger GmbH, Freiburg.

Earthquake Building Damage Mapping Based on Feature Analyzing Method from Synthetic Aperture Radar Data

Science.gov (United States)

An, L.; Zhang, J.; Gong, L.

2018-04-01

Playing an important role in gathering information of social infrastructure damage, Synthetic Aperture Radar (SAR) remote sensing is a useful tool for monitoring earthquake disasters. With the wide application of this technique, a standard method, comparing post-seismic to pre-seismic data, become common. However, multi-temporal SAR processes, are not always achievable. To develop a post-seismic data only method for building damage detection, is of great importance. In this paper, the authors are now initiating experimental investigation to establish an object-based feature analysing classification method for building damage recognition.

Quantitative analysis of the clinical data on leukemia, 5. Specificity of clinical features in acute myelocytic leukemia with 8; 21 translocation by multiple logistic discriminant analysis

Energy Technology Data Exchange (ETDEWEB)

Ueoka, Hiroshi; Kamada, Nanao; Yamamoto, Hisashi; Ohtaki, Megu; Takimoto, Yasuo; Kuramoto, Atsushi; Munaka, Masaki

1984-11-01

In order to determine the necessity of chromosome analysis required for the evaluation of 8;21 translocation, multiple logistic discriminant analysis was made on 124 patients with acute non-lymphocytic leukemia experienced in the authors' institution. Variables which showed positive correlation with the presence of 8;21 translocation were the presence of Auer body and granular abnormality of the cells, numbers of peripheral promyelocytes, myelocytes and metamyelocytes, and bone marrow promyelocytes, myelocytes, and the sum of rods and segments. Those which showed negative correlation with 8;21 translocation were peripheral platelet count, neutrocytealkaline phosphatase (N-AP) score, numbers of eosinocytes, monocytes and erythroblasts, and erythroblasts on myelogram. Auer body, four peripheral hematological features (platelet count, N-AP score, metamyelocytes and monocytes), and three myelogram features (myelocytes, reticular cells and granulocytes/eosionocytes) were used for the multiple logistic discriminant analysis. By the analysis, 2 of the 22 patients (9.1%) with translocation were judged not to have 8;21 translocation and 3 of the 102 patients (2.9%) without translocation were judged to have it. Therefore, this multiple logistic discriminant method has proved to be simple and useful in clinically evaluating acute non-lymphocytic leukemia. (Namekawa, K.).

Scattering features for lung cancer detection in fibered confocal fluorescence microscopy images.

Science.gov (United States)

Rakotomamonjy, Alain; Petitjean, Caroline; Salaün, Mathieu; Thiberville, Luc

2014-06-01

To assess the feasibility of lung cancer diagnosis using fibered confocal fluorescence microscopy (FCFM) imaging technique and scattering features for pattern recognition. FCFM imaging technique is a new medical imaging technique for which interest has yet to be established for diagnosis. This paper addresses the problem of lung cancer detection using FCFM images and, as a first contribution, assesses the feasibility of computer-aided diagnosis through these images. Towards this aim, we have built a pattern recognition scheme which involves a feature extraction stage and a classification stage. The second contribution relies on the features used for discrimination. Indeed, we have employed the so-called scattering transform for extracting discriminative features, which are robust to small deformations in the images. We have also compared and combined these features with classical yet powerful features like local binary patterns (LBP) and their variants denoted as local quinary patterns (LQP). We show that scattering features yielded to better recognition performances than classical features like LBP and their LQP variants for the FCFM image classification problems. Another finding is that LBP-based and scattering-based features provide complementary discriminative information and, in some situations, we empirically establish that performance can be improved when jointly using LBP, LQP and scattering features. In this work we analyze the joint capability of FCFM images and scattering features for lung cancer diagnosis. The proposed method achieves a good recognition rate for such a diagnosis problem. It also performs well when used in conjunction with other features for other classical medical imaging classification problems. Copyright © 2014 Elsevier B.V. All rights reserved.

A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data

Directory of Open Access Journals (Sweden)

Himmelreich Uwe

2009-07-01

Full Text Available Abstract Background Regularized regression methods such as principal component or partial least squares regression perform well in learning tasks on high dimensional spectral data, but cannot explicitly eliminate irrelevant features. The random forest classifier with its associated Gini feature importance, on the other hand, allows for an explicit feature elimination, but may not be optimally adapted to spectral data due to the topology of its constituent classification trees which are based on orthogonal splits in feature space. Results We propose to combine the best of both approaches, and evaluated the joint use of a feature selection based on a recursive feature elimination using the Gini importance of random forests' together with regularized classification methods on spectral data sets from medical diagnostics, chemotaxonomy, biomedical analytics, food science, and synthetically modified spectral data. Here, a feature selection using the Gini feature importance with a regularized classification by discriminant partial least squares regression performed as well as or better than a filtering according to different univariate statistical tests, or using regression coefficients in a backward feature elimination. It outperformed the direct application of the random forest classifier, or the direct application of the regularized classifiers on the full set of features. Conclusion The Gini importance of the random forest provided superior means for measuring feature relevance on spectral data, but – on an optimal subset of features – the regularized classifiers might be preferable over the random forest classifier, in spite of their limitation to model linear dependencies only. A feature selection based on Gini importance, however, may precede a regularized linear classification to identify this optimal subset of features, and to earn a double benefit of both dimensionality reduction and the elimination of noise from the classification task.

Datum Feature Extraction and Deformation Analysis Method Based on Normal Vector of Point Cloud

Science.gov (United States)

Sun, W.; Wang, J.; Jin, F.; Liang, Z.; Yang, Y.

2018-04-01

In order to solve the problem lacking applicable analysis method in the application of three-dimensional laser scanning technology to the field of deformation monitoring, an efficient method extracting datum feature and analysing deformation based on normal vector of point cloud was proposed. Firstly, the kd-tree is used to establish the topological relation. Datum points are detected by tracking the normal vector of point cloud determined by the normal vector of local planar. Then, the cubic B-spline curve fitting is performed on the datum points. Finally, datum elevation and the inclination angle of the radial point are calculated according to the fitted curve and then the deformation information was analyzed. The proposed approach was verified on real large-scale tank data set captured with terrestrial laser scanner in a chemical plant. The results show that the method could obtain the entire information of the monitor object quickly and comprehensively, and reflect accurately the datum feature deformation.

Comparisons of Circular Transmit and Linear Receive Compact Polarimetric SAR Features for Oil Slicks Discrimination

Directory of Open Access Journals (Sweden)

Yu Li

2015-01-01

Full Text Available Compact polarimetric (CP synthetic aperture radar (SAR has proven its potential in distinguishing oil slicks and look-alikes. Polarimetric information can be retrieved directly from scattering vector or from reconstructed pseudo-Quad-Pol covariance matrix of CP SAR data. In this paper, we analysed features from Circular Transmit and Linear Receive (CTLR CP SAR data that are derived by taking both of these two methods. K-means clustering followed by accuracy assessment was also implemented for performance evaluation. Through experiments that were conducted based on L-band UAVSAR fully polarimetric data, it was found that optimum extraction methods varied for different features. The histogram analysis and segmentation results also demonstrated the comparable performance of CP SAR features in distinguishing different damping properties within oil slicks. This study proposed a framework of statistically analyzing polarimetric SAR (Pol-SAR features and provided guidelines for determining optimum feature extraction methods from CP SAR data and for marine oil-spills detection and classification.

Evaluation of feature selection algorithms for classification in temporal lobe epilepsy based on MR images

Science.gov (United States)

Lai, Chunren; Guo, Shengwen; Cheng, Lina; Wang, Wensheng; Wu, Kai

2017-02-01

It's very important to differentiate the temporal lobe epilepsy (TLE) patients from healthy people and localize the abnormal brain regions of the TLE patients. The cortical features and changes can reveal the unique anatomical patterns of brain regions from the structural MR images. In this study, structural MR images from 28 normal controls (NC), 18 left TLE (LTLE), and 21 right TLE (RTLE) were acquired, and four types of cortical feature, namely cortical thickness (CTh), cortical surface area (CSA), gray matter volume (GMV), and mean curvature (MCu), were explored for discriminative analysis. Three feature selection methods, the independent sample t-test filtering, the sparse-constrained dimensionality reduction model (SCDRM), and the support vector machine-recursive feature elimination (SVM-RFE), were investigated to extract dominant regions with significant differences among the compared groups for classification using the SVM classifier. The results showed that the SVM-REF achieved the highest performance (most classifications with more than 92% accuracy), followed by the SCDRM, and the t-test. Especially, the surface area and gray volume matter exhibited prominent discriminative ability, and the performance of the SVM was improved significantly when the four cortical features were combined. Additionally, the dominant regions with higher classification weights were mainly located in temporal and frontal lobe, including the inferior temporal, entorhinal cortex, fusiform, parahippocampal cortex, middle frontal and frontal pole. It was demonstrated that the cortical features provided effective information to determine the abnormal anatomical pattern and the proposed method has the potential to improve the clinical diagnosis of the TLE.

Evaluation of pattern recognition and feature extraction methods in ADHD prediction.

Directory of Open Access Journals (Sweden)

Joao Ricardo Sato

2012-09-01

Full Text Available Attention-Deficit/Hyperactivity Disorder is a neurodevelopmental disorder, being one of the most prevalent psychiatric disorders in childhood. The neural substrates associated with this condition, both from structural and functional perspectives, are not yet well established . Recent studies have highlighted the relevance of neuroimaging not only to provide a more solid understanding about the disorder but also for possible clinical support. The ADHD-200 Consortium organized the ADHD-200 global competition making publicly available, hundreds of structural magnetic resonance imaging (MRI and functional MRI (fMRI datasets of both ADHD patients and typically developing controls for research use. In the current study, we evaluate the predictive power of a set of three different feature extraction methods and 10 different pattern recognition methods. The features tested were regional homogeneity (ReHo, amplitude of low frequency fluctuations (ALFF and independent components analysis maps (RSN. Our findings suggest that the combination ALFF+ReHo maps contain relevant information to discriminate ADHD patients from typically developing controls, but with limited accuracy. All classifiers provided almost the same performance in this case. In addition, the combination ALFF+ReHo+RSN was relevant in combined vs inattentive ADHD classification, achieving a score accuracy of 67%. In this latter case, the performances of the classifiers were not equivalent and L2-regularized logistic regression (both in primal and dual space provided the most accurate predictions. The analysis of brain regions containing most discriminative information suggested that in both classifications (ADHD vs typically developing controls and combined vs inattentive, the relevant information is not confined only to a small set of regions but it is spatially distributed across the whole brain.

Discriminative Elastic-Net Regularized Linear Regression.

Science.gov (United States)

Zhang, Zheng; Lai, Zhihui; Xu, Yong; Shao, Ling; Wu, Jian; Xie, Guo-Sen

2017-03-01

In this paper, we aim at learning compact and discriminative linear regression models. Linear regression has been widely used in different problems. However, most of the existing linear regression methods exploit the conventional zero-one matrix as the regression targets, which greatly narrows the flexibility of the regression model. Another major limitation of these methods is that the learned projection matrix fails to precisely project the image features to the target space due to their weak discriminative capability. To this end, we present an elastic-net regularized linear regression (ENLR) framework, and develop two robust linear regression models which possess the following special characteristics. First, our methods exploit two particular strategies to enlarge the margins of different classes by relaxing the strict binary targets into a more feasible variable matrix. Second, a robust elastic-net regularization of singular values is introduced to enhance the compactness and effectiveness of the learned projection matrix. Third, the resulting optimization problem of ENLR has a closed-form solution in each iteration, which can be solved efficiently. Finally, rather than directly exploiting the projection matrix for recognition, our methods employ the transformed features as the new discriminate representations to make final image classification. Compared with the traditional linear regression model and some of its variants, our method is much more accurate in image classification. Extensive experiments conducted on publicly available data sets well demonstrate that the proposed framework can outperform the state-of-the-art methods. The MATLAB codes of our methods can be available at http://www.yongxu.org/lunwen.html.

Multi-level gene/MiRNA feature selection using deep belief nets and active learning.

Science.gov (United States)

Ibrahim, Rania; Yousri, Noha A; Ismail, Mohamed A; El-Makky, Nagwa M

2014-01-01

Selecting the most discriminative genes/miRNAs has been raised as an important task in bioinformatics to enhance disease classifiers and to mitigate the dimensionality curse problem. Original feature selection methods choose genes/miRNAs based on their individual features regardless of how they perform together. Considering group features instead of individual ones provides a better view for selecting the most informative genes/miRNAs. Recently, deep learning has proven its ability in representing the data in multiple levels of abstraction, allowing for better discrimination between different classes. However, the idea of using deep learning for feature selection is not widely used in the bioinformatics field yet. In this paper, a novel multi-level feature selection approach named MLFS is proposed for selecting genes/miRNAs based on expression profiles. The approach is based on both deep and active learning. Moreover, an extension to use the technique for miRNAs is presented by considering the biological relation between miRNAs and genes. Experimental results show that the approach was able to outperform classical feature selection methods in hepatocellular carcinoma (HCC) by 9%, lung cancer by 6% and breast cancer by around 10% in F1-measure. Results also show the enhancement in F1-measure of our approach over recently related work in [1] and [2].

Texture-based analysis of 100 MR examinations of head and neck tumors. Is it possible to discriminate between benign and malignant masses in a multicenter trial?

International Nuclear Information System (INIS)

Fruehwald-Pallamar, J.; Czerny, C.; Hesselink, J.R.; Mafee, M.F.; Holzer-Fruehwald, L.; Mayerhoefer, M.E.

2016-01-01

To evaluate whether texture-based analysis of standard MRI sequences can help in the discrimination between benign and malignant head and neck tumors. The MR images of 100 patients with a histologically clarified head or neck mass, from two different institutions, were analyzed. Texture-based analysis was performed using texture analysis software, with region of interest measurements for 2D and 3D evaluation independently for all axial sequences. COC, RUN, GRA, ARM, and WAV features were calculated for all ROIs. 10 texture feature subsets were used for a linear discriminant analysis, in combination with k-nearest-neighbor classification. Benign and malignant tumors were compared with regard to texture-based values. There were differences in the images from different field-strength scanners, as well as from different vendors. For the differentiation of benign and malignant tumors, we found differences on STIR and T2-weighted images for 2D, and on contrast-enhanced T1-TSE with fat saturation for 3D evaluation. In a separate analysis of the subgroups 1.5 and 3 Tesla, more discriminating features were found. Texture-based analysis is a useful tool in the discrimination of benign and malignant tumors when performed on one scanner with the same protocol. We cannot recommend this technique for the use of multicenter studies with clinical data.

Texture-based analysis of 100 MR examinations of head and neck tumors. Is it possible to discriminate between benign and malignant masses in a multicenter trial?

Energy Technology Data Exchange (ETDEWEB)

Fruehwald-Pallamar, J.; Czerny, C. [Medical University of Vienna (Austria). Subdiv. of Neuroradiology and Musculoskeletal Radiology; Hesselink, J.R.; Mafee, M.F. [UCSD Medical Center, San Diego, CA (United States). Dept. of Radiology; Holzer-Fruehwald, L.; Mayerhoefer, M.E. [Medical University of Vienna (Austria). Dept. of Biomedical Imaging and Image-Guided Therapy

2016-02-15

To evaluate whether texture-based analysis of standard MRI sequences can help in the discrimination between benign and malignant head and neck tumors. The MR images of 100 patients with a histologically clarified head or neck mass, from two different institutions, were analyzed. Texture-based analysis was performed using texture analysis software, with region of interest measurements for 2D and 3D evaluation independently for all axial sequences. COC, RUN, GRA, ARM, and WAV features were calculated for all ROIs. 10 texture feature subsets were used for a linear discriminant analysis, in combination with k-nearest-neighbor classification. Benign and malignant tumors were compared with regard to texture-based values. There were differences in the images from different field-strength scanners, as well as from different vendors. For the differentiation of benign and malignant tumors, we found differences on STIR and T2-weighted images for 2D, and on contrast-enhanced T1-TSE with fat saturation for 3D evaluation. In a separate analysis of the subgroups 1.5 and 3 Tesla, more discriminating features were found. Texture-based analysis is a useful tool in the discrimination of benign and malignant tumors when performed on one scanner with the same protocol. We cannot recommend this technique for the use of multicenter studies with clinical data.

Data Visualization and Feature Selection Methods in Gel-based Proteomics

DEFF Research Database (Denmark)

Silva, Tomé Santos; Richard, Nadege; Dias, Jorge P.

2014-01-01

-based proteomics, summarizing the current state of research within this field. Particular focus is given on discussing the usefulness of available multivariate analysis tools both for data visualization and feature selection purposes. Visual examples are given using a real gel-based proteomic dataset as basis....

Perceived weight discrimination and chronic biochemical stress: A population?based study using cortisol in scalp hair

OpenAIRE

Jackson, Sarah E.; Kirschbaum, Clemens; Steptoe, Andrew

2016-01-01

Objective There is increasing evidence for weight?based discrimination against persons with obesity. This study aimed to examine the physiological impact of perceived weight discrimination on cortisol in hair, an indicator of chronic stress exposure. Methods Data were from 563 nonsmoking individuals with obesity (body mass index, BMI ?30 kg/m2) participating in the English Longitudinal Study of Ageing. Experiences of discrimination were reported via questionnaire, and hair cortisol concentrat...

A comparative study of sequence- and structure-based features of small RNAs and other RNAs of bacteria.

Science.gov (United States)

Barik, Amita; Das, Santasabuj

2018-01-02

Small RNAs (sRNAs) in bacteria have emerged as key players in transcriptional and post-transcriptional regulation of gene expression. Here, we present a statistical analysis of different sequence- and structure-related features of bacterial sRNAs to identify the descriptors that could discriminate sRNAs from other bacterial RNAs. We investigated a comprehensive and heterogeneous collection of 816 sRNAs, identified by northern blotting across 33 bacterial species and compared their various features with other classes of bacterial RNAs, such as tRNAs, rRNAs and mRNAs. We observed that sRNAs differed significantly from the rest with respect to G+C composition, normalized minimum free energy of folding, motif frequency and several RNA-folding parameters like base-pairing propensity, Shannon entropy and base-pair distance. Based on the selected features, we developed a predictive model using Random Forests (RF) method to classify the above four classes of RNAs. Our model displayed an overall predictive accuracy of 89.5%. These findings would help to differentiate bacterial sRNAs from other RNAs and further promote prediction of novel sRNAs in different bacterial species.

Wearable Sensor-Based Human Activity Recognition Method with Multi-Features Extracted from Hilbert-Huang Transform

Directory of Open Access Journals (Sweden)

Huile Xu

2016-12-01

Full Text Available Wearable sensors-based human activity recognition introduces many useful applications and services in health care, rehabilitation training, elderly monitoring and many other areas of human interaction. Existing works in this field mainly focus on recognizing activities by using traditional features extracted from Fourier transform (FT or wavelet transform (WT. However, these signal processing approaches are suitable for a linear signal but not for a nonlinear signal. In this paper, we investigate the characteristics of the Hilbert-Huang transform (HHT for dealing with activity data with properties such as nonlinearity and non-stationarity. A multi-features extraction method based on HHT is then proposed to improve the effect of activity recognition. The extracted multi-features include instantaneous amplitude (IA and instantaneous frequency (IF by means of empirical mode decomposition (EMD, as well as instantaneous energy density (IE and marginal spectrum (MS derived from Hilbert spectral analysis. Experimental studies are performed to verify the proposed approach by using the PAMAP2 dataset from the University of California, Irvine for wearable sensors-based activity recognition. Moreover, the effect of combining multi-features vs. a single-feature are investigated and discussed in the scenario of a dependent subject. The experimental results show that multi-features combination can further improve the performance measures. Finally, we test the effect of multi-features combination in the scenario of an independent subject. Our experimental results show that we achieve four performance indexes: recall, precision, F-measure, and accuracy to 0.9337, 0.9417, 0.9353, and 0.9377 respectively, which are all better than the achievements of related works.

Feature-based attentional modulation increases with stimulus separation in divided-attention tasks.

Science.gov (United States)

Sally, Sharon L; Vidnyánsky, Zoltán; Papathomas, Thomas V

2009-01-01

Attention modifies our visual experience by selecting certain aspects of a scene for further processing. It is therefore important to understand factors that govern the deployment of selective attention over the visual field. Both location and feature-specific mechanisms of attention have been identified and their modulatory effects can interact at a neural level (Treue and Martinez-Trujillo, 1999). The effects of spatial parameters on feature-based attentional modulation were examined for the feature dimensions of orientation, motion and color using three divided-attention tasks. Subjects performed concurrent discriminations of two briefly presented targets (Gabor patches) to the left and right of a central fixation point at eccentricities of +/-2.5 degrees , 5 degrees , 10 degrees and 15 degrees in the horizontal plane. Gabors were size-scaled to maintain consistent single-task performance across eccentricities. For all feature dimensions, the data show a linear increase in the attentional effects with target separation. In a control experiment, Gabors were presented on an isoeccentric viewing arc at 10 degrees and 15 degrees at the closest spatial separation (+/-2.5 degrees ) of the main experiment. Under these conditions, the effects of feature-based attentional effects were largely eliminated. Our results are consistent with the hypothesis that feature-based attention prioritizes the processing of attended features. Feature-based attentional mechanisms may have helped direct the attentional focus to the appropriate target locations at greater separations, whereas similar assistance may not have been necessary at closer target spacings. The results of the present study specify conditions under which dual-task performance benefits from sharing similar target features and may therefore help elucidate the processes by which feature-based attention operates.

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 %.

Deep Learning Methods for Underwater Target Feature Extraction and Recognition

Directory of Open Access Journals (Sweden)

Gang Hu

2018-01-01

Full Text Available The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved.

Introducing two Random Forest based methods for cloud detection in remote sensing images

Science.gov (United States)

Ghasemian, Nafiseh; Akhoondzadeh, Mehdi

2018-07-01

Cloud detection is a necessary phase in satellite images processing to retrieve the atmospheric and lithospheric parameters. Currently, some cloud detection methods based on Random Forest (RF) model have been proposed but they do not consider both spectral and textural characteristics of the image. Furthermore, they have not been tested in the presence of snow/ice. In this paper, we introduce two RF based algorithms, Feature Level Fusion Random Forest (FLFRF) and Decision Level Fusion Random Forest (DLFRF) to incorporate visible, infrared (IR) and thermal spectral and textural features (FLFRF) including Gray Level Co-occurrence Matrix (GLCM) and Robust Extended Local Binary Pattern (RELBP_CI) or visible, IR and thermal classifiers (DLFRF) for highly accurate cloud detection on remote sensing images. FLFRF first fuses visible, IR and thermal features. Thereafter, it uses the RF model to classify pixels to cloud, snow/ice and background or thick cloud, thin cloud and background. DLFRF considers visible, IR and thermal features (both spectral and textural) separately and inserts each set of features to RF model. Then, it holds vote matrix of each run of the model. Finally, it fuses the classifiers using the majority vote method. To demonstrate the effectiveness of the proposed algorithms, 10 Terra MODIS and 15 Landsat 8 OLI/TIRS images with different spatial resolutions are used in this paper. Quantitative analyses are based on manually selected ground truth data. Results show that after adding RELBP_CI to input feature set cloud detection accuracy improves. Also, the average cloud kappa values of FLFRF and DLFRF on MODIS images (1 and 0.99) are higher than other machine learning methods, Linear Discriminate Analysis (LDA), Classification And Regression Tree (CART), K Nearest Neighbor (KNN) and Support Vector Machine (SVM) (0.96). The average snow/ice kappa values of FLFRF and DLFRF on MODIS images (1 and 0.85) are higher than other traditional methods. The

Non-destructive profiling of volatile organic compounds using HS-SPME/GC-MS and its application for the geographical discrimination of white rice.

Science.gov (United States)

Lim, Dong Kyu; Mo, Changyeun; Lee, Dong-Kyu; Long, Nguyen Phuoc; Lim, Jongguk; Kwon, Sung Won

2018-01-01

The authenticity determination of white rice is crucial to prevent deceptive origin labeling and dishonest trading. However, a non-destructive and comprehensive method for rapidly discriminating the geographical origins of white rice between countries is still lacking. In the current study, we developed a volatile organic compound based geographical discrimination method using headspace solid-phase microextraction coupled to gas chromatography-mass spectrometry (HS-SPME/GC-MS) to discriminate rice samples from Korea and China. A partial least squares discriminant analysis (PLS-DA) model exhibited a good classification of white rice between Korea and China (accuracy = 0.958, goodness of fit = 0.937, goodness of prediction = 0.831, and permutation test p-value = 0.043). Combining the PLS-DA based feature selection with the differentially expressed features from the unpaired t-test and significance analysis of microarrays, 12 discriminatory biomarkers were found. Among them, hexanal and 1-hexanol have been previously known to be associated with the cultivation environment and storage conditions. Other hydrocarbon biomarkers are novel, and their impact on rice production and storage remains to be elucidated. In conclusion, our findings highlight the ability to rapidly discriminate white rice from Korea and China. The developed method maybe useful for the authenticity and quality control of white rice. Copyright © 2017. Published by Elsevier B.V.

Non-destructive profiling of volatile organic compounds using HS-SPME/GC–MS and its application for the geographical discrimination of white rice

Directory of Open Access Journals (Sweden)

Dong Kyu Lim

2018-01-01

Full Text Available The authenticity determination of white rice is crucial to prevent deceptive origin labeling and dishonest trading. However, a non-destructive and comprehensive method for rapidly discriminating the geographical origins of white rice between countries is still lacking. In the current study, we developed a volatile organic compound based geographical discrimination method using headspace solid-phase microextraction coupled to gas chromatography–mass spectrometry (HS-SPME/GC–MS to discriminate rice samples from Korea and China. A partial least squares discriminant analysis (PLS-DA model exhibited a good classification of white rice between Korea and China (accuracy = 0.958, goodness of fit = 0.937, goodness of prediction = 0.831, and permutation test p-value = 0.043. Combining the PLS-DA based feature selection with the differentially expressed features from the unpaired t-test and significance analysis of microarrays, 12 discriminatory biomarkers were found. Among them, hexanal and 1-hexanol have been previously known to be associated with the cultivation environment and storage conditions. Other hydrocarbon biomarkers are novel, and their impact on rice production and storage remains to be elucidated. In conclusion, our findings highlight the ability to rapidly discriminate white rice from Korea and China. The developed method maybe useful for the authenticity and quality control of white rice.

Analysis of Time n Frequency EEG Feature Extraction Methods for Mental Task Classification

Directory of Open Access Journals (Sweden)

Caglar Uyulan

2017-01-01

Full Text Available Many endogenous and external components may affect the physiological, mental and behavioral states in humans. Monitoring tools are required to evaluate biomarkers, identify biological events, and predict their outcomes. Being one of the valuable indicators, brain biomarkers derived from temporal or spectral electroencephalography (EEG signals processing, allow for the classification of mental disorders and mental tasks. An EEG signal has a nonstationary nature and individual frequency feature, hence it can be concluded that each subject has peculiar timing and data to extract unique features. In order to classify data, which are collected by performing four mental task (reciting the alphabet backwards, imagination of rotation of a cube, imagination of right hand movements (open/close and performing mathematical operations, discriminative features were extracted using four competitive time-frequency techniques; Wavelet Packet Decomposition (WPD, Morlet Wavelet Transform (MWT, Short Time Fourier Transform (STFT and Wavelet Filter Bank (WFB, respectively. The extracted features using both time and frequency domain information were then reduced using a principal component analysis for subset reduction. Finally, the reduced subsets were fed into a multi-layer perceptron neural network (MP-NN trained with back propagation (BP algorithm to generate a predictive model. This study mainly focuses on comparing the relative performance of time-frequency feature extraction methods that are used to classify mental tasks. The real-time (RT conducted experimental results underlined that the WPD feature extraction method outperforms with 92% classification accuracy compared to three other aforementioned methods for four different mental tasks.

[Discrimination of types of polyacrylamide based on near infrared spectroscopy coupled with least square support vector machine].

Science.gov (United States)

Zhang, Hong-Guang; Yang, Qin-Min; Lu, Jian-Gang

2014-04-01

In this paper, a novel discriminant methodology based on near infrared spectroscopic analysis technique and least square support vector machine was proposed for rapid and nondestructive discrimination of different types of Polyacrylamide. The diffuse reflectance spectra of samples of Non-ionic Polyacrylamide, Anionic Polyacrylamide and Cationic Polyacrylamide were measured. Then principal component analysis method was applied to reduce the dimension of the spectral data and extract of the principal compnents. The first three principal components were used for cluster analysis of the three different types of Polyacrylamide. Then those principal components were also used as inputs of least square support vector machine model. The optimization of the parameters and the number of principal components used as inputs of least square support vector machine model was performed through cross validation based on grid search. 60 samples of each type of Polyacrylamide were collected. Thus a total of 180 samples were obtained. 135 samples, 45 samples for each type of Polyacrylamide, were randomly split into a training set to build calibration model and the rest 45 samples were used as test set to evaluate the performance of the developed model. In addition, 5 Cationic Polyacrylamide samples and 5 Anionic Polyacrylamide samples adulterated with different proportion of Non-ionic Polyacrylamide were also prepared to show the feasibilty of the proposed method to discriminate the adulterated Polyacrylamide samples. The prediction error threshold for each type of Polyacrylamide was determined by F statistical significance test method based on the prediction error of the training set of corresponding type of Polyacrylamide in cross validation. The discrimination accuracy of the built model was 100% for prediction of the test set. The prediction of the model for the 10 mixing samples was also presented, and all mixing samples were accurately discriminated as adulterated samples. The

A Fast, Open EEG Classification Framework Based on Feature Compression and Channel Ranking

Directory of Open Access Journals (Sweden)

Jiuqi Han

2018-04-01

Full Text Available Superior feature extraction, channel selection and classification methods are essential for designing electroencephalography (EEG classification frameworks. However, the performance of most frameworks is limited by their improper channel selection methods and too specifical design, leading to high computational complexity, non-convergent procedure and narrow expansibility. In this paper, to remedy these drawbacks, we propose a fast, open EEG classification framework centralized by EEG feature compression, low-dimensional representation, and convergent iterative channel ranking. First, to reduce the complexity, we use data clustering to compress the EEG features channel-wise, packing the high-dimensional EEG signal, and endowing them with numerical signatures. Second, to provide easy access to alternative superior methods, we structurally represent each EEG trial in a feature vector with its corresponding numerical signature. Thus, the recorded signals of many trials shrink to a low-dimensional structural matrix compatible with most pattern recognition methods. Third, a series of effective iterative feature selection approaches with theoretical convergence is introduced to rank the EEG channels and remove redundant ones, further accelerating the EEG classification process and ensuring its stability. Finally, a classical linear discriminant analysis (LDA model is employed to classify a single EEG trial with selected channels. Experimental results on two real world brain-computer interface (BCI competition datasets demonstrate the promising performance of the proposed framework over state-of-the-art methods.

An integration of minimum local feature representation methods to recognize large variation of foods

Science.gov (United States)

Razali, Mohd Norhisham bin; Manshor, Noridayu; Halin, Alfian Abdul; Mustapha, Norwati; Yaakob, Razali

2017-10-01

Local invariant features have shown to be successful in describing object appearances for image classification tasks. Such features are robust towards occlusion and clutter and are also invariant against scale and orientation changes. This makes them suitable for classification tasks with little inter-class similarity and large intra-class difference. In this paper, we propose an integrated representation of the Speeded-Up Robust Feature (SURF) and Scale Invariant Feature Transform (SIFT) descriptors, using late fusion strategy. The proposed representation is used for food recognition from a dataset of food images with complex appearance variations. The Bag of Features (BOF) approach is employed to enhance the discriminative ability of the local features. Firstly, the individual local features are extracted to construct two kinds of visual vocabularies, representing SURF and SIFT. The visual vocabularies are then concatenated and fed into a Linear Support Vector Machine (SVM) to classify the respective food categories. Experimental results demonstrate impressive overall recognition at 82.38% classification accuracy based on the challenging UEC-Food100 dataset.

Development and assessment of a lysophospholipid-based deep learning model to discriminate geographical origins of white rice.

Science.gov (United States)

Long, Nguyen Phuoc; Lim, Dong Kyu; Mo, Changyeun; Kim, Giyoung; Kwon, Sung Won

2017-08-17

Geographical origin determination of white rice has become the major issue of food industry. However, there is still lack of a high-throughput method for rapidly and reproducibly differentiating the geographical origins of commercial white rice. In this study, we developed a method that employed lipidomics and deep learning to discriminate white rice from Korea to China. A total of 126 white rice of 30 cultivars from different regions were utilized for the method development and validation. By using direct infusion-mass spectrometry-based targeted lipidomics, 17 lysoglycerophospholipids were simultaneously characterized within minutes per sample. Unsupervised data exploration showed a noticeable overlap of white rice between two countries. In addition, lysophosphatidylcholines (lysoPCs) were prominent in white rice from Korea while lysophosphatidylethanolamines (lysoPEs) were enriched in white rice from China. A deep learning prediction model was built using 2014 white rice and validated using two different batches of 2015 white rice. The model accurately discriminated white rice from two countries. Among 10 selected predictors, lysoPC(18:2), lysoPC(14:0), and lysoPE(16:0) were the three most important features. Random forest and gradient boosting machine models also worked well in this circumstance. In conclusion, this study provides an architecture for high-throughput classification of white rice from different geographical origins.

A consistency-based feature selection method allied with linear SVMs for HIV-1 protease cleavage site prediction.

Directory of Open Access Journals (Sweden)

Orkun Oztürk

Full Text Available BACKGROUND: Predicting type-1 Human Immunodeficiency Virus (HIV-1 protease cleavage site in protein molecules and determining its specificity is an important task which has attracted considerable attention in the research community. Achievements in this area are expected to result in effective drug design (especially for HIV-1 protease inhibitors against this life-threatening virus. However, some drawbacks (like the shortage of the available training data and the high dimensionality of the feature space turn this task into a difficult classification problem. Thus, various machine learning techniques, and specifically several classification methods have been proposed in order to increase the accuracy of the classification model. In addition, for several classification problems, which are characterized by having few samples and many features, selecting the most relevant features is a major factor for increasing classification accuracy. RESULTS: We propose for HIV-1 data a consistency-based feature selection approach in conjunction with recursive feature elimination of support vector machines (SVMs. We used various classifiers for evaluating the results obtained from the feature selection process. We further demonstrated the effectiveness of our proposed method by comparing it with a state-of-the-art feature selection method applied on HIV-1 data, and we evaluated the reported results based on attributes which have been selected from different combinations. CONCLUSION: Applying feature selection on training data before realizing the classification task seems to be a reasonable data-mining process when working with types of data similar to HIV-1. On HIV-1 data, some feature selection or extraction operations in conjunction with different classifiers have been tested and noteworthy outcomes have been reported. These facts motivate for the work presented in this paper. SOFTWARE AVAILABILITY: The software is available at http

Robust Image Hashing Using Radon Transform and Invariant Features

Directory of Open Access Journals (Sweden)

Y.L. Liu

2016-09-01

Full Text Available A robust image hashing method based on radon transform and invariant features is proposed for image authentication, image retrieval, and image detection. Specifically, an input image is firstly converted into a counterpart with a normalized size. Then the invariant centroid algorithm is applied to obtain the invariant feature point and the surrounding circular area, and the radon transform is employed to acquire the mapping coefficient matrix of the area. Finally, the hashing sequence is generated by combining the feature vectors and the invariant moments calculated from the coefficient matrix. Experimental results show that this method not only can resist against the normal image processing operations, but also some geometric distortions. Comparisons of receiver operating characteristic (ROC curve indicate that the proposed method outperforms some existing methods in classification between perceptual robustness and discrimination.

Discrimination symbol applying method for sintered nuclear fuel product

International Nuclear Information System (INIS)

Ishizaki, Jin

1998-01-01

The present invention provides a symbol applying method for applying discrimination information such as an enrichment degree on the end face of a sintered nuclear product. Namely, discrimination symbols of information of powders are applied by a sintering aid to the end face of a molded member formed by molding nuclear fuel powders under pressure. Then, the molded product is sintered. The sintering aid comprises aluminum oxide, a mixture of aluminum oxide and silicon dioxide, aluminum hydride or aluminum stearate alone or in admixture. As an applying means of the sintering aid, discrimination symbols of information of powders are drawn by an isostearic acid on the end face of the molded product, and the sintering aid is sprayed thereto, or the sintering aid is applied directly, or the sintering aid is suspended in isostearic acid, and the suspension is applied with a brush. As a result, visible discrimination information can be applied to the sintered member easily. (N.H.)

Stochastic formalism-based seafloor feature discrimination using multifractality of time-dependent acoustic backscatter

Digital Repository Service at National Institute of Oceanography (India)

Haris, K.; Chakraborty, B.

Nonlin. Processes Geophys., 21, 101–113, 2014 www.nonlin-processes-geophys.net/21/101/2014/ doi:10.5194/npg-21-101-2014 © Author(s) 2014. CC Attribution 3.0 License. Nonlinear Processes in Geophysics O pen A ccess Stochastic formalism-based seafloor... shifted in time to align with the selected feature (Fig. 2). The aligned echo envelopes were averaged to obtain stable acoustic signals to Nonlin. Processes Geophys., 21, 101–113, 2014 www.nonlin-processes-geophys.net/21/101/2014/ K. Haris and B...

A Look into Lookism: An Evaluation of Discrimination Based on Physical Attractiveness

OpenAIRE

Hammer, Cherea

2017-01-01

Discrimination in employment on the basis of race, sex, national origin , religion , and other federally protected categories is well recognized as a social problem and anti-discrimination legislation works to limit the impact of discrimination on marginalized populations. However, most people do not consider discrimination based on physical appearance. "Lookism" captures the idea that an individual can be discriminated against based on their physical appearance or physical attractiveness and...

Structural MRI-based discrimination between autistic and typically developing brain

Energy Technology Data Exchange (ETDEWEB)

Fahmi, R; Hassan, H; Farag, A A [CVIP Lab., Univ. of Louisville, KY (United States); Elbaz, A [Dept. of Bioengineering, Univ. of Louisville, KY (United States); Casanova, M F [Dept. of Psychiatry and Behavioral science, Univ. of Louisville, KY (United States)

2007-06-15

Autism is a neurodevelopmental disorder characterized by marked deficits in communication, social interaction, and interests. Various studies of autism have suggested abnormalities in several brain regions, with an increasing agreement on the abnormal anatomy of the white matter (WM) and on deficits in the size of the corpus callosum (CC) and its sub-regions in autism. In this paper, we aim at using these abnormalities in order to devise robust classification methods of autistic vs. typically developing brains by analyzing their respective MRIs. Our analysis is based on shape descriptions and geometric models. We compute the 3D distance map to describe the shape of the WM, and use it as a statistical feature to discriminate between the two groups. We also use our recently proposed non-rigid registration technique to devise another classification approach by statistically analyzing and comparing the deformation fields generated from registering segmented CC's onto each others. The proposed techniques are tested on postmortem and on in-vivo brain MR data. At the 85% confidence level the WM-based classification algorithm correctly classified 14/14 postmortem-autistics and 12/12 in-vivo autistics, a 100% accuracy rate, and 13/15 postmortem controls (86% accuracy rate) and 30/30 in-vivo controls (100% accuracy rate). The technique based on the analysis of the CC was applied only on the in vivo data. At the 85% confidence rate, this technique correctly classified 10/15 autistics, a 0.66 accuracy rate, and 29/30 controls, a 0.96 accuracy rate. These results are very promising and show that, contrary to traditional methods, the proposed techniques are less sensitive to age and volume effects. (orig.)

Structural MRI-based discrimination between autistic and typically developing brain

International Nuclear Information System (INIS)

Fahmi, R.; Hassan, H.; Farag, A.A.; Elbaz, A.; Casanova, M.F.

2007-01-01

Autism is a neurodevelopmental disorder characterized by marked deficits in communication, social interaction, and interests. Various studies of autism have suggested abnormalities in several brain regions, with an increasing agreement on the abnormal anatomy of the white matter (WM) and on deficits in the size of the corpus callosum (CC) and its sub-regions in autism. In this paper, we aim at using these abnormalities in order to devise robust classification methods of autistic vs. typically developing brains by analyzing their respective MRIs. Our analysis is based on shape descriptions and geometric models. We compute the 3D distance map to describe the shape of the WM, and use it as a statistical feature to discriminate between the two groups. We also use our recently proposed non-rigid registration technique to devise another classification approach by statistically analyzing and comparing the deformation fields generated from registering segmented CC's onto each others. The proposed techniques are tested on postmortem and on in-vivo brain MR data. At the 85% confidence level the WM-based classification algorithm correctly classified 14/14 postmortem-autistics and 12/12 in-vivo autistics, a 100% accuracy rate, and 13/15 postmortem controls (86% accuracy rate) and 30/30 in-vivo controls (100% accuracy rate). The technique based on the analysis of the CC was applied only on the in vivo data. At the 85% confidence rate, this technique correctly classified 10/15 autistics, a 0.66 accuracy rate, and 29/30 controls, a 0.96 accuracy rate. These results are very promising and show that, contrary to traditional methods, the proposed techniques are less sensitive to age and volume effects. (orig.)

Structural MRI-based discrimination between autistic and typically developing brain

Energy Technology Data Exchange (ETDEWEB)

Fahmi, R.; Hassan, H.; Farag, A.A. [CVIP Lab., Univ. of Louisville, KY (United States); Elbaz, A. [Dept. of Bioengineering, Univ. of Louisville, KY (United States); Casanova, M.F. [Dept. of Psychiatry and Behavioral science, Univ. of Louisville, KY (United States)

2007-06-15

Autism is a neurodevelopmental disorder characterized by marked deficits in communication, social interaction, and interests. Various studies of autism have suggested abnormalities in several brain regions, with an increasing agreement on the abnormal anatomy of the white matter (WM) and on deficits in the size of the corpus callosum (CC) and its sub-regions in autism. In this paper, we aim at using these abnormalities in order to devise robust classification methods of autistic vs. typically developing brains by analyzing their respective MRIs. Our analysis is based on shape descriptions and geometric models. We compute the 3D distance map to describe the shape of the WM, and use it as a statistical feature to discriminate between the two groups. We also use our recently proposed non-rigid registration technique to devise another classification approach by statistically analyzing and comparing the deformation fields generated from registering segmented CC's onto each others. The proposed techniques are tested on postmortem and on in-vivo brain MR data. At the 85% confidence level the WM-based classification algorithm correctly classified 14/14 postmortem-autistics and 12/12 in-vivo autistics, a 100% accuracy rate, and 13/15 postmortem controls (86% accuracy rate) and 30/30 in-vivo controls (100% accuracy rate). The technique based on the analysis of the CC was applied only on the in vivo data. At the 85% confidence rate, this technique correctly classified 10/15 autistics, a 0.66 accuracy rate, and 29/30 controls, a 0.96 accuracy rate. These results are very promising and show that, contrary to traditional methods, the proposed techniques are less sensitive to age and volume effects. (orig.)

Multi-Site Diagnostic Classification of Schizophrenia Using Discriminant Deep Learning with Functional Connectivity MRI

Directory of Open Access Journals (Sweden)

Ling-Li Zeng

2018-04-01

Full Text Available Background: A lack of a sufficiently large sample at single sites causes poor generalizability in automatic diagnosis classification of heterogeneous psychiatric disorders such as schizophrenia based on brain imaging scans. Advanced deep learning methods may be capable of learning subtle hidden patterns from high dimensional imaging data, overcome potential site-related variation, and achieve reproducible cross-site classification. However, deep learning-based cross-site transfer classification, despite less imaging site-specificity and more generalizability of diagnostic models, has not been investigated in schizophrenia. Methods: A large multi-site functional MRI sample (n = 734, including 357 schizophrenic patients from seven imaging resources was collected, and a deep discriminant autoencoder network, aimed at learning imaging site-shared functional connectivity features, was developed to discriminate schizophrenic individuals from healthy controls. Findings: Accuracies of approximately 85·0% and 81·0% were obtained in multi-site pooling classification and leave-site-out transfer classification, respectively. The learned functional connectivity features revealed dysregulation of the cortical-striatal-cerebellar circuit in schizophrenia, and the most discriminating functional connections were primarily located within and across the default, salience, and control networks. Interpretation: The findings imply that dysfunctional integration of the cortical-striatal-cerebellar circuit across the default, salience, and control networks may play an important role in the “disconnectivity” model underlying the pathophysiology of schizophrenia. The proposed discriminant deep learning method may be capable of learning reliable connectome patterns and help in understanding the pathophysiology and achieving accurate prediction of schizophrenia across multiple independent imaging sites. Keywords: Schizophrenia, Deep learning, Connectome, f

Digital Discrimination: The Case of Airbnb.com

OpenAIRE

Benjamin Edelman; Micahel Luca

2014-01-01

Online marketplaces often contain information not only about products, but also about the people selling the products. In an effort to facilitate trust, many platforms encourage sellers to provide personal profiles and even to post pictures of themselves. However, these features may also facilitate discrimination based on sellers' race, gender, age, or other aspects of appearance. In this paper, we test for racial discrimination against landlords in the online rental marketplace Airbnb.com. U...

Evaluation of wavelet spectral features in pathological detection and discrimination of yellow rust and powdery mildew in winter wheat with hyperspectral reflectance data

Science.gov (United States)

Shi, Yue; Huang, Wenjiang; Zhou, Xianfeng

2017-04-01

Hyperspectral absorption features are important indicators of characterizing plant biophysical variables for the automatic diagnosis of crop diseases. Continuous wavelet analysis has proven to be an advanced hyperspectral analysis technique for extracting absorption features; however, specific wavelet features (WFs) and their relationship with pathological characteristics induced by different infestations have rarely been summarized. The aim of this research is to determine the most sensitive WFs for identifying specific pathological lesions from yellow rust and powdery mildew in winter wheat, based on 314 hyperspectral samples measured in field experiments in China in 2002, 2003, 2005, and 2012. The resultant WFs could be used as proxies to capture the major spectral absorption features caused by infestation of yellow rust or powdery mildew. Multivariate regression analysis based on these WFs outperformed conventional spectral features in disease detection; meanwhile, a Fisher discrimination model exhibited considerable potential for generating separable clusters for each infestation. Optimal classification returned an overall accuracy of 91.9% with a Kappa of 0.89. This paper also emphasizes the WFs and their relationship with pathological characteristics in order to provide a foundation for the further application of this approach in monitoring winter wheat diseases at the regional scale.

Spectral feature characterization methods for blood stain detection in crime scene backgrounds

Science.gov (United States)

Yang, Jie; Mathew, Jobin J.; Dube, Roger R.; Messinger, David W.

2016-05-01

Blood stains are one of the most important types of evidence for forensic investigation. They contain valuable DNA information, and the pattern of the stains can suggest specifics about the nature of the violence that transpired at the scene. Blood spectral signatures containing unique reflectance or absorption features are important both for forensic on-site investigation and laboratory testing. They can be used for target detection and identification applied to crime scene hyperspectral imagery, and also be utilized to analyze the spectral variation of blood on various backgrounds. Non-blood stains often mislead the detection and can generate false alarms at a real crime scene, especially for dark and red backgrounds. This paper measured the reflectance of liquid blood and 9 kinds of non-blood samples in the range of 350 nm - 2500 nm in various crime scene backgrounds, such as pure samples contained in petri dish with various thicknesses, mixed samples with different colors and materials of fabrics, and mixed samples with wood, all of which are examined to provide sub-visual evidence for detecting and recognizing blood from non-blood samples in a realistic crime scene. The spectral difference between blood and non-blood samples are examined and spectral features such as "peaks" and "depths" of reflectance are selected. Two blood stain detection methods are proposed in this paper. The first method uses index to denote the ratio of "depth" minus "peak" over"depth" add"peak" within a wavelength range of the reflectance spectrum. The second method uses relative band depth of the selected wavelength ranges of the reflectance spectrum. Results show that the index method is able to discriminate blood from non-blood samples in most tested crime scene backgrounds, but is not able to detect it from black felt. Whereas the relative band depth method is able to discriminate blood from non-blood samples on all of the tested background material types and colors.

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%.

Discriminative analysis of early Alzheimer's disease based on two intrinsically anti-correlated networks with resting-state fMRI.

Science.gov (United States)

Wang, Kun; Jiang, Tianzi; Liang, Meng; Wang, Liang; Tian, Lixia; Zhang, Xinqing; Li, Kuncheng; Liu, Zhening

2006-01-01

In this work, we proposed a discriminative model of Alzheimer's disease (AD) on the basis of multivariate pattern classification and functional magnetic resonance imaging (fMRI). This model used the correlation/anti-correlation coefficients of two intrinsically anti-correlated networks in resting brains, which have been suggested by two recent studies, as the feature of classification. Pseudo-Fisher Linear Discriminative Analysis (pFLDA) was then performed on the feature space and a linear classifier was generated. Using leave-one-out (LOO) cross validation, our results showed a correct classification rate of 83%. We also compared the proposed model with another one based on the whole brain functional connectivity. Our proposed model outperformed the other one significantly, and this implied that the two intrinsically anti-correlated networks may be a more susceptible part of the whole brain network in the early stage of AD.

Action recognition using mined hierarchical compound features.

Science.gov (United States)

Gilbert, Andrew; Illingworth, John; Bowden, Richard

2011-05-01

The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single-frame object recognition and adapting them for temporal-based action recognition. Inspired by the success of interest points in the 2D spatial domain, their 3D (space-time) counterparts typically form the basic components used to describe actions, and in action recognition the features used are often engineered to fire sparsely. This is to ensure that the problem is tractable; however, this can sacrifice recognition accuracy as it cannot be assumed that the optimum features in terms of class discrimination are obtained from this approach. In contrast, we propose to initially use an overcomplete set of simple 2D corners in both space and time. These are grouped spatially and temporally using a hierarchical process, with an increasing search area. At each stage of the hierarchy, the most distinctive and descriptive features are learned efficiently through data mining. This allows large amounts of data to be searched for frequently reoccurring patterns of features. At each level of the hierarchy, the mined compound features become more complex, discriminative, and sparse. This results in fast, accurate recognition with real-time performance on high-resolution video. As the compound features are constructed and selected based upon their ability to discriminate, their speed and accuracy increase at each level of the hierarchy. The approach is tested on four state-of-the-art data sets, the popular KTH data set to provide a comparison with other state-of-the-art approaches, the Multi-KTH data set to illustrate performance at simultaneous multiaction classification, despite no explicit localization information provided during training. Finally, the recent Hollywood and Hollywood2 data sets provide challenging complex actions taken from commercial movie sequences. For all four data sets, the proposed hierarchical

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.

A PTV method based on ultrasound imaging and feature tracking in a low-concentration sediment-laden flow

Science.gov (United States)

Ma, Zhimin; Hu, Wenbin; Zhao, Xiaohong; Tao, Weiliang

2018-02-01

This study aims to provide a particle tracking velocimetry (PTV) method based on ultrasound imaging and feature-tracking in a low-concentration sediment-laden flow. A phased array probe is used to generate a 2D ultrasound image at different times. Then, the feature points are extracted to be tracked instead of the centroids of the particle image. In order to better identify the corresponding feature point, each feature is described by an oriented angle and its location. Then, a statistical interpolation procedure is used to yield the displacement vector on the desired grid point. Finally a correction procedure is adopted because the ultrasound image is sequentially acquired line by line through the field of view. A simple test experiment was carried out to evaluate the performance. The ultrasound PTV system was applied to a sediment-laden flow with a low concentration of 1‰, and the speed was up to 10 cm s-1. In comparison to optical particle image velocimetry (PIV), ultrasound imaging does not have a limitation in optical access. The feature-tracking method does not have a binarisation and segmentation procedure, which can result in overlapping particles or a serious loss of particle data. The feature-tracking algorithm improves the peak locking effect and measurement accuracy. Thus, the ultrasound PTV algorithm is a feasible alternative and is significantly more robust against gradients than the correlation-based PIV algorithms in a low-concentration sediment-laden fluid.

Research on Methods for Discovering and Selecting Cloud Infrastructure Services Based on Feature Modeling

Directory of Open Access Journals (Sweden)

Huamin Zhu

2016-01-01

Full Text Available Nowadays more and more cloud infrastructure service providers are providing large numbers of service instances which are a combination of diversified resources, such as computing, storage, and network. However, for cloud infrastructure services, the lack of a description standard and the inadequate research of systematic discovery and selection methods have exposed difficulties in discovering and choosing services for users. First, considering the highly configurable properties of a cloud infrastructure service, the feature model method is used to describe such a service. Second, based on the description of the cloud infrastructure service, a systematic discovery and selection method for cloud infrastructure services are proposed. The automatic analysis techniques of the feature model are introduced to verify the model’s validity and to perform the matching of the service and demand models. Finally, we determine the critical decision metrics and their corresponding measurement methods for cloud infrastructure services, where the subjective and objective weighting results are combined to determine the weights of the decision metrics. The best matching instances from various providers are then ranked by their comprehensive evaluations. Experimental results show that the proposed methods can effectively improve the accuracy and efficiency of cloud infrastructure service discovery and selection.

Multiple-Fault Diagnosis Method Based on Multiscale Feature Extraction and MSVM_PPA

Directory of Open Access Journals (Sweden)

Min Zhang

2018-01-01

Full Text Available Identification of rolling bearing fault patterns, especially for the compound faults, has attracted notable attention and is still a challenge in fault diagnosis. In this paper, a novel method called multiscale feature extraction (MFE and multiclass support vector machine (MSVM with particle parameter adaptive (PPA is proposed. MFE is used to preprocess the process signals, which decomposes the data into intrinsic mode function by empirical mode decomposition method, and instantaneous frequency of decomposed components was obtained by Hilbert transformation. Then, statistical features and principal component analysis are utilized to extract significant information from the features, to get effective data from multiple faults. MSVM method with PPA parameters optimization will classify the fault patterns. The results of a case study of the rolling bearings faults data from Case Western Reserve University show that (1 the proposed intelligent method (MFE_PPA_MSVM improves the classification recognition rate; (2 the accuracy will decline when the number of fault patterns increases; (3 prediction accuracy can be the best when the training set size is increased to 70% of the total sample set. It verifies the method is feasible and efficient for fault diagnosis.

Discriminative region extraction and feature selection based on the combination of SURF and saliency

Science.gov (United States)

Deng, Li; Wang, Chunhong; Rao, Changhui

2011-08-01

The objective of this paper is to provide a possible optimization on salient region algorithm, which is extensively used in recognizing and learning object categories. Salient region algorithm owns the superiority of intra-class tolerance, global score of features and automatically prominent scale selection under certain range. However, the major limitation behaves on performance, and that is what we attempt to improve. By reducing the number of pixels involved in saliency calculation, it can be accelerated. We use interest points detected by fast-Hessian, the detector of SURF, as the candidate feature for saliency operation, rather than the whole set in image. This implementation is thereby called Saliency based Optimization over SURF (SOSU for short). Experiment shows that bringing in of such a fast detector significantly speeds up the algorithm. Meanwhile, Robustness of intra-class diversity ensures object recognition accuracy.

 Optimizing relational algebra operations using discrimination-based joins and lazy products

DEFF Research Database (Denmark)

Henglein, Fritz

We show how to implement in-memory execution of the core re- lational algebra operations of projection, selection and cross-product eciently, using discrimination-based joins and lazy products. We introduce the notion of (partitioning) discriminator, which par- titions a list of values according...... to a specied equivalence relation on keys the values are associated with. We show how discriminators can be dened generically, purely functionally, and eciently (worst-case linear time) on top of the array-based basic multiset discrimination algorithm of Cai and Paige (1995). Discriminators provide the basis...... the selection operation to recognize on the y whenever it is applied to a cross-product, in which case it can choose an ecient discrimination-based equijoin implementation. The techniques subsume most of the optimization techniques based on relational algebra equalities, without need for a query preprocessing...

MR PROSTATE SEGMENTATION VIA DISTRIBUTED DISCRIMINATIVE DICTIONARY (DDD) LEARNING.

Science.gov (United States)

Guo, Yanrong; Zhan, Yiqiang; Gao, Yaozong; Jiang, Jianguo; Shen, Dinggang

2013-01-01

Segmenting prostate from MR images is important yet challenging. Due to non-Gaussian distribution of prostate appearances in MR images, the popular active appearance model (AAM) has its limited performance. Although the newly developed sparse dictionary learning method[1, 2] can model the image appearance in a non-parametric fashion, the learned dictionaries still lack the discriminative power between prostate and non-prostate tissues, which is critical for accurate prostate segmentation. In this paper, we propose to integrate deformable model with a novel learning scheme, namely the Distributed Discriminative Dictionary ( DDD ) learning, which can capture image appearance in a non-parametric and discriminative fashion. In particular, three strategies are designed to boost the tissue discriminative power of DDD. First , minimum Redundancy Maximum Relevance (mRMR) feature selection is performed to constrain the dictionary learning in a discriminative feature space. Second , linear discriminant analysis (LDA) is employed to assemble residuals from different dictionaries for optimal separation between prostate and non-prostate tissues. Third , instead of learning the global dictionaries, we learn a set of local dictionaries for the local regions (each with small appearance variations) along prostate boundary, thus achieving better tissue differentiation locally. In the application stage, DDDs will provide the appearance cues to robustly drive the deformable model onto the prostate boundary. Experiments on 50 MR prostate images show that our method can yield a Dice Ratio of 88% compared to the manual segmentations, and have 7% improvement over the conventional AAM.

Expanding the suite of measures of gender-based discrimination: gender differences in ablution facilities in South Africa

OpenAIRE

Steyn, Renier

2012-01-01

International treaties, national legislation and local by-laws all advocate the equal treatment of men and women, but claims of gender-based discrimination continue. Indicators of discrimination against women, including employment ratios and differences in income, show that there have been considerable gains in the recent past. These measures are, however, often biased. In this study a different, specific and concrete method of describing and detecting discrimination is presented, namely the ...

Improving Classification of Protein Interaction Articles Using Context Similarity-Based Feature Selection.

Science.gov (United States)

Chen, Yifei; Sun, Yuxing; Han, Bing-Qing

2015-01-01

Protein interaction article classification is a text classification task in the biological domain to determine which articles describe protein-protein interactions. Since the feature space in text classification is high-dimensional, feature selection is widely used for reducing the dimensionality of features to speed up computation without sacrificing classification performance. Many existing feature selection methods are based on the statistical measure of document frequency and term frequency. One potential drawback of these methods is that they treat features separately. Hence, first we design a similarity measure between the context information to take word cooccurrences and phrase chunks around the features into account. Then we introduce the similarity of context information to the importance measure of the features to substitute the document and term frequency. Hence we propose new context similarity-based feature selection methods. Their performance is evaluated on two protein interaction article collections and compared against the frequency-based methods. The experimental results reveal that the context similarity-based methods perform better in terms of the F1 measure and the dimension reduction rate. Benefiting from the context information surrounding the features, the proposed methods can select distinctive features effectively for protein interaction article classification.

Discriminating the precipitation phase based on different temperature thresholds in the Songhua River Basin, China

Science.gov (United States)

Zhong, Keyuan; Zheng, Fenli; Xu, Ximeng; Qin, Chao

2018-06-01

Different precipitation phases (rain, snow or sleet) differ greatly in their hydrological and erosional processes. Therefore, accurate discrimination of the precipitation phase is highly important when researching hydrologic processes and climate change at high latitudes and mountainous regions. The objective of this study was to identify suitable temperature thresholds for discriminating the precipitation phase in the Songhua River Basin (SRB) based on 20-year daily precipitation collected from 60 meteorological stations located in and around the basin. Two methods, the air temperature method (AT method) and the wet bulb temperature method (WBT method), were used to discriminate the precipitation phase. Thirteen temperature thresholds were used to discriminate snowfall in the SRB. These thresholds included air temperatures from 0 to 5.5 °C at intervals of 0.5 °C and the wet bulb temperature (WBT). Three evaluation indices, the error percentage of discriminated snowfall days (Ep), the relative error of discriminated snowfall (Re) and the determination coefficient (R2), were applied to assess the discrimination accuracy. The results showed that 2.5 °C was the optimum threshold temperature for discriminating snowfall at the scale of the entire basin. Due to differences in the landscape conditions at the different stations, the optimum threshold varied by station. The optimal threshold ranged 1.5-4.0 °C, and 19 stations, 17 stations and 18 stations had optimal thresholds of 2.5 °C, 3.0 °C, and 3.5 °C respectively, occupying 90% of all stations. Compared with using a single suitable temperature threshold to discriminate snowfall throughout the basin, it was more accurate to use the optimum threshold at each station to estimate snowfall in the basin. In addition, snowfall was underestimated when the temperature threshold was the WBT and when the temperature threshold was below 2.5 °C, whereas snowfall was overestimated when the temperature threshold exceeded 4

Face-iris multimodal biometric scheme based on feature level fusion

Science.gov (United States)

Huo, Guang; Liu, Yuanning; Zhu, Xiaodong; Dong, Hongxing; He, Fei

2015-11-01

Unlike score level fusion, feature level fusion demands all the features extracted from unimodal traits with high distinguishability, as well as homogeneity and compatibility, which is difficult to achieve. Therefore, most multimodal biometric research focuses on score level fusion, whereas few investigate feature level fusion. We propose a face-iris recognition method based on feature level fusion. We build a special two-dimensional-Gabor filter bank to extract local texture features from face and iris images, and then transform them by histogram statistics into an energy-orientation variance histogram feature with lower dimensions and higher distinguishability. Finally, through a fusion-recognition strategy based on principal components analysis and support vector machine (FRSPS), feature level fusion and one-to-n identification are accomplished. The experimental results demonstrate that this method can not only effectively extract face and iris features but also provide higher recognition accuracy. Compared with some state-of-the-art fusion methods, the proposed method has a significant performance advantage.

Human Activity Recognition Using Hierarchically-Mined Feature Constellations