Application of hierarchical clustering method to classify of space-time rainfall patterns

Science.gov (United States)

Yu, Hwa-Lung; Chang, Tu-Je

2010-05-01

Understanding the local precipitation patterns is essential to the water resources management and flooding mitigation. The precipitation patterns can vary in space and time depending upon the factors from different spatial scales such as local topological changes and macroscopic atmospheric circulation. The spatiotemporal variation of precipitation in Taiwan is significant due to its complex terrain and its location at west pacific and subtropical area, where is the boundary between the pacific ocean and Asia continent with the complex interactions among the climatic processes. This study characterizes local-scale precipitation patterns by classifying the historical space-time precipitation records. We applied the hierarchical ascending clustering method to analyze the precipitation records from 1960 to 2008 at the six rainfall stations located in Lan-yang catchment at the northeast of the island. Our results identify the four primary space-time precipitation types which may result from distinct driving forces from the changes of atmospheric variables and topology at different space-time scales. This study also presents an important application of the statistical downscaling to combine large-scale upper-air circulation with local space-time precipitation patterns.

Classifying sows' activity types from acceleration patterns

DEFF Research Database (Denmark)

Cornou, Cecile; Lundbye-Christensen, Søren

2008-01-01

An automated method of classifying sow activity using acceleration measurements would allow the individual sow's behavior to be monitored throughout the reproductive cycle; applications for detecting behaviors characteristic of estrus and farrowing or to monitor illness and welfare can be foreseen....... This article suggests a method of classifying five types of activity exhibited by group-housed sows. The method involves the measurement of acceleration in three dimensions. The five activities are: feeding, walking, rooting, lying laterally and lying sternally. Four time series of acceleration (the three...

Melodic pattern discovery by structural analysis via wavelets and clustering techniques

DEFF Research Database (Denmark)

Velarde, Gissel; Meredith, David

We present an automatic method to support melodic pattern discovery by structural analysis of symbolic representations by means of wavelet analysis and clustering techniques. In previous work, we used the method to recognize the parent works of melodic segments, or to classify tunes into tune......-means to cluster melodic segments into groups of measured similarity and obtain a raking of the most prototypical melodic segments or patterns and their occurrences. We test the method on the JKU Patterns Development Database and evaluate it based on the ground truth defined by the MIREX 2013 Discovery of Repeated...... Themes & Sections task. We compare the results of our method to the output of geometric approaches. Finally, we discuss about the relevance of our wavelet-based analysis in relation to structure, pattern discovery, similarity and variation, and comment about the considerations of the method when used...

Glaucomatous patterns in Frequency Doubling Technology (FDT) perimetry data identified by unsupervised machine learning classifiers.

Science.gov (United States)

Bowd, Christopher; Weinreb, Robert N; Balasubramanian, Madhusudhanan; Lee, Intae; Jang, Giljin; Yousefi, Siamak; Zangwill, Linda M; Medeiros, Felipe A; Girkin, Christopher A; Liebmann, Jeffrey M; Goldbaum, Michael H

2014-01-01

The variational Bayesian independent component analysis-mixture model (VIM), an unsupervised machine-learning classifier, was used to automatically separate Matrix Frequency Doubling Technology (FDT) perimetry data into clusters of healthy and glaucomatous eyes, and to identify axes representing statistically independent patterns of defect in the glaucoma clusters. FDT measurements were obtained from 1,190 eyes with normal FDT results and 786 eyes with abnormal FDT results from the UCSD-based Diagnostic Innovations in Glaucoma Study (DIGS) and African Descent and Glaucoma Evaluation Study (ADAGES). For all eyes, VIM input was 52 threshold test points from the 24-2 test pattern, plus age. FDT mean deviation was -1.00 dB (S.D. = 2.80 dB) and -5.57 dB (S.D. = 5.09 dB) in FDT-normal eyes and FDT-abnormal eyes, respectively (p<0.001). VIM identified meaningful clusters of FDT data and positioned a set of statistically independent axes through the mean of each cluster. The optimal VIM model separated the FDT fields into 3 clusters. Cluster N contained primarily normal fields (1109/1190, specificity 93.1%) and clusters G1 and G2 combined, contained primarily abnormal fields (651/786, sensitivity 82.8%). For clusters G1 and G2 the optimal number of axes were 2 and 5, respectively. Patterns automatically generated along axes within the glaucoma clusters were similar to those known to be indicative of glaucoma. Fields located farther from the normal mean on each glaucoma axis showed increasing field defect severity. VIM successfully separated FDT fields from healthy and glaucoma eyes without a priori information about class membership, and identified familiar glaucomatous patterns of loss.

Classifying Dementia Using Local Binary Patterns from Different Regions in Magnetic Resonance Images

Directory of Open Access Journals (Sweden)

Ketil Oppedal

2015-01-01

Full Text Available Dementia is an evolving challenge in society, and no disease-modifying treatment exists. Diagnosis can be demanding and MR imaging may aid as a noninvasive method to increase prediction accuracy. We explored the use of 2D local binary pattern (LBP extracted from FLAIR and T1 MR images of the brain combined with a Random Forest classifier in an attempt to discern patients with Alzheimer's disease (AD, Lewy body dementia (LBD, and normal controls (NC. Analysis was conducted in areas with white matter lesions (WML and all of white matter (WM. Results from 10-fold nested cross validation are reported as mean accuracy, precision, and recall with standard deviation in brackets. The best result we achieved was in the two-class problem NC versus AD + LBD with total accuracy of 0.98 (0.04. In the three-class problem AD versus LBD versus NC and the two-class problem AD versus LBD, we achieved 0.87 (0.08 and 0.74 (0.16, respectively. The performance using 3DT1 images was notably better than when using FLAIR images. The results from the WM region gave similar results as in the WML region. Our study demonstrates that LBP texture analysis in brain MR images can be successfully used for computer based dementia diagnosis.

Binary naive Bayesian classifiers for correlated Gaussian features: a theoretical analysis

CSIR Research Space (South Africa)

Van Dyk, E

2008-11-01

Full Text Available classifier with Gaussian features while using any quadratic decision boundary. Therefore, the analysis is not restricted to Naive Bayesian classifiers alone and can, for instance, be used to calculate the Bayes error performance. We compare the analytical...

Representative Vector Machines: A Unified Framework for Classical Classifiers.

Science.gov (United States)

Gui, Jie; Liu, Tongliang; Tao, Dacheng; Sun, Zhenan; Tan, Tieniu

2016-08-01

Classifier design is a fundamental problem in pattern recognition. A variety of pattern classification methods such as the nearest neighbor (NN) classifier, support vector machine (SVM), and sparse representation-based classification (SRC) have been proposed in the literature. These typical and widely used classifiers were originally developed from different theory or application motivations and they are conventionally treated as independent and specific solutions for pattern classification. This paper proposes a novel pattern classification framework, namely, representative vector machines (or RVMs for short). The basic idea of RVMs is to assign the class label of a test example according to its nearest representative vector. The contributions of RVMs are twofold. On one hand, the proposed RVMs establish a unified framework of classical classifiers because NN, SVM, and SRC can be interpreted as the special cases of RVMs with different definitions of representative vectors. Thus, the underlying relationship among a number of classical classifiers is revealed for better understanding of pattern classification. On the other hand, novel and advanced classifiers are inspired in the framework of RVMs. For example, a robust pattern classification method called discriminant vector machine (DVM) is motivated from RVMs. Given a test example, DVM first finds its k -NNs and then performs classification based on the robust M-estimator and manifold regularization. Extensive experimental evaluations on a variety of visual recognition tasks such as face recognition (Yale and face recognition grand challenge databases), object categorization (Caltech-101 dataset), and action recognition (Action Similarity LAbeliNg) demonstrate the advantages of DVM over other classifiers.

An ensemble of dissimilarity based classifiers for Mackerel gender determination

Science.gov (United States)

Blanco, A.; Rodriguez, R.; Martinez-Maranon, I.

2014-03-01

Mackerel is an infravalored fish captured by European fishing vessels. A manner to add value to this specie can be achieved by trying to classify it attending to its sex. Colour measurements were performed on Mackerel females and males (fresh and defrozen) extracted gonads to obtain differences between sexes. Several linear and non linear classifiers such as Support Vector Machines (SVM), k Nearest Neighbors (k-NN) or Diagonal Linear Discriminant Analysis (DLDA) can been applied to this problem. However, theyare usually based on Euclidean distances that fail to reflect accurately the sample proximities. Classifiers based on non-Euclidean dissimilarities misclassify a different set of patterns. We combine different kind of dissimilarity based classifiers. The diversity is induced considering a set of complementary dissimilarities for each model. The experimental results suggest that our algorithm helps to improve classifiers based on a single dissimilarity.

An ensemble of dissimilarity based classifiers for Mackerel gender determination

International Nuclear Information System (INIS)

Blanco, A; Rodriguez, R; Martinez-Maranon, I

2014-01-01

Mackerel is an infravalored fish captured by European fishing vessels. A manner to add value to this specie can be achieved by trying to classify it attending to its sex. Colour measurements were performed on Mackerel females and males (fresh and defrozen) extracted gonads to obtain differences between sexes. Several linear and non linear classifiers such as Support Vector Machines (SVM), k Nearest Neighbors (k-NN) or Diagonal Linear Discriminant Analysis (DLDA) can been applied to this problem. However, theyare usually based on Euclidean distances that fail to reflect accurately the sample proximities. Classifiers based on non-Euclidean dissimilarities misclassify a different set of patterns. We combine different kind of dissimilarity based classifiers. The diversity is induced considering a set of complementary dissimilarities for each model. The experimental results suggest that our algorithm helps to improve classifiers based on a single dissimilarity

HPLC fingerprint analysis combined with chemometrics for pattern recognition of ginger.

Science.gov (United States)

Feng, Xu; Kong, Weijun; Wei, Jianhe; Ou-Yang, Zhen; Yang, Meihua

2014-03-01

Ginger, the fresh rhizome of Zingiber officinale Rosc. (Zingiberaceae), has been used worldwide; however, for a long time, there has been no standard approbated internationally for its quality control. To establish an efficacious and combinational method and pattern recognition technique for quality control of ginger. A simple, accurate and reliable method based on high-performance liquid chromatography with photodiode array (HPLC-PDA) detection was developed for establishing the chemical fingerprints of 10 batches of ginger from different markets in China. The method was validated in terms of precision, reproducibility and stability; and the relative standard deviations were all less than 1.57%. On the basis of this method, the fingerprints of 10 batches of ginger samples were obtained, which showed 16 common peaks. Coupled with similarity evaluation software, the similarities between each fingerprint of the sample and the simulative mean chromatogram were in the range of 0.998-1.000. Then, the chemometric techniques, including similarity analysis, hierarchical clustering analysis and principal component analysis were applied to classify the ginger samples. Consistent results were obtained to show that ginger samples could be successfully classified into two groups. This study revealed that HPLC-PDA method was simple, sensitive and reliable for fingerprint analysis, and moreover, for pattern recognition and quality control of ginger.

Effects of cultural characteristics on building an emotion classifier through facial expression analysis

Science.gov (United States)

da Silva, Flávio Altinier Maximiano; Pedrini, Helio

2015-03-01

Facial expressions are an important demonstration of humanity's humors and emotions. Algorithms capable of recognizing facial expressions and associating them with emotions were developed and employed to compare the expressions that different cultural groups use to show their emotions. Static pictures of predominantly occidental and oriental subjects from public datasets were used to train machine learning algorithms, whereas local binary patterns, histogram of oriented gradients (HOGs), and Gabor filters were employed to describe the facial expressions for six different basic emotions. The most consistent combination, formed by the association of HOG filter and support vector machines, was then used to classify the other cultural group: there was a strong drop in accuracy, meaning that the subtle differences of facial expressions of each culture affected the classifier performance. Finally, a classifier was trained with images from both occidental and oriental subjects and its accuracy was higher on multicultural data, evidencing the need of a multicultural training set to build an efficient classifier.

Multivoxel Pattern Analysis for fMRI Data: A Review

Directory of Open Access Journals (Sweden)

Abdelhak Mahmoudi

2012-01-01

Full Text Available Functional magnetic resonance imaging (fMRI exploits blood-oxygen-level-dependent (BOLD contrasts to map neural activity associated with a variety of brain functions including sensory processing, motor control, and cognitive and emotional functions. The general linear model (GLM approach is used to reveal task-related brain areas by searching for linear correlations between the fMRI time course and a reference model. One of the limitations of the GLM approach is the assumption that the covariance across neighbouring voxels is not informative about the cognitive function under examination. Multivoxel pattern analysis (MVPA represents a promising technique that is currently exploited to investigate the information contained in distributed patterns of neural activity to infer the functional role of brain areas and networks. MVPA is considered as a supervised classification problem where a classifier attempts to capture the relationships between spatial pattern of fMRI activity and experimental conditions. In this paper , we review MVPA and describe the mathematical basis of the classification algorithms used for decoding fMRI signals, such as support vector machines (SVMs. In addition, we describe the workflow of processing steps required for MVPA such as feature selection, dimensionality reduction, cross-validation, and classifier performance estimation based on receiver operating characteristic (ROC curves.

Multivoxel Pattern Analysis for fMRI Data: A Review

Science.gov (United States)

Takerkart, Sylvain; Regragui, Fakhita; Boussaoud, Driss; Brovelli, Andrea

2012-01-01

Functional magnetic resonance imaging (fMRI) exploits blood-oxygen-level-dependent (BOLD) contrasts to map neural activity associated with a variety of brain functions including sensory processing, motor control, and cognitive and emotional functions. The general linear model (GLM) approach is used to reveal task-related brain areas by searching for linear correlations between the fMRI time course and a reference model. One of the limitations of the GLM approach is the assumption that the covariance across neighbouring voxels is not informative about the cognitive function under examination. Multivoxel pattern analysis (MVPA) represents a promising technique that is currently exploited to investigate the information contained in distributed patterns of neural activity to infer the functional role of brain areas and networks. MVPA is considered as a supervised classification problem where a classifier attempts to capture the relationships between spatial pattern of fMRI activity and experimental conditions. In this paper , we review MVPA and describe the mathematical basis of the classification algorithms used for decoding fMRI signals, such as support vector machines (SVMs). In addition, we describe the workflow of processing steps required for MVPA such as feature selection, dimensionality reduction, cross-validation, and classifier performance estimation based on receiver operating characteristic (ROC) curves. PMID:23401720

Classifying Human Activity Patterns from Smartphone Collected GPS data: a Fuzzy Classification and Aggregation Approach.

Science.gov (United States)

Wan, Neng; Lin, Ge

2016-12-01

Smartphones have emerged as a promising type of equipment for monitoring human activities in environmental health studies. However, degraded location accuracy and inconsistency of smartphone-measured GPS data have limited its effectiveness for classifying human activity patterns. This study proposes a fuzzy classification scheme for differentiating human activity patterns from smartphone-collected GPS data. Specifically, a fuzzy logic reasoning was adopted to overcome the influence of location uncertainty by estimating the probability of different activity types for single GPS points. Based on that approach, a segment aggregation method was developed to infer activity patterns, while adjusting for uncertainties of point attributes. Validations of the proposed methods were carried out based on a convenient sample of three subjects with different types of smartphones. The results indicate desirable accuracy (e.g., up to 96% in activity identification) with use of this method. Two examples were provided in the appendix to illustrate how the proposed methods could be applied in environmental health studies. Researchers could tailor this scheme to fit a variety of research topics.

Generalization in the XCSF classifier system: analysis, improvement, and extension.

Science.gov (United States)

Lanzi, Pier Luca; Loiacono, Daniele; Wilson, Stewart W; Goldberg, David E

2007-01-01

We analyze generalization in XCSF and introduce three improvements. We begin by showing that the types of generalizations evolved by XCSF can be influenced by the input range. To explain these results we present a theoretical analysis of the convergence of classifier weights in XCSF which highlights a broader issue. In XCSF, because of the mathematical properties of the Widrow-Hoff update, the convergence of classifier weights in a given subspace can be slow when the spread of the eigenvalues of the autocorrelation matrix associated with each classifier is large. As a major consequence, the system's accuracy pressure may act before classifier weights are adequately updated, so that XCSF may evolve piecewise constant approximations, instead of the intended, and more efficient, piecewise linear ones. We propose three different ways to update classifier weights in XCSF so as to increase the generalization capabilities of XCSF: one based on a condition-based normalization of the inputs, one based on linear least squares, and one based on the recursive version of linear least squares. Through a series of experiments we show that while all three approaches significantly improve XCSF, least squares approaches appear to be best performing and most robust. Finally we show how XCSF can be extended to include polynomial approximations.

Performance analysis of a Principal Component Analysis ensemble classifier for Emotiv headset P300 spellers.

Science.gov (United States)

Elsawy, Amr S; Eldawlatly, Seif; Taher, Mohamed; Aly, Gamal M

2014-01-01

The current trend to use Brain-Computer Interfaces (BCIs) with mobile devices mandates the development of efficient EEG data processing methods. In this paper, we demonstrate the performance of a Principal Component Analysis (PCA) ensemble classifier for P300-based spellers. We recorded EEG data from multiple subjects using the Emotiv neuroheadset in the context of a classical oddball P300 speller paradigm. We compare the performance of the proposed ensemble classifier to the performance of traditional feature extraction and classifier methods. Our results demonstrate the capability of the PCA ensemble classifier to classify P300 data recorded using the Emotiv neuroheadset with an average accuracy of 86.29% on cross-validation data. In addition, offline testing of the recorded data reveals an average classification accuracy of 73.3% that is significantly higher than that achieved using traditional methods. Finally, we demonstrate the effect of the parameters of the P300 speller paradigm on the performance of the method.

Prescribing patterns of medicine classified as 'antidepressants' in South African children and adolescents

Directory of Open Access Journals (Sweden)

Johanita R. Burger

2009-07-01

Full Text Available The main objective of this study was to characterise prescribing patterns of medicine classified as 'antidepressants' (hereafter simply referred to as antidepressants in children and adolescents in the private health care sector of South Africa. A retrospective drug utilisation design was used to identify patients aged 19 years and younger from a South African pharmaceutical benefit management company’s database, whom were issued at least one antidepressant between 1 January 2006 and 31 December 2006. Prescribed daily dosages (PDDs were calculated using the Statistical Analysis System® program. A total of 1 013 patients received a mean number of 2.88 (SD 3.04 prescriptions per patient. Females received more prescriptions than their male counterparts, with the highest prevalence in the 15 ≤ 19 years age group. The pharmacological groups most prescribed were the selective serotonin reuptake inhibitors (43.0% and the tricyclics (42.7%, with imipramine (22.04% and amitriptyline (19% as the most commonly prescribed drugs. Approximately 30% (n = 2 300 of all antidepressants in the study population were prescribed off-label. Amitriptyline and clomipramine were prescribed at daily dosages higher than recommended in children and adolescents aged 9 ≤ 15 years. Lithium, trimipramine, trazodone and sulpiride were prescribed at sub-therapeutic dosages in adolescents. This study provided insight in the prescribing patterns of medicine classified as antidepressants in South African children and adolescents. These drugs, however, have many indications. Further research is needed to determine reasons why specific drugs are prescribed in this population. Opsomming Die algemene doelstelling van hierdie studie was om die voorskrifpatrone van middels wat as 'antidepressante' geklassifiseer word (hierna verwys na as slegs antidepressante wat vir kinders en adolessente in die Suid-Afrikaanse private gesondheidsorgsektor voorgeskryf word, te beskryf. 'n

PyMVPA: A python toolbox for multivariate pattern analysis of fMRI data.

Science.gov (United States)

Hanke, Michael; Halchenko, Yaroslav O; Sederberg, Per B; Hanson, Stephen José; Haxby, James V; Pollmann, Stefan

2009-01-01

Decoding patterns of neural activity onto cognitive states is one of the central goals of functional brain imaging. Standard univariate fMRI analysis methods, which correlate cognitive and perceptual function with the blood oxygenation-level dependent (BOLD) signal, have proven successful in identifying anatomical regions based on signal increases during cognitive and perceptual tasks. Recently, researchers have begun to explore new multivariate techniques that have proven to be more flexible, more reliable, and more sensitive than standard univariate analysis. Drawing on the field of statistical learning theory, these new classifier-based analysis techniques possess explanatory power that could provide new insights into the functional properties of the brain. However, unlike the wealth of software packages for univariate analyses, there are few packages that facilitate multivariate pattern classification analyses of fMRI data. Here we introduce a Python-based, cross-platform, and open-source software toolbox, called PyMVPA, for the application of classifier-based analysis techniques to fMRI datasets. PyMVPA makes use of Python's ability to access libraries written in a large variety of programming languages and computing environments to interface with the wealth of existing machine learning packages. We present the framework in this paper and provide illustrative examples on its usage, features, and programmability.

New approach to detect and classify stroke in skull CT images via analysis of brain tissue densities.

Science.gov (United States)

Rebouças Filho, Pedro P; Sarmento, Róger Moura; Holanda, Gabriel Bandeira; de Alencar Lima, Daniel

2017-09-01

Cerebral vascular accident (CVA), also known as stroke, is an important health problem worldwide and it affects 16 million people worldwide every year. About 30% of those that have a stroke die and 40% remain with serious physical limitations. However, recovery in the damaged region is possible if treatment is performed immediately. In the case of a stroke, Computed Tomography (CT) is the most appropriate technique to confirm the occurrence and to investigate its extent and severity. Stroke is an emergency problem for which early identification and measures are difficult; however, computer-aided diagnoses (CAD) can play an important role in obtaining information imperceptible to the human eye. Thus, this work proposes a new method for extracting features based on radiological density patterns of the brain, called Analysis of Brain Tissue Density (ABTD). The proposed method is a specific approach applied to CT images to identify and classify the occurrence of stroke diseases. The evaluation of the results of the ABTD extractor proposed in this paper were compared with extractors already established in the literature, such as features from Gray-Level Co-Occurrence Matrix (GLCM), Local binary patterns (LBP), Central Moments (CM), Statistical Moments (SM), Hu's Moment (HM) and Zernike's Moments (ZM). Using a database of 420 CT images of the skull, each extractor was applied with the classifiers such as MLP, SVM, kNN, OPF and Bayesian to classify if a CT image represented a healthy brain or one with an ischemic or hemorrhagic stroke. ABTD had the shortest extraction time and the highest average accuracy (99.30%) when combined with OPF using the Euclidean distance. Also, the average accuracy values for all classifiers were higher than 95%. The relevance of the results demonstrated that the ABTD method is a useful algorithm to extract features that can potentially be integrated with CAD systems to assist in stroke diagnosis. Copyright © 2017 Elsevier B.V. All rights

A morphometric analysis of vegetation patterns in dryland ecosystems

Science.gov (United States)

Mander, Luke; Dekker, Stefan C.; Li, Mao; Mio, Washington; Punyasena, Surangi W.; Lenton, Timothy M.

2017-02-01

Vegetation in dryland ecosystems often forms remarkable spatial patterns. These range from regular bands of vegetation alternating with bare ground, to vegetated spots and labyrinths, to regular gaps of bare ground within an otherwise continuous expanse of vegetation. It has been suggested that spotted vegetation patterns could indicate that collapse into a bare ground state is imminent, and the morphology of spatial vegetation patterns, therefore, represents a potentially valuable source of information on the proximity of regime shifts in dryland ecosystems. In this paper, we have developed quantitative methods to characterize the morphology of spatial patterns in dryland vegetation. Our approach is based on algorithmic techniques that have been used to classify pollen grains on the basis of textural patterning, and involves constructing feature vectors to quantify the shapes formed by vegetation patterns. We have analysed images of patterned vegetation produced by a computational model and a small set of satellite images from South Kordofan (South Sudan), which illustrates that our methods are applicable to both simulated and real-world data. Our approach provides a means of quantifying patterns that are frequently described using qualitative terminology, and could be used to classify vegetation patterns in large-scale satellite surveys of dryland ecosystems.

A Gaussian mixture model based adaptive classifier for fNIRS brain-computer interfaces and its testing via simulation

Science.gov (United States)

Li, Zheng; Jiang, Yi-han; Duan, Lian; Zhu, Chao-zhe

2017-08-01

Objective. Functional near infra-red spectroscopy (fNIRS) is a promising brain imaging technology for brain-computer interfaces (BCI). Future clinical uses of fNIRS will likely require operation over long time spans, during which neural activation patterns may change. However, current decoders for fNIRS signals are not designed to handle changing activation patterns. The objective of this study is to test via simulations a new adaptive decoder for fNIRS signals, the Gaussian mixture model adaptive classifier (GMMAC). Approach. GMMAC can simultaneously classify and track activation pattern changes without the need for ground-truth labels. This adaptive classifier uses computationally efficient variational Bayesian inference to label new data points and update mixture model parameters, using the previous model parameters as priors. We test GMMAC in simulations in which neural activation patterns change over time and compare to static decoders and unsupervised adaptive linear discriminant analysis classifiers. Main results. Our simulation experiments show GMMAC can accurately decode under time-varying activation patterns: shifts of activation region, expansions of activation region, and combined contractions and shifts of activation region. Furthermore, the experiments show the proposed method can track the changing shape of the activation region. Compared to prior work, GMMAC performed significantly better than the other unsupervised adaptive classifiers on a difficult activation pattern change simulation: 99% versus  brain-computer interfaces, including neurofeedback training systems, where operation over long time spans is required.

A Large Dimensional Analysis of Regularized Discriminant Analysis Classifiers

KAUST Repository

Elkhalil, Khalil

2017-11-01

This article carries out a large dimensional analysis of standard regularized discriminant analysis classifiers designed on the assumption that data arise from a Gaussian mixture model with different means and covariances. The analysis relies on fundamental results from random matrix theory (RMT) when both the number of features and the cardinality of the training data within each class grow large at the same pace. Under mild assumptions, we show that the asymptotic classification error approaches a deterministic quantity that depends only on the means and covariances associated with each class as well as the problem dimensions. Such a result permits a better understanding of the performance of regularized discriminant analsysis, in practical large but finite dimensions, and can be used to determine and pre-estimate the optimal regularization parameter that minimizes the misclassification error probability. Despite being theoretically valid only for Gaussian data, our findings are shown to yield a high accuracy in predicting the performances achieved with real data sets drawn from the popular USPS data base, thereby making an interesting connection between theory and practice.

Consistency Analysis of Nearest Subspace Classifier

OpenAIRE

Wang, Yi

2015-01-01

The Nearest subspace classifier (NSS) finds an estimation of the underlying subspace within each class and assigns data points to the class that corresponds to its nearest subspace. This paper mainly studies how well NSS can be generalized to new samples. It is proved that NSS is strongly consistent under certain assumptions. For completeness, NSS is evaluated through experiments on various simulated and real data sets, in comparison with some other linear model based classifiers. It is also ...

Mass spectrometry-based serum proteome pattern analysis in molecular diagnostics of early stage breast cancer

Directory of Open Access Journals (Sweden)

Stobiecki Maciej

2009-07-01

Full Text Available Abstract Background Mass spectrometric analysis of the blood proteome is an emerging method of clinical proteomics. The approach exploiting multi-protein/peptide sets (fingerprints detected by mass spectrometry that reflect overall features of a specimen's proteome, termed proteome pattern analysis, have been already shown in several studies to have applicability in cancer diagnostics. We aimed to identify serum proteome patterns specific for early stage breast cancer patients using MALDI-ToF mass spectrometry. Methods Blood samples were collected before the start of therapy in a group of 92 patients diagnosed at stages I and II of the disease, and in a group of age-matched healthy controls (104 women. Serum specimens were purified and the low-molecular-weight proteome fraction was examined using MALDI-ToF mass spectrometry after removal of albumin and other high-molecular-weight serum proteins. Protein ions registered in a mass range between 2,000 and 10,000 Da were analyzed using a new bioinformatic tool created in our group, which included modeling spectra as a sum of Gaussian bell-shaped curves. Results We have identified features of serum proteome patterns that were significantly different between blood samples of healthy individuals and early stage breast cancer patients. The classifier built of three spectral components that differentiated controls and cancer patients had 83% sensitivity and 85% specificity. Spectral components (i.e., protein ions that were the most frequent in such classifiers had approximate m/z values of 2303, 2866 and 3579 Da (a biomarker built from these three components showed 88% sensitivity and 78% specificity. Of note, we did not find a significant correlation between features of serum proteome patterns and established prognostic or predictive factors like tumor size, nodal involvement, histopathological grade, estrogen and progesterone receptor expression. In addition, we observed a significantly (p = 0

Building gene expression profile classifiers with a simple and efficient rejection option in R.

Science.gov (United States)

Benso, Alfredo; Di Carlo, Stefano; Politano, Gianfranco; Savino, Alessandro; Hafeezurrehman, Hafeez

2011-01-01

The collection of gene expression profiles from DNA microarrays and their analysis with pattern recognition algorithms is a powerful technology applied to several biological problems. Common pattern recognition systems classify samples assigning them to a set of known classes. However, in a clinical diagnostics setup, novel and unknown classes (new pathologies) may appear and one must be able to reject those samples that do not fit the trained model. The problem of implementing a rejection option in a multi-class classifier has not been widely addressed in the statistical literature. Gene expression profiles represent a critical case study since they suffer from the curse of dimensionality problem that negatively reflects on the reliability of both traditional rejection models and also more recent approaches such as one-class classifiers. This paper presents a set of empirical decision rules that can be used to implement a rejection option in a set of multi-class classifiers widely used for the analysis of gene expression profiles. In particular, we focus on the classifiers implemented in the R Language and Environment for Statistical Computing (R for short in the remaining of this paper). The main contribution of the proposed rules is their simplicity, which enables an easy integration with available data analysis environments. Since in the definition of a rejection model tuning of the involved parameters is often a complex and delicate task, in this paper we exploit an evolutionary strategy to automate this process. This allows the final user to maximize the rejection accuracy with minimum manual intervention. This paper shows how the use of simple decision rules can be used to help the use of complex machine learning algorithms in real experimental setups. The proposed approach is almost completely automated and therefore a good candidate for being integrated in data analysis flows in labs where the machine learning expertise required to tune traditional

Fast Most Similar Neighbor (MSN) classifiers for Mixed Data

OpenAIRE

Hernández Rodríguez, Selene

2010-01-01

The k nearest neighbor (k-NN) classifier has been extensively used in Pattern Recognition because of its simplicity and its good performance. However, in large datasets applications, the exhaustive k-NN classifier becomes impractical. Therefore, many fast k-NN classifiers have been developed; most of them rely on metric properties (usually the triangle inequality) to reduce the number of prototype comparisons. Hence, the existing fast k-NN classifiers are applicable only when the comparison f...

Costochondral ossification pattern. Analysis by 3-dimensional CT image

International Nuclear Information System (INIS)

Ma, Hailong; Nakatani, Kimiko

2005-01-01

We reviewed about an ossification pattern of costal cartilage with using three dimensional images made from computed tomography. We analyzed ossification of 16 costal cartilages in each case. We classified ossification pattern into eight groups by its configuration in one hundred cases. The sexual specificity of ossification pattern was revealed, and we can determinate sex in 82%. It was also revealed that ossification grows with increasing age. Finally, the knowledge of costochondral ossification pattern must help in case of reading chest radiographs. (author)

Analysis of Long Bone and Vertebral Failure Patterns

Science.gov (United States)

1985-02-14

and alter the injury pattern. Classified on an anatomical, kinesiologic , £s and pathologic basis, the vertebral body fracture patterns may...814. Boyde, A. (1972) Scanning electron microscope studies of bone. In Bourne, G.H. (ed): The Biochemistry and Physiology of Bone. New York...Eyring, E.J. (1969) The biochemistry and physiology of intervertebral disk. Clin. Orthop. Rel, Res. 67: 16-18. Fick, R. (1904) Handbuch der Anatomie

A Topic Model Approach to Representing and Classifying Football Plays

KAUST Repository

Varadarajan, Jagannadan

2013-09-09

We address the problem of modeling and classifying American Football offense teams’ plays in video, a challenging example of group activity analysis. Automatic play classification will allow coaches to infer patterns and tendencies of opponents more ef- ficiently, resulting in better strategy planning in a game. We define a football play as a unique combination of player trajectories. To this end, we develop a framework that uses player trajectories as inputs to MedLDA, a supervised topic model. The joint maximiza- tion of both likelihood and inter-class margins of MedLDA in learning the topics allows us to learn semantically meaningful play type templates, as well as, classify different play types with 70% average accuracy. Furthermore, this method is extended to analyze individual player roles in classifying each play type. We validate our method on a large dataset comprising 271 play clips from real-world football games, which will be made publicly available for future comparisons.

MAMMOGRAMS ANALYSIS USING SVM CLASSIFIER IN COMBINED TRANSFORMS DOMAIN

Directory of Open Access Journals (Sweden)

B.N. Prathibha

2011-02-01

Full Text Available Breast cancer is a primary cause of mortality and morbidity in women. Reports reveal that earlier the detection of abnormalities, better the improvement in survival. Digital mammograms are one of the most effective means for detecting possible breast anomalies at early stages. Digital mammograms supported with Computer Aided Diagnostic (CAD systems help the radiologists in taking reliable decisions. The proposed CAD system extracts wavelet features and spectral features for the better classification of mammograms. The Support Vector Machines classifier is used to analyze 206 mammogram images from Mias database pertaining to the severity of abnormality, i.e., benign and malign. The proposed system gives 93.14% accuracy for discrimination between normal-malign and 87.25% accuracy for normal-benign samples and 89.22% accuracy for benign-malign samples. The study reveals that features extracted in hybrid transform domain with SVM classifier proves to be a promising tool for analysis of mammograms.

Pattern Recognition-Based Analysis of COPD in CT

DEFF Research Database (Denmark)

Sørensen, Lauge Emil Borch Laurs

recognition part is used to turn the texture measures, measured in a CT image of the lungs, into a quantitative measure of disease. This is done by applying a classifier that is trained on a training set of data examples with known lung tissue patterns. Different classification systems are considered, and we...... will in particular use the pattern recognition concepts of supervised learning, multiple instance learning, and dissimilarity representation-based classification. The proposed texture-based measures are applied to CT data from two different sources, one comprising low dose CT slices from subjects with manually...... annotated regions of emphysema and healthy tissue, and one comprising volumetric low dose CT images from subjects that are either healthy or suffer from COPD. Several experiments demonstrate that it is clearly beneficial to take the lung tissue texture into account when classifying or quantifying emphysema...

Fisher classifier and its probability of error estimation

Science.gov (United States)

Chittineni, C. B.

1979-01-01

Computationally efficient expressions are derived for estimating the probability of error using the leave-one-out method. The optimal threshold for the classification of patterns projected onto Fisher's direction is derived. A simple generalization of the Fisher classifier to multiple classes is presented. Computational expressions are developed for estimating the probability of error of the multiclass Fisher classifier.

An analysis of correlation between occlusion classification and skeletal pattern

International Nuclear Information System (INIS)

Lu Xinhua; Cai Bin; Wang Dawei; Wu Liping

2003-01-01

Objective: To study the correlation between dental relationship and skeletal pattern of individuals. Methods: 194 cases were selected and classified by angle classification, incisor relationship and skeletal pattern respectively. The correlation of angle classification and incisor relationship to skeletal pattern was analyzed with SPSS 10.0. Results: The values of correlation index (Kappa) were 0.379 and 0.494 respectively. Conclusion: The incisor relationship is more consistent with skeletal pattern than angle classification

Quantitative analysis of breast echotexture patterns in automated breast ultrasound images

International Nuclear Information System (INIS)

Chang, Ruey-Feng; Hou, Yu-Ling; Lo, Chung-Ming; Huang, Chiun-Sheng; Chen, Jeon-Hor; Kim, Won Hwa; Chang, Jung Min; Bae, Min Sun; Moon, Woo Kyung

2015-01-01

Purpose: Breast tissue composition is considered to be associated with breast cancer risk. This study aimed to develop a computer-aided classification (CAC) system to automatically classify echotexture patterns as heterogeneous or homogeneous using automated breast ultrasound (ABUS) images. Methods: A CAC system was proposed that can recognize breast echotexture patterns in ABUS images. For each case, the echotexture pattern was assessed by two expert radiologists and classified as heterogeneous or homogeneous. After neutrosophic image transformation and fuzzy c-mean clusterings, the lower and upper boundaries of the fibroglandular tissues were defined. Then, the number of hypoechoic regions and histogram features were extracted from the fibroglandular tissues, and the support vector machine model with the leave-one-out cross-validation method was utilized as the classifier. The authors’ database included a total of 208 ABUS images of the breasts of 104 females. Results: The accuracies of the proposed system for the classification of heterogeneous and homogeneous echotexture patterns were 93.48% (43/46) and 92.59% (150/162), respectively, with an overall Az (area under the receiver operating characteristic curve) of 0.9786. The agreement between the radiologists and the proposed system was almost perfect, with a kappa value of 0.814. Conclusions: The use of ABUS and the proposed method can provide quantitative information on the echotexture patterns of the breast and can be used to evaluate whether breast echotexture patterns are associated with breast cancer risk in the future

Quantitative analysis of breast echotexture patterns in automated breast ultrasound images

Energy Technology Data Exchange (ETDEWEB)

Chang, Ruey-Feng [Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei 10617, Taiwan and Department of Computer Science and Information Engineering, National Taiwan University, Taipei 10617, Taiwan (China); Hou, Yu-Ling [Graduate Institute of Biomedical Electronics and Bioinformatics, National Taiwan University, Taipei 10617, Taiwan (China); Lo, Chung-Ming [Department of Computer Science and Information Engineering, National Taiwan University, Taipei 10617, Taiwan (China); Huang, Chiun-Sheng [Department of Surgery, National Taiwan University Hospital, Taipei 10617, Taiwan (China); Chen, Jeon-Hor [Department of Radiology, E-Da Hospital and I-Shou University, Kaohsiung 82445, Taiwan and Tu and Yuen Center for Functional Onco-Imaging and Department of Radiological Science, University of California, Irvine, California 92697 (United States); Kim, Won Hwa; Chang, Jung Min; Bae, Min Sun; Moon, Woo Kyung, E-mail: moonwk@snu.ac.kr [Department of Radiology, Seoul National University Hospital, Seoul 110-744 (Korea, Republic of)

2015-08-15

Purpose: Breast tissue composition is considered to be associated with breast cancer risk. This study aimed to develop a computer-aided classification (CAC) system to automatically classify echotexture patterns as heterogeneous or homogeneous using automated breast ultrasound (ABUS) images. Methods: A CAC system was proposed that can recognize breast echotexture patterns in ABUS images. For each case, the echotexture pattern was assessed by two expert radiologists and classified as heterogeneous or homogeneous. After neutrosophic image transformation and fuzzy c-mean clusterings, the lower and upper boundaries of the fibroglandular tissues were defined. Then, the number of hypoechoic regions and histogram features were extracted from the fibroglandular tissues, and the support vector machine model with the leave-one-out cross-validation method was utilized as the classifier. The authors’ database included a total of 208 ABUS images of the breasts of 104 females. Results: The accuracies of the proposed system for the classification of heterogeneous and homogeneous echotexture patterns were 93.48% (43/46) and 92.59% (150/162), respectively, with an overall Az (area under the receiver operating characteristic curve) of 0.9786. The agreement between the radiologists and the proposed system was almost perfect, with a kappa value of 0.814. Conclusions: The use of ABUS and the proposed method can provide quantitative information on the echotexture patterns of the breast and can be used to evaluate whether breast echotexture patterns are associated with breast cancer risk in the future.

Exploring the potential of data mining techniques for the analysis of accident patterns

DEFF Research Database (Denmark)

Prato, Carlo Giacomo; Bekhor, Shlomo; Galtzur, Ayelet

2010-01-01

Research in road safety faces major challenges: individuation of the most significant determinants of traffic accidents, recognition of the most recurrent accident patterns, and allocation of resources necessary to address the most relevant issues. This paper intends to comprehend which data mining...... and association rules) data mining techniques are implemented for the analysis of traffic accidents occurred in Israel between 2001 and 2004. Results show that descriptive techniques are useful to classify the large amount of analyzed accidents, even though introduce problems with respect to the clear...... importance of input and intermediate neurons, and the relative importance of hundreds of association rules. Further research should investigate whether limiting the analysis to fatal accidents would simplify the task of data mining techniques in recognizing accident patterns without the “noise” probably...

Automatic denoising of functional MRI data: combining independent component analysis and hierarchical fusion of classifiers.

Science.gov (United States)

Salimi-Khorshidi, Gholamreza; Douaud, Gwenaëlle; Beckmann, Christian F; Glasser, Matthew F; Griffanti, Ludovica; Smith, Stephen M

2014-04-15

Many sources of fluctuation contribute to the fMRI signal, and this makes identifying the effects that are truly related to the underlying neuronal activity difficult. Independent component analysis (ICA) - one of the most widely used techniques for the exploratory analysis of fMRI data - has shown to be a powerful technique in identifying various sources of neuronally-related and artefactual fluctuation in fMRI data (both with the application of external stimuli and with the subject "at rest"). ICA decomposes fMRI data into patterns of activity (a set of spatial maps and their corresponding time series) that are statistically independent and add linearly to explain voxel-wise time series. Given the set of ICA components, if the components representing "signal" (brain activity) can be distinguished form the "noise" components (effects of motion, non-neuronal physiology, scanner artefacts and other nuisance sources), the latter can then be removed from the data, providing an effective cleanup of structured noise. Manual classification of components is labour intensive and requires expertise; hence, a fully automatic noise detection algorithm that can reliably detect various types of noise sources (in both task and resting fMRI) is desirable. In this paper, we introduce FIX ("FMRIB's ICA-based X-noiseifier"), which provides an automatic solution for denoising fMRI data via accurate classification of ICA components. For each ICA component FIX generates a large number of distinct spatial and temporal features, each describing a different aspect of the data (e.g., what proportion of temporal fluctuations are at high frequencies). The set of features is then fed into a multi-level classifier (built around several different classifiers). Once trained through the hand-classification of a sufficient number of training datasets, the classifier can then automatically classify new datasets. The noise components can then be subtracted from (or regressed out of) the original

Angiographic patterns of in-stent restenosis classified by computed tomography in patients with drug-eluting stents: correlation with invasive coronary angiography

International Nuclear Information System (INIS)

Pan, Jingwei; Lu, Zhigang; Wei, Meng; Zhang, Jiayin; Li, Minghua

2013-01-01

To evaluate the diagnostic accuracy of Mehran's in-stent restenosis (ISR) classification by coronary computed angiography (CCTA), with reference to invasive coronary angiography (ICA). Consecutive symptomatic patients, who had clinically suspected ISR and implanted stent diameter ≥ 3 mm, were prospectively enrolled in our study. Mehran's classification was employed by CCTA and ICA to classify ISR lesions into four subtypes: focal, diffuse intrastent, diffuse proliferative and total occlusion. CCTA and ICA measurement of lesion length was further compared. Sixty-one patients with 101 implanted stents were included in our study. The overall sensitivity, specificity, PPV and NPV of CCTA diagnosis of binary ISR, as shown by patient-based analysis (n = 61), were 100 % (49/49), 75 % (8/12), 92.45 % (49/53) and 100 % (8/8) respectively. Mehran's classification of CCTA correlated well with ICA findings. The diagnostic accuracy of CCTA for class I, class II, class III and class IV lesions was 92.5 %, 91.67 %, 100 % and 100 % respectively. Lesion length was assessed to be significantly longer with CCTA than with ICA (11.03 ± 5.89 mm versus 8.56 ± 4.99 mm, P < 0.001). Angiographic patterns of in-stent restenosis can be accurately classified by coronary computed angiography. The lesion length measured by CCTA is longer than that assessed by invasive coronary angiography. (orig.)

Pharmacokinetic Tumor Heterogeneity as a Prognostic Biomarker for Classifying Breast Cancer Recurrence Risk.

Science.gov (United States)

Mahrooghy, Majid; Ashraf, Ahmed B; Daye, Dania; McDonald, Elizabeth S; Rosen, Mark; Mies, Carolyn; Feldman, Michael; Kontos, Despina

2015-06-01

Heterogeneity in cancer can affect response to therapy and patient prognosis. Histologic measures have classically been used to measure heterogeneity, although a reliable noninvasive measurement is needed both to establish baseline risk of recurrence and monitor response to treatment. Here, we propose using spatiotemporal wavelet kinetic features from dynamic contrast-enhanced magnetic resonance imaging to quantify intratumor heterogeneity in breast cancer. Tumor pixels are first partitioned into homogeneous subregions using pharmacokinetic measures. Heterogeneity wavelet kinetic (HetWave) features are then extracted from these partitions to obtain spatiotemporal patterns of the wavelet coefficients and the contrast agent uptake. The HetWave features are evaluated in terms of their prognostic value using a logistic regression classifier with genetic algorithm wrapper-based feature selection to classify breast cancer recurrence risk as determined by a validated gene expression assay. Receiver operating characteristic analysis and area under the curve (AUC) are computed to assess classifier performance using leave-one-out cross validation. The HetWave features outperform other commonly used features (AUC = 0.88 HetWave versus 0.70 standard features). The combination of HetWave and standard features further increases classifier performance (AUCs 0.94). The rate of the spatial frequency pattern over the pharmacokinetic partitions can provide valuable prognostic information. HetWave could be a powerful feature extraction approach for characterizing tumor heterogeneity, providing valuable prognostic information.

Recognition of Arabic Sign Language Alphabet Using Polynomial Classifiers

Directory of Open Access Journals (Sweden)

M. Al-Rousan

2005-08-01

Full Text Available Building an accurate automatic sign language recognition system is of great importance in facilitating efficient communication with deaf people. In this paper, we propose the use of polynomial classifiers as a classification engine for the recognition of Arabic sign language (ArSL alphabet. Polynomial classifiers have several advantages over other classifiers in that they do not require iterative training, and that they are highly computationally scalable with the number of classes. Based on polynomial classifiers, we have built an ArSL system and measured its performance using real ArSL data collected from deaf people. We show that the proposed system provides superior recognition results when compared with previously published results using ANFIS-based classification on the same dataset and feature extraction methodology. The comparison is shown in terms of the number of misclassified test patterns. The reduction in the rate of misclassified patterns was very significant. In particular, we have achieved a 36% reduction of misclassifications on the training data and 57% on the test data.

Localizing genes to cerebellar layers by classifying ISH images.

Directory of Open Access Journals (Sweden)

Lior Kirsch

Full Text Available Gene expression controls how the brain develops and functions. Understanding control processes in the brain is particularly hard since they involve numerous types of neurons and glia, and very little is known about which genes are expressed in which cells and brain layers. Here we describe an approach to detect genes whose expression is primarily localized to a specific brain layer and apply it to the mouse cerebellum. We learn typical spatial patterns of expression from a few markers that are known to be localized to specific layers, and use these patterns to predict localization for new genes. We analyze images of in-situ hybridization (ISH experiments, which we represent using histograms of local binary patterns (LBP and train image classifiers and gene classifiers for four layers of the cerebellum: the Purkinje, granular, molecular and white matter layer. On held-out data, the layer classifiers achieve accuracy above 94% (AUC by representing each image at multiple scales and by combining multiple image scores into a single gene-level decision. When applied to the full mouse genome, the classifiers predict specific layer localization for hundreds of new genes in the Purkinje and granular layers. Many genes localized to the Purkinje layer are likely to be expressed in astrocytes, and many others are involved in lipid metabolism, possibly due to the unusual size of Purkinje cells.

IAEA safeguards and classified materials

International Nuclear Information System (INIS)

Pilat, J.F.; Eccleston, G.W.; Fearey, B.L.; Nicholas, N.J.; Tape, J.W.; Kratzer, M.

1997-01-01

The international community in the post-Cold War period has suggested that the International Atomic Energy Agency (IAEA) utilize its expertise in support of the arms control and disarmament process in unprecedented ways. The pledges of the US and Russian presidents to place excess defense materials, some of which are classified, under some type of international inspections raises the prospect of using IAEA safeguards approaches for monitoring classified materials. A traditional safeguards approach, based on nuclear material accountancy, would seem unavoidably to reveal classified information. However, further analysis of the IAEA's safeguards approaches is warranted in order to understand fully the scope and nature of any problems. The issues are complex and difficult, and it is expected that common technical understandings will be essential for their resolution. Accordingly, this paper examines and compares traditional safeguards item accounting of fuel at a nuclear power station (especially spent fuel) with the challenges presented by inspections of classified materials. This analysis is intended to delineate more clearly the problems as well as reveal possible approaches, techniques, and technologies that could allow the adaptation of safeguards to the unprecedented task of inspecting classified materials. It is also hoped that a discussion of these issues can advance ongoing political-technical debates on international inspections of excess classified materials

Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis

International Nuclear Information System (INIS)

Li Qiang; Doi Kunio

2006-01-01

Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists detect various lesions in medical images. In CAD schemes, classifiers play a key role in achieving a high lesion detection rate and a low false-positive rate. Although many popular classifiers such as linear discriminant analysis and artificial neural networks have been employed in CAD schemes for reduction of false positives, a rule-based classifier has probably been the simplest and most frequently used one since the early days of development of various CAD schemes. However, with existing rule-based classifiers, there are major disadvantages that significantly reduce their practicality and credibility. The disadvantages include manual design, poor reproducibility, poor evaluation methods such as resubstitution, and a large overtraining effect. An automated rule-based classifier with a minimized overtraining effect can overcome or significantly reduce the extent of the above-mentioned disadvantages. In this study, we developed an 'optimal' method for the selection of cutoff thresholds and a fully automated rule-based classifier. Experimental results performed with Monte Carlo simulation and a real lung nodule CT data set demonstrated that the automated threshold selection method can completely eliminate overtraining effect in the procedure of cutoff threshold selection, and thus can minimize overall overtraining effect in the constructed rule-based classifier. We believe that this threshold selection method is very useful in the construction of automated rule-based classifiers with minimized overtraining effect

Data Stream Classification Based on the Gamma Classifier

Directory of Open Access Journals (Sweden)

Abril Valeria Uriarte-Arcia

2015-01-01

Full Text Available The ever increasing data generation confronts us with the problem of handling online massive amounts of information. One of the biggest challenges is how to extract valuable information from these massive continuous data streams during single scanning. In a data stream context, data arrive continuously at high speed; therefore the algorithms developed to address this context must be efficient regarding memory and time management and capable of detecting changes over time in the underlying distribution that generated the data. This work describes a novel method for the task of pattern classification over a continuous data stream based on an associative model. The proposed method is based on the Gamma classifier, which is inspired by the Alpha-Beta associative memories, which are both supervised pattern recognition models. The proposed method is capable of handling the space and time constrain inherent to data stream scenarios. The Data Streaming Gamma classifier (DS-Gamma classifier implements a sliding window approach to provide concept drift detection and a forgetting mechanism. In order to test the classifier, several experiments were performed using different data stream scenarios with real and synthetic data streams. The experimental results show that the method exhibits competitive performance when compared to other state-of-the-art algorithms.

Change detection for synthetic aperture radar images based on pattern and intensity distinctiveness analysis

Science.gov (United States)

Wang, Xiao; Gao, Feng; Dong, Junyu; Qi, Qiang

2018-04-01

Synthetic aperture radar (SAR) image is independent on atmospheric conditions, and it is the ideal image source for change detection. Existing methods directly analysis all the regions in the speckle noise contaminated difference image. The performance of these methods is easily affected by small noisy regions. In this paper, we proposed a novel change detection framework for saliency-guided change detection based on pattern and intensity distinctiveness analysis. The saliency analysis step can remove small noisy regions, and therefore makes the proposed method more robust to the speckle noise. In the proposed method, the log-ratio operator is first utilized to obtain a difference image (DI). Then, the saliency detection method based on pattern and intensity distinctiveness analysis is utilized to obtain the changed region candidates. Finally, principal component analysis and k-means clustering are employed to analysis pixels in the changed region candidates. Thus, the final change map can be obtained by classifying these pixels into changed or unchanged class. The experiment results on two real SAR images datasets have demonstrated the effectiveness of the proposed method.

Attractor structure discriminates sleep states: recurrence plot analysis applied to infant breathing patterns.

Science.gov (United States)

Terrill, Philip Ian; Wilson, Stephen James; Suresh, Sadasivam; Cooper, David M; Dakin, Carolyn

2010-05-01

Breathing patterns are characteristically different between infant active sleep (AS) and quiet sleep (QS), and statistical quantifications of interbreath interval (IBI) data have previously been used to discriminate between infant sleep states. It has also been identified that breathing patterns are governed by a nonlinear controller. This study aims to investigate whether nonlinear quantifications of infant IBI data are characteristically different between AS and QS, and whether they may be used to discriminate between these infant sleep states. Polysomnograms were obtained from 24 healthy infants at six months of age. Periods of AS and QS were identified, and IBI data extracted. Recurrence quantification analysis (RQA) was applied to each period, and recurrence calculated for a fixed radius in the range of 0-8 in steps of 0.02, and embedding dimensions of 4, 6, 8, and 16. When a threshold classifier was trained, the RQA variable recurrence was able to correctly classify 94.3% of periods in a test dataset. It was concluded that RQA of IBI data is able to accurately discriminate between infant sleep states. This is a promising step toward development of a minimal-channel automatic sleep state classification system.

Oblique decision trees using embedded support vector machines in classifier ensembles

NARCIS (Netherlands)

Menkovski, V.; Christou, I.; Efremidis, S.

2008-01-01

Classifier ensembles have emerged in recent years as a promising research area for boosting pattern recognition systems' performance. We present a new base classifier that utilizes oblique decision tree technology based on support vector machines for the construction of oblique (non-axis parallel)

Stack filter classifiers

Energy Technology Data Exchange (ETDEWEB)

Porter, Reid B [Los Alamos National Laboratory; Hush, Don [Los Alamos National Laboratory

2009-01-01

Just as linear models generalize the sample mean and weighted average, weighted order statistic models generalize the sample median and weighted median. This analogy can be continued informally to generalized additive modeels in the case of the mean, and Stack Filters in the case of the median. Both of these model classes have been extensively studied for signal and image processing but it is surprising to find that for pattern classification, their treatment has been significantly one sided. Generalized additive models are now a major tool in pattern classification and many different learning algorithms have been developed to fit model parameters to finite data. However Stack Filters remain largely confined to signal and image processing and learning algorithms for classification are yet to be seen. This paper is a step towards Stack Filter Classifiers and it shows that the approach is interesting from both a theoretical and a practical perspective.

Asymptotic performance of regularized quadratic discriminant analysis based classifiers

KAUST Repository

Elkhalil, Khalil

2017-12-13

This paper carries out a large dimensional analysis of the standard regularized quadratic discriminant analysis (QDA) classifier designed on the assumption that data arise from a Gaussian mixture model. The analysis relies on fundamental results from random matrix theory (RMT) when both the number of features and the cardinality of the training data within each class grow large at the same pace. Under some mild assumptions, we show that the asymptotic classification error converges to a deterministic quantity that depends only on the covariances and means associated with each class as well as the problem dimensions. Such a result permits a better understanding of the performance of regularized QDA and can be used to determine the optimal regularization parameter that minimizes the misclassification error probability. Despite being valid only for Gaussian data, our theoretical findings are shown to yield a high accuracy in predicting the performances achieved with real data sets drawn from popular real data bases, thereby making an interesting connection between theory and practice.

Interface Prostheses With Classifier-Feedback-Based User Training.

Science.gov (United States)

Fang, Yinfeng; Zhou, Dalin; Li, Kairu; Liu, Honghai

2017-11-01

It is evident that user training significantly affects performance of pattern-recognition-based myoelectric prosthetic device control. Despite plausible classification accuracy on offline datasets, online accuracy usually suffers from the changes in physiological conditions and electrode displacement. The user ability in generating consistent electromyographic (EMG) patterns can be enhanced via proper user training strategies in order to improve online performance. This study proposes a clustering-feedback strategy that provides real-time feedback to users by means of a visualized online EMG signal input as well as the centroids of the training samples, whose dimensionality is reduced to minimal number by dimension reduction. Clustering feedback provides a criterion that guides users to adjust motion gestures and muscle contraction forces intentionally. The experiment results have demonstrated that hand motion recognition accuracy increases steadily along the progress of the clustering-feedback-based user training, while conventional classifier-feedback methods, i.e., label feedback, hardly achieve any improvement. The result concludes that the use of proper classifier feedback can accelerate the process of user training, and implies prosperous future for the amputees with limited or no experience in pattern-recognition-based prosthetic device manipulation.It is evident that user training significantly affects performance of pattern-recognition-based myoelectric prosthetic device control. Despite plausible classification accuracy on offline datasets, online accuracy usually suffers from the changes in physiological conditions and electrode displacement. The user ability in generating consistent electromyographic (EMG) patterns can be enhanced via proper user training strategies in order to improve online performance. This study proposes a clustering-feedback strategy that provides real-time feedback to users by means of a visualized online EMG signal input as well

Local curvature analysis for classifying breast tumors: Preliminary analysis in dedicated breast CT

International Nuclear Information System (INIS)

Lee, Juhun; Nishikawa, Robert M.; Reiser, Ingrid; Boone, John M.; Lindfors, Karen K.

2015-01-01

Purpose: The purpose of this study is to measure the effectiveness of local curvature measures as novel image features for classifying breast tumors. Methods: A total of 119 breast lesions from 104 noncontrast dedicated breast computed tomography images of women were used in this study. Volumetric segmentation was done using a seed-based segmentation algorithm and then a triangulated surface was extracted from the resulting segmentation. Total, mean, and Gaussian curvatures were then computed. Normalized curvatures were used as classification features. In addition, traditional image features were also extracted and a forward feature selection scheme was used to select the optimal feature set. Logistic regression was used as a classifier and leave-one-out cross-validation was utilized to evaluate the classification performances of the features. The area under the receiver operating characteristic curve (AUC, area under curve) was used as a figure of merit. Results: Among curvature measures, the normalized total curvature (C_T) showed the best classification performance (AUC of 0.74), while the others showed no classification power individually. Five traditional image features (two shape, two margin, and one texture descriptors) were selected via the feature selection scheme and its resulting classifier achieved an AUC of 0.83. Among those five features, the radial gradient index (RGI), which is a margin descriptor, showed the best classification performance (AUC of 0.73). A classifier combining RGI and C_T yielded an AUC of 0.81, which showed similar performance (i.e., no statistically significant difference) to the classifier with the above five traditional image features. Additional comparisons in AUC values between classifiers using different combinations of traditional image features and C_T were conducted. The results showed that C_T was able to replace the other four image features for the classification task. Conclusions: The normalized curvature measure

An eye tracking study of bloodstain pattern analysts during pattern classification.

Science.gov (United States)

Arthur, R M; Hoogenboom, J; Green, R D; Taylor, M C; de Bruin, K G

2018-05-01

Bloodstain pattern analysis (BPA) is the forensic discipline concerned with the classification and interpretation of bloodstains and bloodstain patterns at the crime scene. At present, it is unclear exactly which stain or pattern properties and their associated values are most relevant to analysts when classifying a bloodstain pattern. Eye tracking technology has been widely used to investigate human perception and cognition. Its application to forensics, however, is limited. This is the first study to use eye tracking as a tool for gaining access to the mindset of the bloodstain pattern expert. An eye tracking method was used to follow the gaze of 24 bloodstain pattern analysts during an assigned task of classifying a laboratory-generated test bloodstain pattern. With the aid of an automated image-processing methodology, the properties of selected features of the pattern were quantified leading to the delineation of areas of interest (AOIs). Eye tracking data were collected for each AOI and combined with verbal statements made by analysts after the classification task to determine the critical range of values for relevant diagnostic features. Eye-tracking data indicated that there were four main regions of the pattern that analysts were most interested in. Within each region, individual elements or groups of elements that exhibited features associated with directionality, size, colour and shape appeared to capture the most interest of analysts during the classification task. The study showed that the eye movements of trained bloodstain pattern experts and their verbal descriptions of a pattern were well correlated.

Variants of the Borda count method for combining ranked classifier hypotheses

NARCIS (Netherlands)

van Erp, Merijn; Schomaker, Lambert; Schomaker, Lambert; Vuurpijl, Louis

2000-01-01

The Borda count is a simple yet effective method of combining rankings. In pattern recognition, classifiers are often able to return a ranked set of results. Several experiments have been conducted to test the ability of the Borda count and two variant methods to combine these ranked classifier

Multivariate analysis of quantitative traits can effectively classify rapeseed germplasm

Directory of Open Access Journals (Sweden)

Jankulovska Mirjana

2014-01-01

Full Text Available In this study, the use of different multivariate approaches to classify rapeseed genotypes based on quantitative traits has been presented. Tree regression analysis, PCA analysis and two-way cluster analysis were applied in order todescribe and understand the extent of genetic variability in spring rapeseed genotype by trait data. The traits which highly influenced seed and oil yield in rapeseed were successfully identified by the tree regression analysis. Principal predictor for both response variables was number of pods per plant (NP. NP and 1000 seed weight could help in the selection of high yielding genotypes. High values for both traits and oil content could lead to high oil yielding genotypes. These traits may serve as indirect selection criteria and can lead to improvement of seed and oil yield in rapeseed. Quantitative traits that explained most of the variability in the studied germplasm were classified using principal component analysis. In this data set, five PCs were identified, out of which the first three PCs explained 63% of the total variance. It helped in facilitating the choice of variables based on which the genotypes’ clustering could be performed. The two-way cluster analysissimultaneously clustered genotypes and quantitative traits. The final number of clusters was determined using bootstrapping technique. This approach provided clear overview on the variability of the analyzed genotypes. The genotypes that have similar performance regarding the traits included in this study can be easily detected on the heatmap. Genotypes grouped in the clusters 1 and 8 had high values for seed and oil yield, and relatively short vegetative growth duration period and those in cluster 9, combined moderate to low values for vegetative growth duration and moderate to high seed and oil yield. These genotypes should be further exploited and implemented in the rapeseed breeding program. The combined application of these multivariate methods

Multivariate pattern analysis of obsessive-compulsive disorder using structural neuroanatomy.

Science.gov (United States)

Hu, Xinyu; Liu, Qi; Li, Bin; Tang, Wanjie; Sun, Huaiqiang; Li, Fei; Yang, Yanchun; Gong, Qiyong; Huang, Xiaoqi

2016-02-01

Magnetic resonance imaging (MRI) studies have revealed brain structural abnormalities in obsessive-compulsive disorder (OCD) patients, involving both gray matter (GM) and white matter (WM). However, the results of previous publications were based on average differences between groups, which limited their usages in clinical practice. Therefore, the aim of this study was to examine whether the application of multivariate pattern analysis (MVPA) to high-dimensional structural images would allow accurate discrimination between OCD patients and healthy control subjects (HCS). High-resolution T1-weighted images were acquired from 33 OCD patients and 33 demographically matched HCS in a 3.0 T scanner. Differences in GM and WM volume between OCD and HCS were examined using two types of well-established MVPA techniques: support vector machine (SVM) and Gaussian process classifier (GPC). We also drew a receiver operating characteristic (ROC) curve to evaluate the performance of each classifier. The classification accuracies for both classifiers using GM and WM anatomy were all above 75%. The highest classification accuracy (81.82%, P<0.001) was achieved with the SVM classifier using WM information. Regional brain anomalies with high discriminative power were based on three distributed networks including the fronto-striatal circuit, the temporo-parieto-occipital junction and the cerebellum. Our study illustrated that both GM and WM anatomical features may be useful in differentiating OCD patients from HCS. WM volume using the SVM approach showed the highest accuracy in our population for revealing group differences, which suggested its potential diagnostic role in detecting highly enriched OCD patients at the level of the individual. Copyright © 2015 Elsevier B.V. and ECNP. All rights reserved.

Classifier Fusion With Contextual Reliability Evaluation.

Science.gov (United States)

Liu, Zhunga; Pan, Quan; Dezert, Jean; Han, Jun-Wei; He, You

2018-05-01

Classifier fusion is an efficient strategy to improve the classification performance for the complex pattern recognition problem. In practice, the multiple classifiers to combine can have different reliabilities and the proper reliability evaluation plays an important role in the fusion process for getting the best classification performance. We propose a new method for classifier fusion with contextual reliability evaluation (CF-CRE) based on inner reliability and relative reliability concepts. The inner reliability, represented by a matrix, characterizes the probability of the object belonging to one class when it is classified to another class. The elements of this matrix are estimated from the -nearest neighbors of the object. A cautious discounting rule is developed under belief functions framework to revise the classification result according to the inner reliability. The relative reliability is evaluated based on a new incompatibility measure which allows to reduce the level of conflict between the classifiers by applying the classical evidence discounting rule to each classifier before their combination. The inner reliability and relative reliability capture different aspects of the classification reliability. The discounted classification results are combined with Dempster-Shafer's rule for the final class decision making support. The performance of CF-CRE have been evaluated and compared with those of main classical fusion methods using real data sets. The experimental results show that CF-CRE can produce substantially higher accuracy than other fusion methods in general. Moreover, CF-CRE is robust to the changes of the number of nearest neighbors chosen for estimating the reliability matrix, which is appealing for the applications.

Hierarchical cluster analysis of progression patterns in open-angle glaucoma patients with medical treatment.

Science.gov (United States)

Bae, Hyoung Won; Rho, Seungsoo; Lee, Hye Sun; Lee, Naeun; Hong, Samin; Seong, Gong Je; Sung, Kyung Rim; Kim, Chan Yun

2014-04-29

To classify medically treated open-angle glaucoma (OAG) by the pattern of progression using hierarchical cluster analysis, and to determine OAG progression characteristics by comparing clusters. Ninety-five eyes of 95 OAG patients who received medical treatment, and who had undergone visual field (VF) testing at least once per year for 5 or more years. OAG was classified into subgroups using hierarchical cluster analysis based on the following five variables: baseline mean deviation (MD), baseline visual field index (VFI), MD slope, VFI slope, and Glaucoma Progression Analysis (GPA) printout. After that, other parameters were compared between clusters. Two clusters were made after a hierarchical cluster analysis. Cluster 1 showed -4.06 ± 2.43 dB baseline MD, 92.58% ± 6.27% baseline VFI, -0.28 ± 0.38 dB per year MD slope, -0.52% ± 0.81% per year VFI slope, and all "no progression" cases in GPA printout, whereas cluster 2 showed -8.68 ± 3.81 baseline MD, 77.54 ± 12.98 baseline VFI, -0.72 ± 0.55 MD slope, -2.22 ± 1.89 VFI slope, and seven "possible" and four "likely" progression cases in GPA printout. There were no significant differences in age, sex, mean IOP, central corneal thickness, and axial length between clusters. However, cluster 2 included more high-tension glaucoma patients and used a greater number of antiglaucoma eye drops significantly compared with cluster 1. Hierarchical cluster analysis of progression patterns divided OAG into slow and fast progression groups, evidenced by assessing the parameters of glaucomatous progression in VF testing. In the fast progression group, the prevalence of high-tension glaucoma was greater and the number of antiglaucoma medications administered was increased versus the slow progression group. Copyright 2014 The Association for Research in Vision and Ophthalmology, Inc.

Predict or classify: The deceptive role of time-locking in brain signal classification

Science.gov (United States)

Rusconi, Marco; Valleriani, Angelo

2016-06-01

Several experimental studies claim to be able to predict the outcome of simple decisions from brain signals measured before subjects are aware of their decision. Often, these studies use multivariate pattern recognition methods with the underlying assumption that the ability to classify the brain signal is equivalent to predict the decision itself. Here we show instead that it is possible to correctly classify a signal even if it does not contain any predictive information about the decision. We first define a simple stochastic model that mimics the random decision process between two equivalent alternatives, and generate a large number of independent trials that contain no choice-predictive information. The trials are first time-locked to the time point of the final event and then classified using standard machine-learning techniques. The resulting classification accuracy is above chance level long before the time point of time-locking. We then analyze the same trials using information theory. We demonstrate that the high classification accuracy is a consequence of time-locking and that its time behavior is simply related to the large relaxation time of the process. We conclude that when time-locking is a crucial step in the analysis of neural activity patterns, both the emergence and the timing of the classification accuracy are affected by structural properties of the network that generates the signal.

Adaptive pattern recognition in real-time video-based soccer analysis

DEFF Research Database (Denmark)

Schlipsing, Marc; Salmen, Jan; Tschentscher, Marc

2017-01-01

are taken into account. Our contribution is twofold: (1) the deliberate use of machine learning and pattern recognition techniques allows us to achieve high classification accuracy in varying environments. We systematically evaluate combinations of image features and learning machines in the given online......Computer-aided sports analysis is demanded by coaches and the media. Image processing and machine learning techniques that allow for "live" recognition and tracking of players exist. But these methods are far from collecting and analyzing event data fully autonomously. To generate accurate results......, human interaction is required at different stages including system setup, calibration, supervision of classifier training, and resolution of tracking conflicts. Furthermore, the real-time constraints are challenging: in contrast to other object recognition and tracking applications, we cannot treat data...

Robust Combining of Disparate Classifiers Through Order Statistics

Science.gov (United States)

Tumer, Kagan; Ghosh, Joydeep

2001-01-01

Integrating the outputs of multiple classifiers via combiners or meta-learners has led to substantial improvements in several difficult pattern recognition problems. In this article we investigate a family of combiners based on order statistics, for robust handling of situations where there are large discrepancies in performance of individual classifiers. Based on a mathematical modeling of how the decision boundaries are affected by order statistic combiners, we derive expressions for the reductions in error expected when simple output combination methods based on the the median, the maximum and in general, the ith order statistic, are used. Furthermore, we analyze the trim and spread combiners, both based on linear combinations of the ordered classifier outputs, and show that in the presence of uneven classifier performance, they often provide substantial gains over both linear and simple order statistics combiners. Experimental results on both real world data and standard public domain data sets corroborate these findings.

Investigation of using wavelet analysis for classifying pattern of cyclic voltammetry signals

Science.gov (United States)

Jityen, Arthit; Juagwon, Teerasak; Jaisuthi, Rawat; Osotchan, Tanakorn

2017-09-01

Wavelet analysis is an excellent technique for data processing analysis based on linear vector algebra since it has an ability to perform local analysis and is able to analyze an unspecific localized area of a large signal. In this work, the wavelet analysis of cyclic waveform was investigated in order to find the distinguishable feature from the cyclic data. The analyzed wavelet coefficients were proposed to be used as selected cyclic feature parameters. The cyclic voltammogram (CV) of different electrodes consisting of carbon nanotube (CNT) and several types of metal phthalocyanine (MPc) including CoPc, FePc, ZnPc and MnPc powders was used as several sets of cyclic data for various types of coffee. The mixture powder was embedded in a hollow Teflon rod and used as working electrodes. Electrochemical response of the fabricated electrodes in Robusta, blend coffee I, blend coffee II, chocolate malt and cocoa at the same concentrations was measured with scanning rate of 0.05V/s from -1.5 to 1.5V respectively to Ag/AgCl electrode for five scanning loops. The CV of blended CNT electrode with some MPc electrodes indicated the ionic interaction which can be the effect of catalytic oxidation of saccharides and/or polyphenol on the sensor surface. The major information of CV response can be extracted by using several mother wavelet families viz. daubechies (dB1 to dB3), coiflets (coiflet1), biorthogonal (Bior1.1) and symlets (sym2) and then the discrimination of these wavelet coefficients of each data group can be separated by principal component analysis (PCA). The PCA results indicated the clearly separate groups with total contribution more than 62.37% representing from PC1 and PC2.

Classification of Multiple Chinese Liquors by Means of a QCM-based E-Nose and MDS-SVM Classifier.

Science.gov (United States)

Li, Qiang; Gu, Yu; Jia, Jing

2017-01-30

Chinese liquors are internationally well-known fermentative alcoholic beverages. They have unique flavors attributable to the use of various bacteria and fungi, raw materials, and production processes. Developing a novel, rapid, and reliable method to identify multiple Chinese liquors is of positive significance. This paper presents a pattern recognition system for classifying ten brands of Chinese liquors based on multidimensional scaling (MDS) and support vector machine (SVM) algorithms in a quartz crystal microbalance (QCM)-based electronic nose (e-nose) we designed. We evaluated the comprehensive performance of the MDS-SVM classifier that predicted all ten brands of Chinese liquors individually. The prediction accuracy (98.3%) showed superior performance of the MDS-SVM classifier over the back-propagation artificial neural network (BP-ANN) classifier (93.3%) and moving average-linear discriminant analysis (MA-LDA) classifier (87.6%). The MDS-SVM classifier has reasonable reliability, good fitting and prediction (generalization) performance in classification of the Chinese liquors. Taking both application of the e-nose and validation of the MDS-SVM classifier into account, we have thus created a useful method for the classification of multiple Chinese liquors.

Classification of Multiple Chinese Liquors by Means of a QCM-based E-Nose and MDS-SVM Classifier

Directory of Open Access Journals (Sweden)

Qiang Li

2017-01-01

Full Text Available Chinese liquors are internationally well-known fermentative alcoholic beverages. They have unique flavors attributable to the use of various bacteria and fungi, raw materials, and production processes. Developing a novel, rapid, and reliable method to identify multiple Chinese liquors is of positive significance. This paper presents a pattern recognition system for classifying ten brands of Chinese liquors based on multidimensional scaling (MDS and support vector machine (SVM algorithms in a quartz crystal microbalance (QCM-based electronic nose (e-nose we designed. We evaluated the comprehensive performance of the MDS-SVM classifier that predicted all ten brands of Chinese liquors individually. The prediction accuracy (98.3% showed superior performance of the MDS-SVM classifier over the back-propagation artificial neural network (BP-ANN classifier (93.3% and moving average-linear discriminant analysis (MA-LDA classifier (87.6%. The MDS-SVM classifier has reasonable reliability, good fitting and prediction (generalization performance in classification of the Chinese liquors. Taking both application of the e-nose and validation of the MDS-SVM classifier into account, we have thus created a useful method for the classification of multiple Chinese liquors.

Exemplar-based optical neural net classifier for color pattern recognition

Science.gov (United States)

Yu, Francis T. S.; Uang, Chii-Maw; Yang, Xiangyang

1992-10-01

We present a color exemplar-based neural network that can be used as an optimum image classifier or an associative memory. Color decomposition and composition technique is used for constructing the polychromatic interconnection weight matrix (IWM). The Hamming net algorithm is modified to relax the dynamic range requirement of the spatial light modulator and to reduce the number of iteration cycles in the winner-take-all layer. Computer simulation results demonstrated the feasibility of this approach

Comparison of multivariate preprocessing techniques as applied to electronic tongue based pattern classification for black tea

International Nuclear Information System (INIS)

Palit, Mousumi; Tudu, Bipan; Bhattacharyya, Nabarun; Dutta, Ankur; Dutta, Pallab Kumar; Jana, Arun; Bandyopadhyay, Rajib; Chatterjee, Anutosh

2010-01-01

In an electronic tongue, preprocessing on raw data precedes pattern analysis and choice of the appropriate preprocessing technique is crucial for the performance of the pattern classifier. While attempting to classify different grades of black tea using a voltammetric electronic tongue, different preprocessing techniques have been explored and a comparison of their performances is presented in this paper. The preprocessing techniques are compared first by a quantitative measurement of separability followed by principle component analysis; and then two different supervised pattern recognition models based on neural networks are used to evaluate the performance of the preprocessing techniques.

Simultaneous-Fault Diagnosis of Gas Turbine Generator Systems Using a Pairwise-Coupled Probabilistic Classifier

Directory of Open Access Journals (Sweden)

Zhixin Yang

2013-01-01

Full Text Available A reliable fault diagnostic system for gas turbine generator system (GTGS, which is complicated and inherent with many types of component faults, is essential to avoid the interruption of electricity supply. However, the GTGS diagnosis faces challenges in terms of the existence of simultaneous-fault diagnosis and high cost in acquiring the exponentially increased simultaneous-fault vibration signals for constructing the diagnostic system. This research proposes a new diagnostic framework combining feature extraction, pairwise-coupled probabilistic classifier, and decision threshold optimization. The feature extraction module adopts wavelet packet transform and time-domain statistical features to extract vibration signal features. Kernel principal component analysis is then applied to further reduce the redundant features. The features of single faults in a simultaneous-fault pattern are extracted and then detected using a probabilistic classifier, namely, pairwise-coupled relevance vector machine, which is trained with single-fault patterns only. Therefore, the training dataset of simultaneous-fault patterns is unnecessary. To optimize the decision threshold, this research proposes to use grid search method which can ensure a global solution as compared with traditional computational intelligence techniques. Experimental results show that the proposed framework performs well for both single-fault and simultaneous-fault diagnosis and is superior to the frameworks without feature extraction and pairwise coupling.

Algorithms for adaptive nonlinear pattern recognition

Science.gov (United States)

Schmalz, Mark S.; Ritter, Gerhard X.; Hayden, Eric; Key, Gary

2011-09-01

In Bayesian pattern recognition research, static classifiers have featured prominently in the literature. A static classifier is essentially based on a static model of input statistics, thereby assuming input ergodicity that is not realistic in practice. Classical Bayesian approaches attempt to circumvent the limitations of static classifiers, which can include brittleness and narrow coverage, by training extensively on a data set that is assumed to cover more than the subtense of expected input. Such assumptions are not realistic for more complex pattern classification tasks, for example, object detection using pattern classification applied to the output of computer vision filters. In contrast, we have developed a two step process, that can render the majority of static classifiers adaptive, such that the tracking of input nonergodicities is supported. Firstly, we developed operations that dynamically insert (or resp. delete) training patterns into (resp. from) the classifier's pattern database, without requiring that the classifier's internal representation of its training database be completely recomputed. Secondly, we developed and applied a pattern replacement algorithm that uses the aforementioned pattern insertion/deletion operations. This algorithm is designed to optimize the pattern database for a given set of performance measures, thereby supporting closed-loop, performance-directed optimization. This paper presents theory and algorithmic approaches for the efficient computation of adaptive linear and nonlinear pattern recognition operators that use our pattern insertion/deletion technology - in particular, tabular nearest-neighbor encoding (TNE) and lattice associative memories (LAMs). Of particular interest is the classification of nonergodic datastreams that have noise corruption with time-varying statistics. The TNE and LAM based classifiers discussed herein have been successfully applied to the computation of object classification in hyperspectral

Learning to classify wakes from local sensory information

Science.gov (United States)

Alsalman, Mohamad; Colvert, Brendan; Kanso, Eva; Kanso Team

2017-11-01

Aquatic organisms exhibit remarkable abilities to sense local flow signals contained in their fluid environment and to surmise the origins of these flows. For example, fish can discern the information contained in various flow structures and utilize this information for obstacle avoidance and prey tracking. Flow structures created by flapping and swimming bodies are well characterized in the fluid dynamics literature; however, such characterization relies on classical methods that use an external observer to reconstruct global flow fields. The reconstructed flows, or wakes, are then classified according to the unsteady vortex patterns. Here, we propose a new approach for wake identification: we classify the wakes resulting from a flapping airfoil by applying machine learning algorithms to local flow information. In particular, we simulate the wakes of an oscillating airfoil in an incoming flow, extract the downstream vorticity information, and train a classifier to learn the different flow structures and classify new ones. This data-driven approach provides a promising framework for underwater navigation and detection in application to autonomous bio-inspired vehicles.

Analysis of unintended events in hospitals: inter-rater reliability of constructing causal trees and classifying root causes

NARCIS (Netherlands)

Smits, M.; Janssen, J.; Vet, de H.C.W.; Zwaan, L.; Timmermans, D.R.M.; Groenewegen, P.P.; Wagner, C.

2009-01-01

BACKGROUND: Root cause analysis is a method to examine causes of unintended events. PRISMA (Prevention and Recovery Information System for Monitoring and Analysis: is a root cause analysis tool. With PRISMA, events are described in causal trees and root causes are subsequently classified with the

Analysis of unintended events in hospitals : inter-rater reliability of constructing causal trees and classifying root causes

NARCIS (Netherlands)

Smits, M.; Janssen, J.; Vet, R. de; Zwaan, L.; Groenewegen, P.P.; Timmermans, D.

2009-01-01

Background. Root cause analysis is a method to examine causes of unintended events. PRISMA (Prevention and Recovery Information System for Monitoring and Analysis) is a root cause analysis tool. With PRISMA, events are described in causal trees and root causes are subsequently classified with the

Analysis of unintended events in hospitals: inter-rater reliability of constructing causal trees and classifying root causes.

NARCIS (Netherlands)

Smits, M.; Janssen, J.; Vet, R. de; Zwaan, L.; Timmermans, D.; Groenewegen, P.; Wagner, C.

2009-01-01

Background: Root cause analysis is a method to examine causes of unintended events. PRISMA (Prevention and Recovery Information System for Monitoring and Analysis) is a root cause analysis tool. With PRISMA, events are described in causal trees and root causes are subsequently classified with the

Finger crease pattern recognition using Legendre moments and principal component analysis

Science.gov (United States)

Luo, Rongfang; Lin, Tusheng

2007-03-01

The finger joint lines defined as finger creases and its distribution can identify a person. In this paper, we propose a new finger crease pattern recognition method based on Legendre moments and principal component analysis (PCA). After obtaining the region of interest (ROI) for each finger image in the pre-processing stage, Legendre moments under Radon transform are applied to construct a moment feature matrix from the ROI, which greatly decreases the dimensionality of ROI and can represent principal components of the finger creases quite well. Then, an approach to finger crease pattern recognition is designed based on Karhunen-Loeve (K-L) transform. The method applies PCA to a moment feature matrix rather than the original image matrix to achieve the feature vector. The proposed method has been tested on a database of 824 images from 103 individuals using the nearest neighbor classifier. The accuracy up to 98.584% has been obtained when using 4 samples per class for training. The experimental results demonstrate that our proposed approach is feasible and effective in biometrics.

Knee Joint Vibration Signal Analysis with Matching Pursuit Decomposition and Dynamic Weighted Classifier Fusion

Directory of Open Access Journals (Sweden)

Suxian Cai

2013-01-01

detected with the fixed threshold in the time domain. To perform a better classification over the data set of 89 VAG signals, we applied a novel classifier fusion system based on the dynamic weighted fusion (DWF method to ameliorate the classification performance. For comparison, a single leastsquares support vector machine (LS-SVM and the Bagging ensemble were used for the classification task as well. The results in terms of overall accuracy in percentage and area under the receiver operating characteristic curve obtained with the DWF-based classifier fusion method reached 88.76% and 0.9515, respectively, which demonstrated the effectiveness and superiority of the DWF method with two distinct features for the VAG signal analysis.

Hard-Rock Stability Analysis for Span Design in Entry-Type Excavations with Learning Classifiers

Directory of Open Access Journals (Sweden)

Esperanza García-Gonzalo

2016-06-01

Full Text Available The mining industry relies heavily on empirical analysis for design and prediction. An empirical design method, called the critical span graph, was developed specifically for rock stability analysis in entry-type excavations, based on an extensive case-history database of cut and fill mining in Canada. This empirical span design chart plots the critical span against rock mass rating for the observed case histories and has been accepted by many mining operations for the initial span design of cut and fill stopes. Different types of analysis have been used to classify the observed cases into stable, potentially unstable and unstable groups. The main purpose of this paper is to present a new method for defining rock stability areas of the critical span graph, which applies machine learning classifiers (support vector machine and extreme learning machine. The results show a reasonable correlation with previous guidelines. These machine learning methods are good tools for developing empirical methods, since they make no assumptions about the regression function. With this software, it is easy to add new field observations to a previous database, improving prediction output with the addition of data that consider the local conditions for each mine.

Hard-Rock Stability Analysis for Span Design in Entry-Type Excavations with Learning Classifiers.

Science.gov (United States)

García-Gonzalo, Esperanza; Fernández-Muñiz, Zulima; García Nieto, Paulino José; Bernardo Sánchez, Antonio; Menéndez Fernández, Marta

2016-06-29

The mining industry relies heavily on empirical analysis for design and prediction. An empirical design method, called the critical span graph, was developed specifically for rock stability analysis in entry-type excavations, based on an extensive case-history database of cut and fill mining in Canada. This empirical span design chart plots the critical span against rock mass rating for the observed case histories and has been accepted by many mining operations for the initial span design of cut and fill stopes. Different types of analysis have been used to classify the observed cases into stable, potentially unstable and unstable groups. The main purpose of this paper is to present a new method for defining rock stability areas of the critical span graph, which applies machine learning classifiers (support vector machine and extreme learning machine). The results show a reasonable correlation with previous guidelines. These machine learning methods are good tools for developing empirical methods, since they make no assumptions about the regression function. With this software, it is easy to add new field observations to a previous database, improving prediction output with the addition of data that consider the local conditions for each mine.

Local-global classifier fusion for screening chest radiographs

Science.gov (United States)

Ding, Meng; Antani, Sameer; Jaeger, Stefan; Xue, Zhiyun; Candemir, Sema; Kohli, Marc; Thoma, George

2017-03-01

Tuberculosis (TB) is a severe comorbidity of HIV and chest x-ray (CXR) analysis is a necessary step in screening for the infective disease. Automatic analysis of digital CXR images for detecting pulmonary abnormalities is critical for population screening, especially in medical resource constrained developing regions. In this article, we describe steps that improve previously reported performance of NLM's CXR screening algorithms and help advance the state of the art in the field. We propose a local-global classifier fusion method where two complementary classification systems are combined. The local classifier focuses on subtle and partial presentation of the disease leveraging information in radiology reports that roughly indicates locations of the abnormalities. In addition, the global classifier models the dominant spatial structure in the gestalt image using GIST descriptor for the semantic differentiation. Finally, the two complementary classifiers are combined using linear fusion, where the weight of each decision is calculated by the confidence probabilities from the two classifiers. We evaluated our method on three datasets in terms of the area under the Receiver Operating Characteristic (ROC) curve, sensitivity, specificity and accuracy. The evaluation demonstrates the superiority of our proposed local-global fusion method over any single classifier.

Classifying regularized sensor covariance matrices: An alternative to CSP

NARCIS (Netherlands)

Roijendijk, L.M.M.; Gielen, C.C.A.M.; Farquhar, J.D.R.

2016-01-01

Common spatial patterns ( CSP) is a commonly used technique for classifying imagined movement type brain-computer interface ( BCI) datasets. It has been very successful with many extensions and improvements on the basic technique. However, a drawback of CSP is that the signal processing pipeline

Classifying regularised sensor covariance matrices: An alternative to CSP

NARCIS (Netherlands)

Roijendijk, L.M.M.; Gielen, C.C.A.M.; Farquhar, J.D.R.

2016-01-01

Common spatial patterns (CSP) is a commonly used technique for classifying imagined movement type brain computer interface (BCI) datasets. It has been very successful with many extensions and improvements on the basic technique. However, a drawback of CSP is that the signal processing pipeline

The decision tree classifier - Design and potential. [for Landsat-1 data

Science.gov (United States)

Hauska, H.; Swain, P. H.

1975-01-01

A new classifier has been developed for the computerized analysis of remote sensor data. The decision tree classifier is essentially a maximum likelihood classifier using multistage decision logic. It is characterized by the fact that an unknown sample can be classified into a class using one or several decision functions in a successive manner. The classifier is applied to the analysis of data sensed by Landsat-1 over Kenosha Pass, Colorado. The classifier is illustrated by a tree diagram which for processing purposes is encoded as a string of symbols such that there is a unique one-to-one relationship between string and decision tree.

Analysis of Insulating Material of XLPE Cables considering Innovative Patterns of Partial Discharges

Directory of Open Access Journals (Sweden)

Fernando Figueroa Godoy

2017-01-01

Full Text Available This paper aims to analyze the quality of insulation in high voltage underground cables XLPE using a prototype which classifies the following usual types of patterns of partial discharge (PD: (1 internal PD, (2 superficial PD, (3 corona discharge in air, and (4 corona discharge in oil, in addition to considering two new PD patterns: (1 false contact and (2 floating ground. The tests and measurements to obtain the patterns and study cases of partial discharges were performed at the Testing Laboratory Equipment and Materials (LEPEM of the Federal Electricity Commission of Mexico (CFE using a measuring equipment LDIC and norm IEC60270. To classify the six patterns of partial discharges mentioned above a Probabilistic Neural Network Bayesian Modified (PNNBM method having the feature of using a large amount of data will be used and it is not saturated. In addition, PNN converges, always finding a solution in a short period of time with low computational cost. The insulation of two high voltage cables with different characteristics was analyzed. The test results allow us to conclude which wire has better insulation.

A systematic comparison of supervised classifiers.

Directory of Open Access Journals (Sweden)

Diego Raphael Amancio

Full Text Available Pattern recognition has been employed in a myriad of industrial, commercial and academic applications. Many techniques have been devised to tackle such a diversity of applications. Despite the long tradition of pattern recognition research, there is no technique that yields the best classification in all scenarios. Therefore, as many techniques as possible should be considered in high accuracy applications. Typical related works either focus on the performance of a given algorithm or compare various classification methods. In many occasions, however, researchers who are not experts in the field of machine learning have to deal with practical classification tasks without an in-depth knowledge about the underlying parameters. Actually, the adequate choice of classifiers and parameters in such practical circumstances constitutes a long-standing problem and is one of the subjects of the current paper. We carried out a performance study of nine well-known classifiers implemented in the Weka framework and compared the influence of the parameter configurations on the accuracy. The default configuration of parameters in Weka was found to provide near optimal performance for most cases, not including methods such as the support vector machine (SVM. In addition, the k-nearest neighbor method frequently allowed the best accuracy. In certain conditions, it was possible to improve the quality of SVM by more than 20% with respect to their default parameter configuration.

Hidden pattern discovery on epileptic EEG with 1-D local binary patterns and epileptic seizures detection by grey relational analysis.

Science.gov (United States)

Kaya, Yılmaz

2015-09-01

This paper proposes a novel approach to detect epilepsy seizures by using Electroencephalography (EEG), which is one of the most common methods for the diagnosis of epilepsy, based on 1-Dimension Local Binary Pattern (1D-LBP) and grey relational analysis (GRA) methods. The main aim of this paper is to evaluate and validate a novel approach, which is a computer-based quantitative EEG analyzing method and based on grey systems, aimed to help decision-maker. In this study, 1D-LBP, which utilizes all data points, was employed for extracting features in raw EEG signals, Fisher score (FS) was employed to select the representative features, which can also be determined as hidden patterns. Additionally, GRA is performed to classify EEG signals through these Fisher scored features. The experimental results of the proposed approach, which was employed in a public dataset for validation, showed that it has a high accuracy in identifying epileptic EEG signals. For various combinations of epileptic EEG, such as A-E, B-E, C-E, D-E, and A-D clusters, 100, 96, 100, 99.00 and 100% were achieved, respectively. Also, this work presents an attempt to develop a new general-purpose hidden pattern determination scheme, which can be utilized for different categories of time-varying signals.

Visual and Quantitative Analysis Methods of Respiratory Patterns for Respiratory Gated PET/CT.

Science.gov (United States)

Son, Hye Joo; Jeong, Young Jin; Yoon, Hyun Jin; Park, Jong-Hwan; Kang, Do-Young

2016-01-01

We integrated visual and quantitative methods for analyzing the stability of respiration using four methods: phase space diagrams, Fourier spectra, Poincaré maps, and Lyapunov exponents. Respiratory patterns of 139 patients were grouped based on the combination of the regularity of amplitude, period, and baseline positions. Visual grading was done by inspecting the shape of diagram and classified into two states: regular and irregular. Quantitation was done by measuring standard deviation of x and v coordinates of Poincaré map (SD x , SD v ) or the height of the fundamental peak ( A 1 ) in Fourier spectrum or calculating the difference between maximal upward and downward drift. Each group showed characteristic pattern on visual analysis. There was difference of quantitative parameters (SD x , SD v , A 1 , and MUD-MDD) among four groups (one way ANOVA, p = 0.0001 for MUD-MDD, SD x , and SD v , p = 0.0002 for A 1 ). In ROC analysis, the cutoff values were 0.11 for SD x (AUC: 0.982, p quantitative indices of respiratory stability and determining quantitative cutoff value for differentiating regular and irregular respiration.

Automatic classification of canine PRG neuronal discharge patterns using K-means clustering.

Science.gov (United States)

Zuperku, Edward J; Prkic, Ivana; Stucke, Astrid G; Miller, Justin R; Hopp, Francis A; Stuth, Eckehard A

2015-02-01

Respiratory-related neurons in the parabrachial-Kölliker-Fuse (PB-KF) region of the pons play a key role in the control of breathing. The neuronal activities of these pontine respiratory group (PRG) neurons exhibit a variety of inspiratory (I), expiratory (E), phase spanning and non-respiratory related (NRM) discharge patterns. Due to the variety of patterns, it can be difficult to classify them into distinct subgroups according to their discharge contours. This report presents a method that automatically classifies neurons according to their discharge patterns and derives an average subgroup contour of each class. It is based on the K-means clustering technique and it is implemented via SigmaPlot User-Defined transform scripts. The discharge patterns of 135 canine PRG neurons were classified into seven distinct subgroups. Additional methods for choosing the optimal number of clusters are described. Analysis of the results suggests that the K-means clustering method offers a robust objective means of both automatically categorizing neuron patterns and establishing the underlying archetypical contours of subtypes based on the discharge patterns of group of neurons. Published by Elsevier B.V.

Pattern analysis of planning and management at the radiographic dept. in hospital

International Nuclear Information System (INIS)

Yanagisawa, Makoto; Taniguchi, Gen; Imai, Shoji.

1979-01-01

This papers attempt to make the planning method, and the relationships between planning and management by the circulation studies. We investigated the circulation of radiographic departments in 3 hospitals, the managements of 20 hospitals, and the planning layouts of 63 hospitals. Now we made 9 typical diagrammatic layouts to classify many plans and some patterns to classify many management types. In this process we used some items to classify as follows. (1) Staffs' works; there are diagnosis, photographing, nursing, developing, assistant or management works, and so on. (2) Management manners; there are three types, such as only photographing facility type, photographing and nursing facility type, and diagnosis facility type. (3) Classify how to developing and how to do assistant or management works. (4) Planning types; table-6 1) Patients' spaces are separate or not. 2) Photographing staffs' corners are independent or not. 3) Developing spaces are centralized or not. 4) Are there or not, the connections between patients' zones and staffs'. (author)

Scoring and Classifying Examinees Using Measurement Decision Theory

Directory of Open Access Journals (Sweden)

Lawrence M. Rudner

2009-04-01

Full Text Available This paper describes and evaluates the use of measurement decision theory (MDT to classify examinees based on their item response patterns. The model has a simple framework that starts with the conditional probabilities of examinees in each category or mastery state responding correctly to each item. The presented evaluation investigates: (1 the classification accuracy of tests scored using decision theory; (2 the effectiveness of different sequential testing procedures; and (3 the number of items needed to make a classification. A large percentage of examinees can be classified accurately with very few items using decision theory. A Java Applet for self instruction and software for generating, calibrating and scoring MDT data are provided.

Cross-View Neuroimage Pattern Analysis for Alzheimer's Disease Staging

Directory of Open Access Journals (Sweden)

Sidong eLiu

2016-02-01

Full Text Available The research on staging of pre-symptomatic and prodromal phase of neurological disorders, e.g., Alzheimer's disease (AD, is essential for prevention of dementia. New strategies for AD staging with a focus on early detection, are demanded to optimize potential efficacy of disease-modifying therapies that can halt or slow the disease progression. Recently, neuroimaging are increasingly used as additional research-based markers to detect AD onset and predict conversion of MCI and normal control (NC to AD. Researchers have proposed a variety of neuroimaging biomarkers to characterize the patterns of the pathology of AD and MCI, and suggested that multi-view neuroimaging biomarkers could lead to better performance than single-view biomarkers in AD staging. However, it is still unclear what leads to such synergy and how to preserve or maximize. In an attempt to answer these questions, we proposed a cross-view pattern analysis framework for investigating the synergy between different neuroimaging biomarkers. We quantitatively analyzed 9 types of biomarkers derived from FDG-PET and T1-MRI, and evaluated their performance in a task of classifying AD, MCI and NC subjects obtained from the ADNI baseline cohort. The experiment results showed that these biomarkers could depict the pathology of AD from different perspectives, and output distinct patterns that are significantly associated with the disease progression. Most importantly, we found that these features could be separated into clusters, each depicting a particular aspect; and the inter-cluster features could always achieve better performance than the intra-cluster features in AD staging.

Pattern recognition methods for acoustic emission analysis

International Nuclear Information System (INIS)

Doctor, P.G.; Harrington, T.P.; Hutton, P.H.

1979-07-01

Models have been developed that relate the rate of acoustic emissions to structural integrity. The implementation of these techniques in the field has been hindered by the noisy environment in which the data must be taken. Acoustic emissions from noncritical sources are recorded in addition to those produced by critical sources, such as flaws. A technique is discussed for prescreening acoustic events and filtering out those that are produced by noncritical sources. The methodology that was investigated is pattern recognition. Three different pattern recognition techniques were applied to a data set that consisted of acoustic emissions caused by crack growth and acoustic signals caused by extraneous noise sources. Examination of the acoustic emission data presented has uncovered several features of the data that can provide a reasonable filter. Two of the most valuable features are the frequency of maximum response and the autocorrelation coefficient at Lag 13. When these two features and several others were combined with a least squares decision algorithm, 90% of the acoustic emissions in the data set were correctly classified. It appears possible to design filters that eliminate extraneous noise sources from flaw-growth acoustic emissions using pattern recognition techniques

Authentication and distinction of Shenmai injection with HPLC fingerprint analysis assisted by pattern recognition techniques

Directory of Open Access Journals (Sweden)

Xue-Feng Lu

2012-10-01

Full Text Available In this paper, the feasibility and advantages of employing high performance liquid chromatographic (HPLC fingerprints combined with pattern recognition techniques for quality control of Shenmai injection were investigated and demonstrated. The Similarity Evaluation System was employed to evaluate the similarities of samples of Shenmai injection, and the HPLC generated chromatographic data were analyzed using hierarchical clustering analysis (HCA and soft independent modeling of class analogy (SIMCA. Consistent results were obtained to show that the authentic samples and the blended samples were successfully classified by SIMCA, which could be applied to accurate discrimination and quality control of Shenmai injection. Furthermore, samples could also be grouped in accordance with manufacturers. Our results revealed that the developed method has potential perspective for the original discrimination and quality control of Shenmai injection. Keywords: Shenmai injection, High performance liquid chromatography, Fingerprint, Pattern recognition

Classifying Microorganisms

DEFF Research Database (Denmark)

Sommerlund, Julie

2006-01-01

This paper describes the coexistence of two systems for classifying organisms and species: a dominant genetic system and an older naturalist system. The former classifies species and traces their evolution on the basis of genetic characteristics, while the latter employs physiological characteris......This paper describes the coexistence of two systems for classifying organisms and species: a dominant genetic system and an older naturalist system. The former classifies species and traces their evolution on the basis of genetic characteristics, while the latter employs physiological...... characteristics. The coexistence of the classification systems does not lead to a conflict between them. Rather, the systems seem to co-exist in different configurations, through which they are complementary, contradictory and inclusive in different situations-sometimes simultaneously. The systems come...

High dimensional classifiers in the imbalanced case

DEFF Research Database (Denmark)

Bak, Britta Anker; Jensen, Jens Ledet

We consider the binary classification problem in the imbalanced case where the number of samples from the two groups differ. The classification problem is considered in the high dimensional case where the number of variables is much larger than the number of samples, and where the imbalance leads...... to a bias in the classification. A theoretical analysis of the independence classifier reveals the origin of the bias and based on this we suggest two new classifiers that can handle any imbalance ratio. The analytical results are supplemented by a simulation study, where the suggested classifiers in some...

Classification of natural circulation two-phase flow patterns using fuzzy inference on image analysis

International Nuclear Information System (INIS)

Mesquita, R.N. de; Masotti, P.H.F.; Penha, R.M.L.; Andrade, D.A.; Sabundjian, G.; Torres, W.M.

2012-01-01

Highlights: ► A fuzzy classification system for two-phase flow instability patterns is developed. ► Flow patterns are classified based on images of natural circulation experiments. ► Fuzzy inference is optimized to use single grayscale profiles as input. - Abstract: Two-phase flow on natural circulation phenomenon has been an important theme on recent studies related to nuclear reactor designs. The accuracy of heat transfer estimation has been improved with new models that require precise prediction of pattern transitions of flow. In this work, visualization of natural circulation cycles is used to study two-phase flow patterns associated with phase transients and static instabilities of flow. A Fuzzy Flow-type Classification System (FFCS) was developed to classify these patterns based only on image extracted features. Image acquisition and temperature measurements were simultaneously done. Experiments in natural circulation facility were adjusted to generate a series of characteristic two-phase flow instability periodic cycles. The facility is composed of a loop of glass tubes, a heat source using electrical heaters, a cold source using a helicoidal heat exchanger, a visualization section and thermocouples positioned over different loop sections. The instability cyclic period is estimated based on temperature measurements associated with the detection of a flow transition image pattern. FFCS shows good results provided that adequate image acquisition parameters and pre-processing adjustments are used.

Cellular-automata-based learning network for pattern recognition

Science.gov (United States)

Tzionas, Panagiotis G.; Tsalides, Phillippos G.; Thanailakis, Adonios

1991-11-01

Most classification techniques either adopt an approach based directly on the statistical characteristics of the pattern classes involved, or they transform the patterns in a feature space and try to separate the point clusters in this space. An alternative approach based on memory networks has been presented, its novelty being that it can be implemented in parallel and it utilizes direct features of the patterns rather than statistical characteristics. This study presents a new approach for pattern classification using pseudo 2-D binary cellular automata (CA). This approach resembles the memory network classifier in the sense that it is based on an adaptive knowledge based formed during a training phase, and also in the fact that both methods utilize pattern features that are directly available. The main advantage of this approach is that the sensitivity of the pattern classifier can be controlled. The proposed pattern classifier has been designed using 1.5 micrometers design rules for an N-well CMOS process. Layout has been achieved using SOLO 1400. Binary pseudo 2-D hybrid additive CA (HACA) is described in the second section of this paper. The third section describes the operation of the pattern classifier and the fourth section presents some possible applications. The VLSI implementation of the pattern classifier is presented in the fifth section and, finally, the sixth section draws conclusions from the results obtained.

Neural Network Classifiers for Local Wind Prediction.

Science.gov (United States)

Kretzschmar, Ralf; Eckert, Pierre; Cattani, Daniel; Eggimann, Fritz

2004-05-01

This paper evaluates the quality of neural network classifiers for wind speed and wind gust prediction with prediction lead times between +1 and +24 h. The predictions were realized based on local time series and model data. The selection of appropriate input features was initiated by time series analysis and completed by empirical comparison of neural network classifiers trained on several choices of input features. The selected input features involved day time, yearday, features from a single wind observation device at the site of interest, and features derived from model data. The quality of the resulting classifiers was benchmarked against persistence for two different sites in Switzerland. The neural network classifiers exhibited superior quality when compared with persistence judged on a specific performance measure, hit and false-alarm rates.

Different Patterns of the Urban Heat Island Intensity from Cluster Analysis

Science.gov (United States)

Silva, F. B.; Longo, K.

2014-12-01

This study analyzes the different variability patterns of the Urban Heat Island intensity (UHII) in the Metropolitan Area of Rio de Janeiro (MARJ), one of the largest urban agglomerations in Brazil. The UHII is defined as the difference in the surface air temperature between the urban/suburban and rural/vegetated areas. To choose one or more stations that represent those areas we used the technique of cluster analysis on the air temperature observations from 14 surface weather stations in the MARJ. The cluster analysis aims to classify objects based on their characteristics, gathering similar groups. The results show homogeneity patterns between air temperature observations, with 6 homogeneous groups being defined. Among those groups, one might be a natural choice for the representative urban area (Central station); one corresponds to suburban area (Afonsos station); and another group referred as rural area is compound of three stations (Ecologia, Santa Cruz and Xerém) that are located in vegetated regions. The arithmetic mean of temperature from the three rural stations is taken to represent the rural station temperature. The UHII is determined from these homogeneous groups. The first UHII is estimated from urban and rural temperature areas (Case 1), whilst the second UHII is obtained from suburban and rural temperature areas (Case 2). In Case 1, the maximum UHII occurs in two periods, one in the early morning and the other at night, while the minimum UHII occurs in the afternoon. In Case 2, the maximum UHII is observed during afternoon/night and the minimum during dawn/early morning. This study demonstrates that the stations choice reflects different UHII patterns, evidencing that distinct behaviors of this phenomenon can be identified.

Classifying cognitive profiles using machine learning with privileged information in Mild Cognitive Impairment

Directory of Open Access Journals (Sweden)

Hanin Hamdan Alahmadi

2016-11-01

Full Text Available Early diagnosis of dementia is critical for assessing disease progression and potential treatment. State-or-the-art machine learning techniques have been increasingly employed to take on this diagnostic task. In this study, we employed Generalised Matrix Learning Vector Quantization (GMLVQ classifiers to discriminate patients with Mild Cognitive Impairment (MCI from healthy controls based on their cognitive skills. Further, we adopted a ``Learning with privileged information'' approach to combine cognitive and fMRI data for the classification task. The resulting classifier operates solely on the cognitive data while it incorporates the fMRI data as privileged information (PI during training. This novel classifier is of practical use as the collection of brain imaging data is not always possible with patients and older participants.MCI patients and healthy age-matched controls were trained to extract structure from temporal sequences. We ask whether machine learning classifiers can be used to discriminate patients from controls based on the learning performance and whether differences between these groups relate to individual cognitive profiles. To this end, we tested participants in four cognitive tasks: working memory, cognitive inhibition, divided attention, and selective attention. We also collected fMRI data before and after training on the learning task and extracted fMRI responses and connectivity as features for machine learning classifiers. Our results show that the PI guided GMLVQ classifiers outperform the baseline classifier that only used the cognitive data. In addition, we found that for the baseline classifier, divided attention is the only relevant cognitive feature. When PI was incorporated, divided attention remained the most relevant feature while cognitive inhibition became also relevant for the task. Interestingly, this analysis for the fMRI GMLVQ classifier suggests that (1 when overall fMRI signal for structured stimuli is

A DNA-based pattern classifier with in vitro learning and associative recall for genomic characterization and biosensing without explicit sequence knowledge.

Science.gov (United States)

Lee, Ju Seok; Chen, Junghuei; Deaton, Russell; Kim, Jin-Woo

2014-01-01

Genetic material extracted from in situ microbial communities has high promise as an indicator of biological system status. However, the challenge is to access genomic information from all organisms at the population or community scale to monitor the biosystem's state. Hence, there is a need for a better diagnostic tool that provides a holistic view of a biosystem's genomic status. Here, we introduce an in vitro methodology for genomic pattern classification of biological samples that taps large amounts of genetic information from all genes present and uses that information to detect changes in genomic patterns and classify them. We developed a biosensing protocol, termed Biological Memory, that has in vitro computational capabilities to "learn" and "store" genomic sequence information directly from genomic samples without knowledge of their explicit sequences, and that discovers differences in vitro between previously unknown inputs and learned memory molecules. The Memory protocol was designed and optimized based upon (1) common in vitro recombinant DNA operations using 20-base random probes, including polymerization, nuclease digestion, and magnetic bead separation, to capture a snapshot of the genomic state of a biological sample as a DNA memory and (2) the thermal stability of DNA duplexes between new input and the memory to detect similarities and differences. For efficient read out, a microarray was used as an output method. When the microarray-based Memory protocol was implemented to test its capability and sensitivity using genomic DNA from two model bacterial strains, i.e., Escherichia coli K12 and Bacillus subtilis, results indicate that the Memory protocol can "learn" input DNA, "recall" similar DNA, differentiate between dissimilar DNA, and detect relatively small concentration differences in samples. This study demonstrated not only the in vitro information processing capabilities of DNA, but also its promise as a genomic pattern classifier that could

Adaptation in P300 braincomputer interfaces: A two-classifier cotraining approach

DEFF Research Database (Denmark)

Panicker, Rajesh C.; Sun, Ying; Puthusserypady, Sadasivan

2010-01-01

A cotraining-based approach is introduced for constructing high-performance classifiers for P300-based braincomputer interfaces (BCIs), which were trained from very little data. It uses two classifiers: Fishers linear discriminant analysis and Bayesian linear discriminant analysis progressively...

Gene-expression patterns in peripheral blood classify familial breast cancer susceptibility.

Science.gov (United States)

Piccolo, Stephen R; Andrulis, Irene L; Cohen, Adam L; Conner, Thomas; Moos, Philip J; Spira, Avrum E; Buys, Saundra S; Johnson, W Evan; Bild, Andrea H

2015-11-04

Women with a family history of breast cancer face considerable uncertainty about whether to pursue standard screening, intensive screening, or prophylactic surgery. Accurate and individualized risk-estimation approaches may help these women make more informed decisions. Although highly penetrant genetic variants have been associated with familial breast cancer (FBC) risk, many individuals do not carry these variants, and many carriers never develop breast cancer. Common risk variants have a relatively modest effect on risk and show limited potential for predicting FBC development. As an alternative, we hypothesized that additional genomic data types, such as gene-expression levels, which can reflect genetic and epigenetic variation, could contribute to classifying a person's risk status. Specifically, we aimed to identify common patterns in gene-expression levels across individuals who develop FBC. We profiled peripheral blood mononuclear cells from women with a family history of breast cancer (with or without a germline BRCA1/2 variant) and from controls. We used the support vector machines algorithm to differentiate between patients who developed FBC and those who did not. Our study used two independent datasets, a training set of 124 women from Utah (USA) and an external validation (test) set from Ontario (Canada) of 73 women (197 total). We controlled for expression variation associated with clinical, demographic, and treatment variables as well as lymphocyte markers. Our multigene biomarker provided accurate, individual-level estimates of FBC occurrence for the Utah cohort (AUC = 0.76 [0.67-84]) . Even at their lower confidence bounds, these accuracy estimates meet or exceed estimates from alternative approaches. Our Ontario cohort resulted in similarly high levels of accuracy (AUC = 0.73 [0.59-0.86]), thus providing external validation of our findings. Individuals deemed to have "high" risk by our model would have an estimated 2.4 times greater odds of

Patterns of functional vision loss in glaucoma determined with archetypal analysis

Science.gov (United States)

Elze, Tobias; Pasquale, Louis R.; Shen, Lucy Q.; Chen, Teresa C.; Wiggs, Janey L.; Bex, Peter J.

2015-01-01

Glaucoma is an optic neuropathy accompanied by vision loss which can be mapped by visual field (VF) testing revealing characteristic patterns related to the retinal nerve fibre layer anatomy. While detailed knowledge about these patterns is important to understand the anatomic and genetic aspects of glaucoma, current classification schemes are typically predominantly derived qualitatively. Here, we classify glaucomatous vision loss quantitatively by statistically learning prototypical patterns on the convex hull of the data space. In contrast to component-based approaches, this method emphasizes distinct aspects of the data and provides patterns that are easier to interpret for clinicians. Based on 13 231 reliable Humphrey VFs from a large clinical glaucoma practice, we identify an optimal solution with 17 glaucomatous vision loss prototypes which fit well with previously described qualitative patterns from a large clinical study. We illustrate relations of our patterns to retinal structure by a previously developed mathematical model. In contrast to the qualitative clinical approaches, our results can serve as a framework to quantify the various subtypes of glaucomatous visual field loss. PMID:25505132

Face-selective regions differ in their ability to classify facial expressions.

Science.gov (United States)

Zhang, Hui; Japee, Shruti; Nolan, Rachel; Chu, Carlton; Liu, Ning; Ungerleider, Leslie G

2016-04-15

Recognition of facial expressions is crucial for effective social interactions. Yet, the extent to which the various face-selective regions in the human brain classify different facial expressions remains unclear. We used functional magnetic resonance imaging (fMRI) and support vector machine pattern classification analysis to determine how well face-selective brain regions are able to decode different categories of facial expression. Subjects participated in a slow event-related fMRI experiment in which they were shown 32 face pictures, portraying four different expressions: neutral, fearful, angry, and happy and belonging to eight different identities. Our results showed that only the amygdala and the posterior superior temporal sulcus (STS) were able to accurately discriminate between these expressions, albeit in different ways: the amygdala discriminated fearful faces from non-fearful faces, whereas STS discriminated neutral from emotional (fearful, angry and happy) faces. In contrast to these findings on the classification of emotional expression, only the fusiform face area (FFA) and anterior inferior temporal cortex (aIT) could discriminate among the various facial identities. Further, the amygdala and STS were better than FFA and aIT at classifying expression, while FFA and aIT were better than the amygdala and STS at classifying identity. Taken together, our findings indicate that the decoding of facial emotion and facial identity occurs in different neural substrates: the amygdala and STS for the former and FFA and aIT for the latter. Published by Elsevier Inc.

Mapping spatial patterns with morphological image processing

Science.gov (United States)

Peter Vogt; Kurt H. Riitters; Christine Estreguil; Jacek Kozak; Timothy G. Wade; James D. Wickham

2006-01-01

We use morphological image processing for classifying spatial patterns at the pixel level on binary land-cover maps. Land-cover pattern is classified as 'perforated,' 'edge,' 'patch,' and 'core' with higher spatial precision and thematic accuracy compared to a previous approach based on image convolution, while retaining the...

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.

Role of Dietary Pattern Analysis in Determining Cognitive Status in Elderly Australian Adults

Directory of Open Access Journals (Sweden)

Kimberly Ashby-Mitchell

2015-02-01

Full Text Available Principal Component Analysis (PCA was used to determine the association between dietary patterns and cognitive function and to examine how classification systems based on food groups and food items affect levels of association between diet and cognitive function. The present study focuses on the older segment of the Australian Diabetes, Obesity and Lifestyle Study (AusDiab sample (age 60+ that completed the food frequency questionnaire at Wave 1 (1999/2000 and the mini-mental state examination and tests of memory, verbal ability and processing speed at Wave 3 (2012. Three methods were used in order to classify these foods before applying PCA. In the first instance, the 101 individual food items asked about in the questionnaire were used (no categorisation. In the second and third instances, foods were combined and reduced to 32 and 20 food groups, respectively, based on nutrient content and culinary usage—a method employed in several other published studies for PCA. Logistic regression analysis and generalized linear modelling was used to analyse the relationship between PCA-derived dietary patterns and cognitive outcome. Broader food group classifications resulted in a greater proportion of food use variance in the sample being explained (use of 101 individual foods explained 23.22% of total food use, while use of 32 and 20 food groups explained 29.74% and 30.74% of total variance in food use in the sample, respectively. Three dietary patterns were found to be associated with decreased odds of cognitive impairment (CI. Dietary patterns derived from 101 individual food items showed that for every one unit increase in ((Fruit and Vegetable Pattern: p = 0.030, OR 1.061, confidence interval: 1.006–1.118; (Fish, Legumes and Vegetable Pattern: p = 0.040, OR 1.032, confidence interval: 1.001–1.064; (Dairy, Cereal and Eggs Pattern: p = 0.003, OR 1.020, confidence interval: 1.007–1.033, the odds of cognitive impairment decreased. Different

Neural Dissociation in the Production of Lexical versus Classifier Signs in ASL: Distinct Patterns of Hemispheric Asymmetry

Science.gov (United States)

Hickok, Gregory; Pickell, Herbert; Klima, Edward; Bellugi, Ursula

2009-01-01

We examine the hemispheric organization for the production of two classes of ASL signs, lexical signs and classifier signs. Previous work has found strong left hemisphere dominance for the production of lexical signs, but several authors have speculated that classifier signs may involve the right hemisphere to a greater degree because they can…

Using Neural Pattern Classifiers to Quantify the Modularity of Conflict–Control Mechanisms in the Human Brain

Science.gov (United States)

Jiang, Jiefeng; Egner, Tobias

2014-01-01

Resolving conflicting sensory and motor representations is a core function of cognitive control, but it remains uncertain to what degree control over different sources of conflict is implemented by shared (domain general) or distinct (domain specific) neural resources. Behavioral data suggest conflict–control to be domain specific, but results from neuroimaging studies have been ambivalent. Here, we employed multivoxel pattern analyses that can decode a brain region's informational content, allowing us to distinguish incidental activation overlap from actual shared information processing. We trained independent sets of “searchlight” classifiers on functional magnetic resonance imaging data to decode control processes associated with stimulus-conflict (Stroop task) and ideomotor-conflict (Simon task). Quantifying the proportion of domain-specific searchlights (capable of decoding only one type of conflict) and domain-general searchlights (capable of decoding both conflict types) in each subject, we found both domain-specific and domain-general searchlights, though the former were more common. When mapping anatomical loci of these searchlights across subjects, neural substrates of stimulus- and ideomotor-specific conflict–control were found to be anatomically consistent across subjects, whereas the substrates of domain-general conflict–control were not. Overall, these findings suggest a hybrid neural architecture of conflict–control that entails both modular (domain specific) and global (domain general) components. PMID:23402762

An SVM classifier to separate false signals from microcalcifications in digital mammograms

Energy Technology Data Exchange (ETDEWEB)

Bazzani, Armando; Bollini, Dante; Brancaccio, Rosa; Campanini, Renato; Riccardi, Alessandro; Romani, Davide [Department of Physics, University of Bologna (Italy); INFN, Bologna (Italy); Lanconelli, Nico [Department of Physics, University of Bologna, and INFN, Bologna (Italy). E-mail: nico.lanconelli@bo.infn.it; Bevilacqua, Alessandro [Department of Electronics, Computer Science and Systems, University of Bologna, and INFN, Bologna (Italy)

2001-06-01

In this paper we investigate the feasibility of using an SVM (support vector machine) classifier in our automatic system for the detection of clustered microcalcifications in digital mammograms. SVM is a technique for pattern recognition which relies on the statistical learning theory. It minimizes a function of two terms: the number of misclassified vectors of the training set and a term regarding the generalization classifier capability. We compare the SVM classifier with an MLP (multi-layer perceptron) in the false-positive reduction phase of our detection scheme: a detected signal is considered either microcalcification or false signal, according to the value of a set of its features. The SVM classifier gets slightly better results than the MLP one (Az value of 0.963 against 0.958) in the presence of a high number of training data; the improvement becomes much more evident (Az value of 0.952 against 0.918) in training sets of reduced size. Finally, the setting of the SVM classifier is much easier than the MLP one. (author)

Rhythmic EEG patterns in extremely preterm infants : Classification and association with brain injury and outcome

NARCIS (Netherlands)

Weeke, Lauren C; van Ooijen, Inge M; Groenendaal, Floris; van Huffelen, Alexander C.; van Haastert, Ingrid C; van Stam, Carolien; Benders, Manon J; Toet, Mona C; Hellström-Westas, Lena; de Vries, Linda S

2017-01-01

OBJECTIVE: Classify rhythmic EEG patterns in extremely preterm infants and relate these to brain injury and outcome. METHODS: Retrospective analysis of 77 infants born <28 weeks gestational age (GA) who had a 2-channel EEG during the first 72 h after birth. Patterns detected by the BrainZ seizure

Linking brain-wide multivoxel activation patterns to behaviour: Examples from language and math

Science.gov (United States)

Raizada, Rajeev D.S.; Tsao, Feng-Ming; Liu, Huei-Mei; Holloway, Ian D.; Ansari, Daniel; Kuhl, Patricia K.

2010-01-01

A key goal of cognitive neuroscience is to find simple and direct connections between brain and behaviour. However, fMRI analysis typically involves choices between many possible options, with each choice potentially biasing any brain–behaviour correlations that emerge. Standard methods of fMRI analysis assess each voxel individually, but then face the problem of selection bias when combining those voxels into a region-of-interest, or ROI. Multivariate pattern-based fMRI analysis methods use classifiers to analyse multiple voxels together, but can also introduce selection bias via data-reduction steps as feature selection of voxels, pre-selecting activated regions, or principal components analysis. We show here that strong brain–behaviour links can be revealed without any voxel selection or data reduction, using just plain linear regression as a classifier applied to the whole brain at once, i.e. treating each entire brain volume as a single multi-voxel pattern. The brain–behaviour correlations emerged despite the fact that the classifier was not provided with any information at all about subjects' behaviour, but instead was given only the neural data and its condition-labels. Surprisingly, more powerful classifiers such as a linear SVM and regularised logistic regression produce very similar results. We discuss some possible reasons why the very simple brain-wide linear regression model is able to find correlations with behaviour that are as strong as those obtained on the one hand from a specific ROI and on the other hand from more complex classifiers. In a manner which is unencumbered by arbitrary choices, our approach offers a method for investigating connections between brain and behaviour which is simple, rigorous and direct. PMID:20132896

Improving the analysis of near-spectroscopy data with multivariate classification of hemodynamic patterns: a theoretical formulation and validation.

Science.gov (United States)

Gemignani, Jessica; Middell, Eike; Barbour, Randall L; Graber, Harry L; Blankertz, Benjamin

2018-04-04

The statistical analysis of functional near infrared spectroscopy (fNIRS) data based on the general linear model (GLM) is often made difficult by serial correlations, high inter-subject variability of the hemodynamic response, and the presence of motion artifacts. In this work we propose to extract information on the pattern of hemodynamic activations without using any a priori model for the data, by classifying the channels as 'active' or 'not active' with a multivariate classifier based on linear discriminant analysis (LDA). This work is developed in two steps. First we compared the performance of the two analyses, using a synthetic approach in which simulated hemodynamic activations were combined with either simulated or real resting-state fNIRS data. This procedure allowed for exact quantification of the classification accuracies of GLM and LDA. In the case of real resting-state data, the correlations between classification accuracy and demographic characteristics were investigated by means of a Linear Mixed Model. In the second step, to further characterize the reliability of the newly proposed analysis method, we conducted an experiment in which participants had to perform a simple motor task and data were analyzed with the LDA-based classifier as well as with the standard GLM analysis. The results of the simulation study show that the LDA-based method achieves higher classification accuracies than the GLM analysis, and that the LDA results are more uniform across different subjects and, in contrast to the accuracies achieved by the GLM analysis, have no significant correlations with any of the demographic characteristics. Findings from the real-data experiment are consistent with the results of the real-plus-simulation study, in that the GLM-analysis results show greater inter-subject variability than do the corresponding LDA results. The results obtained suggest that the outcome of GLM analysis is highly vulnerable to violations of theoretical assumptions

Comparing cosmic web classifiers using information theory

Energy Technology Data Exchange (ETDEWEB)

Leclercq, Florent [Institute of Cosmology and Gravitation (ICG), University of Portsmouth, Dennis Sciama Building, Burnaby Road, Portsmouth PO1 3FX (United Kingdom); Lavaux, Guilhem; Wandelt, Benjamin [Institut d' Astrophysique de Paris (IAP), UMR 7095, CNRS – UPMC Université Paris 6, Sorbonne Universités, 98bis boulevard Arago, F-75014 Paris (France); Jasche, Jens, E-mail: florent.leclercq@polytechnique.org, E-mail: lavaux@iap.fr, E-mail: j.jasche@tum.de, E-mail: wandelt@iap.fr [Excellence Cluster Universe, Technische Universität München, Boltzmannstrasse 2, D-85748 Garching (Germany)

2016-08-01

We introduce a decision scheme for optimally choosing a classifier, which segments the cosmic web into different structure types (voids, sheets, filaments, and clusters). Our framework, based on information theory, accounts for the design aims of different classes of possible applications: (i) parameter inference, (ii) model selection, and (iii) prediction of new observations. As an illustration, we use cosmographic maps of web-types in the Sloan Digital Sky Survey to assess the relative performance of the classifiers T-WEB, DIVA and ORIGAMI for: (i) analyzing the morphology of the cosmic web, (ii) discriminating dark energy models, and (iii) predicting galaxy colors. Our study substantiates a data-supported connection between cosmic web analysis and information theory, and paves the path towards principled design of analysis procedures for the next generation of galaxy surveys. We have made the cosmic web maps, galaxy catalog, and analysis scripts used in this work publicly available.

Comparing cosmic web classifiers using information theory

International Nuclear Information System (INIS)

Leclercq, Florent; Lavaux, Guilhem; Wandelt, Benjamin; Jasche, Jens

2016-01-01

We introduce a decision scheme for optimally choosing a classifier, which segments the cosmic web into different structure types (voids, sheets, filaments, and clusters). Our framework, based on information theory, accounts for the design aims of different classes of possible applications: (i) parameter inference, (ii) model selection, and (iii) prediction of new observations. As an illustration, we use cosmographic maps of web-types in the Sloan Digital Sky Survey to assess the relative performance of the classifiers T-WEB, DIVA and ORIGAMI for: (i) analyzing the morphology of the cosmic web, (ii) discriminating dark energy models, and (iii) predicting galaxy colors. Our study substantiates a data-supported connection between cosmic web analysis and information theory, and paves the path towards principled design of analysis procedures for the next generation of galaxy surveys. We have made the cosmic web maps, galaxy catalog, and analysis scripts used in this work publicly available.

Just-in-time adaptive classifiers-part II: designing the classifier.

Science.gov (United States)

Alippi, Cesare; Roveri, Manuel

2008-12-01

Aging effects, environmental changes, thermal drifts, and soft and hard faults affect physical systems by changing their nature and behavior over time. To cope with a process evolution adaptive solutions must be envisaged to track its dynamics; in this direction, adaptive classifiers are generally designed by assuming the stationary hypothesis for the process generating the data with very few results addressing nonstationary environments. This paper proposes a methodology based on k-nearest neighbor (NN) classifiers for designing adaptive classification systems able to react to changing conditions just-in-time (JIT), i.e., exactly when it is needed. k-NN classifiers have been selected for their computational-free training phase, the possibility to easily estimate the model complexity k and keep under control the computational complexity of the classifier through suitable data reduction mechanisms. A JIT classifier requires a temporal detection of a (possible) process deviation (aspect tackled in a companion paper) followed by an adaptive management of the knowledge base (KB) of the classifier to cope with the process change. The novelty of the proposed approach resides in the general framework supporting the real-time update of the KB of the classification system in response to novel information coming from the process both in stationary conditions (accuracy improvement) and in nonstationary ones (process tracking) and in providing a suitable estimate of k. It is shown that the classification system grants consistency once the change targets the process generating the data in a new stationary state, as it is the case in many real applications.

Automatic classification of liver scintigram patterns by computer

International Nuclear Information System (INIS)

Csernay, L.; Csirik, J.

1976-01-01

The pattern recognition of projection is one of the problems in the automatic evaluation of scintigrams. An algorythm and a computerized programme with the ability to classify the shapes of liver scintigrams has been elaborated by the authors. The programme differentiates not only normal and pathologic basic forms, but performs the identification of nine normal forms described by the literature. To pattern recognition structural and local parameters of the picture were defined. A detailed mechanism of the programme is given in their reports. The programme can classify 55 out of 60 actual liver scintigrams, a result different from subjective definition obtained in 5 cases. These were normal pattern of liver scans. No wrong definition was obtained when classifying normal and pathologic patterns

Differential theory of learning for efficient neural network pattern recognition

Science.gov (United States)

Hampshire, John B., II; Vijaya Kumar, Bhagavatula

1993-09-01

We describe a new theory of differential learning by which a broad family of pattern classifiers (including many well-known neural network paradigms) can learn stochastic concepts efficiently. We describe the relationship between a classifier's ability to generate well to unseen test examples and the efficiency of the strategy by which it learns. We list a series of proofs that differential learning is efficient in its information and computational resource requirements, whereas traditional probabilistic learning strategies are not. The proofs are illustrated by a simple example that lends itself to closed-form analysis. We conclude with an optical character recognition task for which three different types of differentially generated classifiers generalize significantly better than their probabilistically generated counterparts.

Executed Movement Using EEG Signals through a Naive Bayes Classifier

Directory of Open Access Journals (Sweden)

Juliano Machado

2014-11-01

Full Text Available Recent years have witnessed a rapid development of brain-computer interface (BCI technology. An independent BCI is a communication system for controlling a device by human intension, e.g., a computer, a wheelchair or a neuroprosthes is, not depending on the brain’s normal output pathways of peripheral nerves and muscles, but on detectable signals that represent responsive or intentional brain activities. This paper presents a comparative study of the usage of the linear discriminant analysis (LDA and the naive Bayes (NB classifiers on describing both right- and left-hand movement through electroencephalographic signal (EEG acquisition. For the analysis, we considered the following input features: the energy of the segments of a band pass-filtered signal with the frequency band in sensorimotor rhythms and the components of the spectral energy obtained through the Welch method. We also used the common spatial pattern (CSP filter, so as to increase the discriminatory activity among movement classes. By using the database generated by this experiment, we obtained hit rates up to 70%. The results are compatible with previous studies.

Aspectual Morphemes as Verb Classifiers in Slavic and Non-Slavic Languages

OpenAIRE

Menzenski, Matthew

2014-01-01

This paper was presented at the Slavic Linguistics Society Annual Meeting in Seattle, Washington on September 19 2014.   Abstract: Janda et al. (2013) propose an analysis of Russian aspectual prefixes as verb classifiers, arguing that the prefix which forms the 'natural perfective' from a given verb serves to classify that verb according to its semantic characteristics. This analysis contrasts with the traditional analysis of Russian aspect, described by Tixonov (1998) and others, in...

Pre-emergency-department care-seeking patterns are associated with the severity of presenting condition for emergency department visit and subsequent adverse events: a timeframe episode analysis.

Science.gov (United States)

Chan, Chien-Lung; Lin, Wender; Yang, Nan-Ping; Lai, K Robert; Huang, Hsin-Tsung

2015-01-01

Many patients treated in Emergency Department (ED) visits can be treated at primary or urgent care sectors, despite the fact that a number of ED visitors seek other forms of care prior to an ED visit. However, little is known regarding how the pre-ED activity episodes affect ED visits. We investigated whether care-seeking patterns involve the use of health care services of various types prior to ED visits and examined the associations of these patterns with the severity of the presenting condition for the ED visit (EDVS) and subsequent events. This retrospective observational study used administrative data on beneficiaries of the universal health care insurance program in Taiwan. The service type, treatment capacity, and relative diagnosis were used to classify pre-ED visits into 8 care types. Frequent pattern analysis was used to identify sequential care-seeking patterns and to classify 667,183 eligible pre-ED episodes into patterns. Generalized linear models were developed using generalized estimating equations to examine the associations of these patterns with EDVS and subsequent events. The results revealed 17 care-seeking patterns. The EDVS and likelihood of subsequent events significantly differed among patterns. The ED severity index of patterns differ from patterns seeking directly ED care (coefficients ranged from -0.05 to 0.13), and the odds-ratios for the likelihood of subsequent ED visits and hospitalization ranged from 1.18 to 1.86 and 1.16 to 2.84, respectively. The pre-ED care-seeking patterns differ in severity of presenting condition and subsequent events that may represent different causes of ED visit. Future health policy maker may adopt different intervention strategies for targeted population to reduce unnecessary ED visit effectively.

Hybrid classifiers methods of data, knowledge, and classifier combination

CERN Document Server

Wozniak, Michal

2014-01-01

This book delivers a definite and compact knowledge on how hybridization can help improving the quality of computer classification systems. In order to make readers clearly realize the knowledge of hybridization, this book primarily focuses on introducing the different levels of hybridization and illuminating what problems we will face with as dealing with such projects. In the first instance the data and knowledge incorporated in hybridization were the action points, and then a still growing up area of classifier systems known as combined classifiers was considered. This book comprises the aforementioned state-of-the-art topics and the latest research results of the author and his team from Department of Systems and Computer Networks, Wroclaw University of Technology, including as classifier based on feature space splitting, one-class classification, imbalance data, and data stream classification.

Role of BRAFV600E Mutation Analysis for Thyroid Nodules Classified as Indeterminate on Ultrasonography

International Nuclear Information System (INIS)

Nam, Sang Yu; Shin, Jung Hee; Han, Boo Kyung; Ko, Eun Young; Kang, Seok Seon; Hahn, Soo Yeon; Hwang, Ji Young; Nam, Mee Young; Kim, Jong Won; Chung, Jae Hoon

2010-01-01

We aimed to evaluate a possible role for BRAFV600E mutation analysis of aspiration specimens in the work up of thyroid nodules classified as indeterminate on US. A total of 122 nodules from 122 patients were prospectively classified as indeterminate nodules based on US findings. US-guided fine needle aspiration (FNA) was done for all 122 nodules. The presence of a BRAFV600E mutation in FNA specimens was determined by allele-specific PCR. US-indeterminate nodules were confirmed as malignant in 20.5% (25/122) of cases and benign in 76.2% (93/122) after FNA or surgery. A few (3.3% (4/122), remained indeterminate. A BRAFV600E mutation was identified in 14.8% (18/122) of US indeterminate nodules. Of those 18 nodules, three were benign and 13 were malignant after the initial FNA. One (0.8%, 1/122) with an initially benign cytology and a BRAFV600E mutation was confirmed to be malignant after surgery. The remaining two benign nodules with a mutation were not followed-up. All 9 initial FNA-nondiagnostic nodules were mutation negative but 2 (11.8%) of 17 indeterminate nodules on initial FNAs were mutation positive. BRAFV600E mutation analysis prevents false negative cytology for only 0.8% of cases and reduces ambiguous diagnoses for 1.6% of all US-indeterminate thyroid nodules. Therefore, adding BRAFV600E mutation analysis to FNA for US-indeterminate nodules is of limited usefulness

General aviation air traffic pattern safety analysis

Science.gov (United States)

Parker, L. C.

1973-01-01

A concept is described for evaluating the general aviation mid-air collision hazard in uncontrolled terminal airspace. Three-dimensional traffic pattern measurements were conducted at uncontrolled and controlled airports. Computer programs for data reduction, storage retrieval and statistical analysis have been developed. Initial general aviation air traffic pattern characteristics are presented. These preliminary results indicate that patterns are highly divergent from the expected standard pattern, and that pattern procedures observed can affect the ability of pilots to see and avoid each other.

Classifying Internet Pathological Users: Their Usage, Internet Sensation Seeking, and Perceptions.

Science.gov (United States)

Lin, Sunny S. J.

A study was conducted to identify pathological Internet users and to reveal their psychological features and problematic usage patterns. One thousand and fifty Taiwanese undergraduates were selected. An Internet Addiction Scale was adopted to classify 648 students into 4 clusters. The 146 users in the 4th cluster, who reported significantly higher…

Neural network classifier of attacks in IP telephony

Science.gov (United States)

Safarik, Jakub; Voznak, Miroslav; Mehic, Miralem; Partila, Pavol; Mikulec, Martin

2014-05-01

Various types of monitoring mechanism allow us to detect and monitor behavior of attackers in VoIP networks. Analysis of detected malicious traffic is crucial for further investigation and hardening the network. This analysis is typically based on statistical methods and the article brings a solution based on neural network. The proposed algorithm is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. Information about attacks on these honeypots is collected on a centralized server and then classified. This classification is based on different mechanisms. One of them is based on the multilayer perceptron neural network. The article describes inner structure of used neural network and also information about implementation of this network. The learning set for this neural network is based on real attack data collected from IP telephony honeypot called Dionaea. We prepare the learning set from real attack data after collecting, cleaning and aggregation of this information. After proper learning is the neural network capable to classify 6 types of most commonly used VoIP attacks. Using neural network classifier brings more accurate attack classification in a distributed system of honeypots. With this approach is possible to detect malicious behavior in a different part of networks, which are logically or geographically divided and use the information from one network to harden security in other networks. Centralized server for distributed set of nodes serves not only as a collector and classifier of attack data, but also as a mechanism for generating a precaution steps against attacks.

Using neural pattern classifiers to quantify the modularity of conflict-control mechanisms in the human brain.

Science.gov (United States)

Jiang, Jiefeng; Egner, Tobias

2014-07-01

Resolving conflicting sensory and motor representations is a core function of cognitive control, but it remains uncertain to what degree control over different sources of conflict is implemented by shared (domain general) or distinct (domain specific) neural resources. Behavioral data suggest conflict-control to be domain specific, but results from neuroimaging studies have been ambivalent. Here, we employed multivoxel pattern analyses that can decode a brain region's informational content, allowing us to distinguish incidental activation overlap from actual shared information processing. We trained independent sets of "searchlight" classifiers on functional magnetic resonance imaging data to decode control processes associated with stimulus-conflict (Stroop task) and ideomotor-conflict (Simon task). Quantifying the proportion of domain-specific searchlights (capable of decoding only one type of conflict) and domain-general searchlights (capable of decoding both conflict types) in each subject, we found both domain-specific and domain-general searchlights, though the former were more common. When mapping anatomical loci of these searchlights across subjects, neural substrates of stimulus- and ideomotor-specific conflict-control were found to be anatomically consistent across subjects, whereas the substrates of domain-general conflict-control were not. Overall, these findings suggest a hybrid neural architecture of conflict-control that entails both modular (domain specific) and global (domain general) components. © The Author 2013. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Reverse inference of memory retrieval processes underlying metacognitive monitoring of learning using multivariate pattern analysis.

Science.gov (United States)

Stiers, Peter; Falbo, Luciana; Goulas, Alexandros; van Gog, Tamara; de Bruin, Anique

2016-05-15

Monitoring of learning is only accurate at some time after learning. It is thought that immediate monitoring is based on working memory, whereas later monitoring requires re-activation of stored items, yielding accurate judgements. Such interpretations are difficult to test because they require reverse inference, which presupposes specificity of brain activity for the hidden cognitive processes. We investigated whether multivariate pattern classification can provide this specificity. We used a word recall task to create single trial examples of immediate and long term retrieval and trained a learning algorithm to discriminate them. Next, participants performed a similar task involving monitoring instead of recall. The recall-trained classifier recognized the retrieval patterns underlying immediate and long term monitoring and classified delayed monitoring examples as long-term retrieval. This result demonstrates the feasibility of decoding cognitive processes, instead of their content. Copyright © 2016 Elsevier Inc. All rights reserved.

A Gene Expression Classifier of Node-Positive Colorectal Cancer

Directory of Open Access Journals (Sweden)

Paul F. Meeh

2009-10-01

Full Text Available We used digital long serial analysis of gene expression to discover gene expression differences between node-negative and node-positive colorectal tumors and developed a multigene classifier able to discriminate between these two tumor types. We prepared and sequenced long serial analysis of gene expression libraries from one node-negative and one node-positive colorectal tumor, sequenced to a depth of 26,060 unique tags, and identified 262 tags significantly differentially expressed between these two tumors (P < 2 x 10-6. We confirmed the tag-to-gene assignments and differential expression of 31 genes by quantitative real-time polymerase chain reaction, 12 of which were elevated in the node-positive tumor. We analyzed the expression levels of these 12 upregulated genes in a validation panel of 23 additional tumors and developed an optimized seven-gene logistic regression classifier. The classifier discriminated between node-negative and node-positive tumors with 86% sensitivity and 80% specificity. Receiver operating characteristic analysis of the classifier revealed an area under the curve of 0.86. Experimental manipulation of the function of one classification gene, Fibronectin, caused profound effects on invasion and migration of colorectal cancer cells in vitro. These results suggest that the development of node-positive colorectal cancer occurs in part through elevated epithelial FN1 expression and suggest novel strategies for the diagnosis and treatment of advanced disease.

Machine Learning-based Individual Assessment of Cortical Atrophy Pattern in Alzheimer's Disease Spectrum: Development of the Classifier and Longitudinal Evaluation.

Science.gov (United States)

Lee, Jin San; Kim, Changsoo; Shin, Jeong-Hyeon; Cho, Hanna; Shin, Dae-Seock; Kim, Nakyoung; Kim, Hee Jin; Kim, Yeshin; Lockhart, Samuel N; Na, Duk L; Seo, Sang Won; Seong, Joon-Kyung

2018-03-07

To develop a new method for measuring Alzheimer's disease (AD)-specific similarity of cortical atrophy patterns at the individual-level, we employed an individual-level machine learning algorithm. A total of 869 cognitively normal (CN) individuals and 473 patients with probable AD dementia who underwent high-resolution 3T brain MRI were included. We propose a machine learning-based method for measuring the similarity of an individual subject's cortical atrophy pattern with that of a representative AD patient cohort. In addition, we validated this similarity measure in two longitudinal cohorts consisting of 79 patients with amnestic-mild cognitive impairment (aMCI) and 27 patients with probable AD dementia. Surface-based morphometry classifier for discriminating AD from CN showed sensitivity and specificity values of 87.1% and 93.3%, respectively. In the longitudinal validation study, aMCI-converts had higher atrophy similarity at both baseline (p < 0.001) and first year visits (p < 0.001) relative to non-converters. Similarly, AD patients with faster decline had higher atrophy similarity than slower decliners at baseline (p = 0.042), first year (p = 0.028), and third year visits (p = 0.027). The AD-specific atrophy similarity measure is a novel approach for the prediction of dementia risk and for the evaluation of AD trajectories on an individual subject level.

Patterns of 11C-PIB cerebral retention in mild cognitive impairment patients.

Science.gov (United States)

Banzo, I; Jiménez-Bonilla, J F; Martínez-Rodríguez, I; Quirce, R; de Arcocha-Torres, M; Bravo-Ferrer, Z; Lavado-Pérez, C; Sánchez-Juan, P; Rodríguez, E; Jiménez-Alonso, M; López-Defilló, J; Carril, J M

2016-01-01

To evaluate the patterns of cerebral cortical distribution of (11)C-PIB in patients with mild cognitive impairment (MCI). The study included 69 patients (37 male, age range 42-79 years) with MCI, sub-classified as 53 with amnestic-MCI (A-MCI), and 16 with non-amnestic-MCI (NA-MCI). Patients underwent (11)C-PIB PET/CT scan 60min after intravenous injection of the radiotracer. A visual analysis of the images was performed by 2 experienced physicians. (11)C-PIB-positive studies were considered when gray matter uptake was equal to or greater than white matter. According to the regions involved, (11)C-PIB-positive studies were classified into A-pattern (predominant retention in frontal, anterior cingulate, lateral temporal, and basal ganglia) and B-pattern (generalized retention). Thirty-nine of the 69 (56%) patients with MCI showed (11)C-PIB retention. Of the 53 A-MCI patients, 36 (68%) showed (11)C-PIB retention. Eleven out of 36 (30%) positive scans in A-MCI patients showed A-pattern, and 25 out of 36 (70%) patients had a B-pattern. Positive (11)C-PIB was observed in 3 out of 16 (19%) patients with NA-MCI. Regional distribution in these 3 patients showed A-pattern in 1, and B-pattern in 2 patients. Cortical retention of (11)C-PIB was more frequent in A-MCI than in NA-MCI patients, and also B-pattern than A-pattern in the (11)C-PIB positive group. The recognition of (11)C-PIB distribution patterns allows MCI patients to be classified, and the A-pattern may offer a therapeutic window for potential future treatments. Copyright © 2015 Elsevier España, S.L.U. and SEMNIM. All rights reserved.

Quantification of differences between nailfold capillaroscopy images with a scleroderma pattern and normal pattern using measures of geometric and algorithmic complexity.

Science.gov (United States)

Urwin, Samuel George; Griffiths, Bridget; Allen, John

2017-02-01

This study aimed to quantify and investigate differences in the geometric and algorithmic complexity of the microvasculature in nailfold capillaroscopy (NFC) images displaying a scleroderma pattern and those displaying a 'normal' pattern. 11 NFC images were qualitatively classified by a capillary specialist as indicative of 'clear microangiopathy' (CM), i.e. a scleroderma pattern, and 11 as 'not clear microangiopathy' (NCM), i.e. a 'normal' pattern. Pre-processing was performed, and fractal dimension (FD) and Kolmogorov complexity (KC) were calculated following image binarisation. FD and KC were compared between groups, and a k-means cluster analysis (n  =  2) on all images was performed, without prior knowledge of the group assigned to them (i.e. CM or NCM), using FD and KC as inputs. CM images had significantly reduced FD and KC compared to NCM images, and the cluster analysis displayed promising results that the quantitative classification of images into CM and NCM groups is possible using the mathematical measures of FD and KC. The analysis techniques used show promise for quantitative microvascular investigation in patients with systemic sclerosis.

Towards pattern understanding-new technologies beyond pattern recognition

Energy Technology Data Exchange (ETDEWEB)

Sakai, T

1982-04-01

The techniques employed in understanding-systems for pattern information are classified roughly under top-down and bottom-up techniques. These are outlined in the paper, and intellectual preparation for communications and information processing is briefly described. 1 ref.

Bayes classifiers for imbalanced traffic accidents datasets.

Science.gov (United States)

Mujalli, Randa Oqab; López, Griselda; Garach, Laura

2016-03-01

Traffic accidents data sets are usually imbalanced, where the number of instances classified under the killed or severe injuries class (minority) is much lower than those classified under the slight injuries class (majority). This, however, supposes a challenging problem for classification algorithms and may cause obtaining a model that well cover the slight injuries instances whereas the killed or severe injuries instances are misclassified frequently. Based on traffic accidents data collected on urban and suburban roads in Jordan for three years (2009-2011); three different data balancing techniques were used: under-sampling which removes some instances of the majority class, oversampling which creates new instances of the minority class and a mix technique that combines both. In addition, different Bayes classifiers were compared for the different imbalanced and balanced data sets: Averaged One-Dependence Estimators, Weightily Average One-Dependence Estimators, and Bayesian networks in order to identify factors that affect the severity of an accident. The results indicated that using the balanced data sets, especially those created using oversampling techniques, with Bayesian networks improved classifying a traffic accident according to its severity and reduced the misclassification of killed and severe injuries instances. On the other hand, the following variables were found to contribute to the occurrence of a killed causality or a severe injury in a traffic accident: number of vehicles involved, accident pattern, number of directions, accident type, lighting, surface condition, and speed limit. This work, to the knowledge of the authors, is the first that aims at analyzing historical data records for traffic accidents occurring in Jordan and the first to apply balancing techniques to analyze injury severity of traffic accidents. Copyright © 2015 Elsevier Ltd. All rights reserved.

Automated measurement and classification of pulmonary blood-flow velocity patterns using phase-contrast MRI and correlation analysis.

Science.gov (United States)

van Amerom, Joshua F P; Kellenberger, Christian J; Yoo, Shi-Joon; Macgowan, Christopher K

2009-01-01

An automated method was evaluated to detect blood flow in small pulmonary arteries and classify each as artery or vein, based on a temporal correlation analysis of their blood-flow velocity patterns. The method was evaluated using velocity-sensitive phase-contrast magnetic resonance data collected in vitro with a pulsatile flow phantom and in vivo in 11 human volunteers. The accuracy of the method was validated in vitro, which showed relative velocity errors of 12% at low spatial resolution (four voxels per diameter), but was reduced to 5% at increased spatial resolution (16 voxels per diameter). The performance of the method was evaluated in vivo according to its reproducibility and agreement with manual velocity measurements by an experienced radiologist. In all volunteers, the correlation analysis was able to detect and segment peripheral pulmonary vessels and distinguish arterial from venous velocity patterns. The intrasubject variability of repeated measurements was approximately 10% of peak velocity, or 2.8 cm/s root-mean-variance, demonstrating the high reproducibility of the method. Excellent agreement was obtained between the correlation analysis and radiologist measurements of pulmonary velocities, with a correlation of R2=0.98 (P<.001) and a slope of 0.99+/-0.01.

Detection of Driver Drowsiness Using Wavelet Analysis of Heart Rate Variability and a Support Vector Machine Classifier

Directory of Open Access Journals (Sweden)

Gang Li

2013-12-01

Full Text Available Driving while fatigued is just as dangerous as drunk driving and may result in car accidents. Heart rate variability (HRV analysis has been studied recently for the detection of driver drowsiness. However, the detection reliability has been lower than anticipated, because the HRV signals of drivers were always regarded as stationary signals. The wavelet transform method is a method for analyzing non-stationary signals. The aim of this study is to classify alert and drowsy driving events using the wavelet transform of HRV signals over short time periods and to compare the classification performance of this method with the conventional method that uses fast Fourier transform (FFT-based features. Based on the standard shortest duration for FFT-based short-term HRV evaluation, the wavelet decomposition is performed on 2-min HRV samples, as well as 1-min and 3-min samples for reference purposes. A receiver operation curve (ROC analysis and a support vector machine (SVM classifier are used for feature selection and classification, respectively. The ROC analysis results show that the wavelet-based method performs better than the FFT-based method regardless of the duration of the HRV sample that is used. Finally, based on the real-time requirements for driver drowsiness detection, the SVM classifier is trained using eighty FFT and wavelet-based features that are extracted from 1-min HRV signals from four subjects. The averaged leave-one-out (LOO classification performance using wavelet-based feature is 95% accuracy, 95% sensitivity, and 95% specificity. This is better than the FFT-based results that have 68.8% accuracy, 62.5% sensitivity, and 75% specificity. In addition, the proposed hardware platform is inexpensive and easy-to-use.

Dietary patterns and colorectal cancer risk: a meta-analysis.

Science.gov (United States)

Feng, Yu-Liang; Shu, Long; Zheng, Pei-Fen; Zhang, Xiao-Yan; Si, Cai-Juan; Yu, Xiao-Long; Gao, Wei; Zhang, Lun

2017-05-01

The analysis of dietary patterns has recently drawn considerable attention as a method of investigating the association between the overall whole diet and the risk of colorectal cancer. However, the results have yielded conflicting findings. Here, we carried out a meta-analysis to identify the association between dietary patterns and the risk of colorectal cancer. A total of 40 studies fulfilled the inclusion criteria and were included in this meta-analysis. The highest category of 'healthy' dietary pattern compared with the lowest category was apparently associated with a decreased risk for colorectal cancer [odds ratio (OR)=0.75; confidence interval (CI): 0.68-0.83; Pcolorectal cancer was shown for the highest compared with the lowest category of a 'western-style' dietary pattern (OR=1.40; CI: 1.26-1.56; Pcolorectal cancer in the highest compared with the lowest category of 'alcohol-consumption' pattern (OR=1.44; CI: 1.13-1.82; P=0.003). The results of this meta-analysis indicate that a 'healthy' dietary pattern may decrease the risk of colorectal cancer, whereas 'western-style' and 'alcohol-consumption' patterns may increase the risk of colorectal cancer.

Movement patterns of limb coordination in infant rolling.

Science.gov (United States)

Kobayashi, Yoshio; Watanabe, Hama; Taga, Gentaro

2016-12-01

Infants must perform dynamic whole-body movements to initiate rolling, a key motor skill. However, little is known regarding limb coordination and postural control in infant rolling. To address this lack of knowledge, we examined movement patterns and limb coordination during rolling in younger infants (aged 5-7 months) that had just begun to roll and in older infants (aged 8-10 months) with greater rolling experience. Due to anticipated difficulty in obtaining measurements over the second half of the rolling sequence, we limited our analysis to the first half. Ipsilateral and contralateral limbs were identified on the basis of rolling direction and were classified as either a stationary limb used for postural stability or a moving limb used for controlled movement. We classified the observed movement patterns by identifying the number of stationary limbs and the serial order of combinational limb movement patterns. Notably, older infants performed more movement patterns that involved a lower number of stationary limbs than younger infants. Despite the wide range of possible movement patterns, a small group of basic patterns dominated in both age groups. Our results suggest that the fundamental structure of limb coordination during rolling in the early acquisition stages remains unchanged until at least 8-10 months of age. However, compared to younger infants, older infants exhibited a greater ability to select an effective rotational movement by positioning themselves with fewer stationary limbs and performing faster limb movements.

Movement coordination patterns between the foot joints during walking

Directory of Open Access Journals (Sweden)

John B. Arnold

2017-10-01

Full Text Available Abstract Background In 3D gait analysis, kinematics of the foot joints are usually reported via isolated time histories of joint rotations and no information is provided on the relationship between rotations at different joints. The aim of this study was to identify movement coordination patterns in the foot during walking by expanding an existing vector coding technique according to an established multi-segment foot and ankle model. A graphical representation is also described to summarise the coordination patterns of joint rotations across multiple patients. Methods Three-dimensional multi-segment foot kinematics were recorded in 13 adults during walking. A modified vector coding technique was used to identify coordination patterns between foot joints involving calcaneus, midfoot, metatarsus and hallux segments. According to the type and direction of joints rotations, these were classified as in-phase (same direction, anti-phase (opposite directions, proximal or distal joint dominant. Results In early stance, 51 to 75% of walking trials showed proximal-phase coordination between foot joints comprising the calcaneus, midfoot and metatarsus. In-phase coordination was more prominent in late stance, reflecting synergy in the simultaneous inversion occurring at multiple foot joints. Conversely, a distal-phase coordination pattern was identified for sagittal plane motion of the ankle relative to the midtarsal joint, highlighting the critical role of arch shortening to locomotor function in push-off. Conclusions This study has identified coordination patterns between movement of the calcaneus, midfoot, metatarsus and hallux by expanding an existing vector cording technique for assessing and classifying coordination patterns of foot joints rotations during walking. This approach provides a different perspective in the analysis of multi-segment foot kinematics, and may be used for the objective quantification of the alterations in foot joint

Climatology of local flow patterns around Basel

Energy Technology Data Exchange (ETDEWEB)

Weber, R.O. [Paul Scherrer Inst. (PSI), Villigen (Switzerland)

1997-06-01

Recently a method has been developed to classify local-scale flow patterns from the wind measurements at a dense network of stations. It was found that in the MISTRAL area around Basel a dozen characteristic flow patterns occur. However, as the dense network of stations ran only during one year, no reliable climatology can be inferred from these data, especially the annual cycle of the flow patterns is not well determined from a single year of observations. As there exist several routinely operated stations in and near the MISTRAL area, a method was searched to identify the local flow patterns from the observations at the few routine stations. A linear discriminant analysis turned out to be the best method. Based of data from 11 stations which were simultaneously operated during 1990-1995 a six-year climatology of the flow patterns could be obtained. (author) 1 fig., 1 tab., 3 refs.

Pre-emergency-department care-seeking patterns are associated with the severity of presenting condition for emergency department visit and subsequent adverse events: a timeframe episode analysis.

Directory of Open Access Journals (Sweden)

Chien-Lung Chan

Full Text Available Many patients treated in Emergency Department (ED visits can be treated at primary or urgent care sectors, despite the fact that a number of ED visitors seek other forms of care prior to an ED visit. However, little is known regarding how the pre-ED activity episodes affect ED visits.We investigated whether care-seeking patterns involve the use of health care services of various types prior to ED visits and examined the associations of these patterns with the severity of the presenting condition for the ED visit (EDVS and subsequent events.This retrospective observational study used administrative data on beneficiaries of the universal health care insurance program in Taiwan. The service type, treatment capacity, and relative diagnosis were used to classify pre-ED visits into 8 care types. Frequent pattern analysis was used to identify sequential care-seeking patterns and to classify 667,183 eligible pre-ED episodes into patterns. Generalized linear models were developed using generalized estimating equations to examine the associations of these patterns with EDVS and subsequent events.The results revealed 17 care-seeking patterns. The EDVS and likelihood of subsequent events significantly differed among patterns. The ED severity index of patterns differ from patterns seeking directly ED care (coefficients ranged from -0.05 to 0.13, and the odds-ratios for the likelihood of subsequent ED visits and hospitalization ranged from 1.18 to 1.86 and 1.16 to 2.84, respectively.The pre-ED care-seeking patterns differ in severity of presenting condition and subsequent events that may represent different causes of ED visit. Future health policy maker may adopt different intervention strategies for targeted population to reduce unnecessary ED visit effectively.

Two Classifiers Based on Serum Peptide Pattern for Prediction of HBV-Induced Liver Cirrhosis Using MALDI-TOF MS

Directory of Open Access Journals (Sweden)

Yuan Cao

2013-01-01

Full Text Available Chronic infection with hepatitis B virus (HBV is associated with the majority of cases of liver cirrhosis (LC in China. Although liver biopsy is the reference method for evaluation of cirrhosis, it is an invasive procedure with inherent risk. The aim of this study is to discover novel noninvasive specific serum biomarkers for the diagnosis of HBV-induced LC. We performed bead fractionation/MALDI-TOF MS analysis on sera from patients with LC. Thirteen feature peaks which had optimal discriminatory performance were obtained by using support-vector-machine-(SVM- based strategy. Based on the previous results, five supervised machine learning methods were employed to construct classifiers that discriminated proteomic spectra of patients with HBV-induced LC from those of controls. Here, we describe two novel methods for prediction of HBV-induced LC, termed LC-NB and LC-MLP, respectively. We obtained a sensitivity of 90.9%, a specificity of 94.9%, and overall accuracy of 93.8% on an independent test set. Comparisons with the existing methods showed that LC-NB and LC-MLP held better accuracy. Our study suggests that potential serum biomarkers can be determined for discriminating LC and non-LC cohorts by using matrix-assisted laser desorption/ionization time-of-flight mass spectrometry. These two classifiers could be used for clinical practice in HBV-induced LC assessment.

Glycosyltransferase Gene Expression Profiles Classify Cancer Types and Propose Prognostic Subtypes

Science.gov (United States)

Ashkani, Jahanshah; Naidoo, Kevin J.

2016-05-01

Aberrant glycosylation in tumours stem from altered glycosyltransferase (GT) gene expression but can the expression profiles of these signature genes be used to classify cancer types and lead to cancer subtype discovery? The differential structural changes to cellular glycan structures are predominantly regulated by the expression patterns of GT genes and are a hallmark of neoplastic cell metamorphoses. We found that the expression of 210 GT genes taken from 1893 cancer patient samples in The Cancer Genome Atlas (TCGA) microarray data are able to classify six cancers; breast, ovarian, glioblastoma, kidney, colon and lung. The GT gene expression profiles are used to develop cancer classifiers and propose subtypes. The subclassification of breast cancer solid tumour samples illustrates the discovery of subgroups from GT genes that match well against basal-like and HER2-enriched subtypes and correlates to clinical, mutation and survival data. This cancer type glycosyltransferase gene signature finding provides foundational evidence for the centrality of glycosylation in cancer.

Fuzzy prototype classifier based on items and its application in recommender system

Directory of Open Access Journals (Sweden)

Mei Cai

2017-01-01

Full Text Available Currently, recommender systems (RS are incorporating implicit information from social circle of the Internet. The implicit social information in human mind is not easy to reflect in appropriate decision making techniques. This paper consists of 2 contributions. First, we develop an item-based prototype classifier (IPC in which a prototype represents a social circlers preferences as a pattern classification technique. We assume the social circle which distinguishes with others by the items their members like. The prototype structure of the classifier is defined by two2-dimensional matrices. We use information gain and OWA aggregator to construct a feature space. The item-based classifier assigns a new item to some prototypes with different prototypicalities. We reform a typical data setmIris data set in UCI Machine Learning Repository to verify our fuzzy prototype classifier. The second proposition of this paper is to give the application of IPC in recommender system to solve new item cold-start problems. We modify the dataset of MovieLens to perform experimental demonstrations of the proposed ideas.

Enhancing the Performance of LibSVM Classifier by Kernel F-Score Feature Selection

Science.gov (United States)

Sarojini, Balakrishnan; Ramaraj, Narayanasamy; Nickolas, Savarimuthu

Medical Data mining is the search for relationships and patterns within the medical datasets that could provide useful knowledge for effective clinical decisions. The inclusion of irrelevant, redundant and noisy features in the process model results in poor predictive accuracy. Much research work in data mining has gone into improving the predictive accuracy of the classifiers by applying the techniques of feature selection. Feature selection in medical data mining is appreciable as the diagnosis of the disease could be done in this patient-care activity with minimum number of significant features. The objective of this work is to show that selecting the more significant features would improve the performance of the classifier. We empirically evaluate the classification effectiveness of LibSVM classifier on the reduced feature subset of diabetes dataset. The evaluations suggest that the feature subset selected improves the predictive accuracy of the classifier and reduce false negatives and false positives.

Splicing analysis of 14 BRCA1 missense variants classifies nine variants as pathogenic

DEFF Research Database (Denmark)

Ahlborn, Lise B; Dandanell, Mette; Steffensen, Ane Y

2015-01-01

by functional analysis at the protein level. Results from a validated mini-gene splicing assay indicated that nine BRCA1 variants resulted in splicing aberrations leading to truncated transcripts and thus can be considered pathogenic (c.4987A>T/p.Met1663Leu, c.4988T>A/p.Met1663Lys, c.5072C>T/p.Thr1691Ile, c......Pathogenic germline mutations in the BRCA1 gene predispose carriers to early onset breast and ovarian cancer. Clinical genetic screening of BRCA1 often reveals variants with uncertain clinical significance, complicating patient and family management. Therefore, functional examinations are urgently...... needed to classify whether these uncertain variants are pathogenic or benign. In this study, we investigated 14 BRCA1 variants by in silico splicing analysis and mini-gene splicing assay. All 14 alterations were missense variants located within the BRCT domain of BRCA1 and had previously been examined...

Geostatistical analysis of allele presence patterns among American black bears in eastern North Carolina

Science.gov (United States)

Thompson, L.M.; Van Manen, F.T.; King, T.L.

2005-01-01

primary orientation of the best habitat areas. Furthermore, the patterns we observed suggest directions of potential source populations beyond the 2 study areas. Indeed, nearby areas classified as core black bear habitat exist in the directions indicated by our analysis. Geostatistical analysis of allele occurrence patterns may provide a useful technique to identify potential barriers to gene flow among bear populations.

Classifying smoking urges via machine learning.

Science.gov (United States)

Dumortier, Antoine; Beckjord, Ellen; Shiffman, Saul; Sejdić, Ervin

2016-12-01

Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications. In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms' performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions. Copyright © 2016 Elsevier Ireland Ltd. All rights

Minimal methylation classifier (MIMIC): A novel method for derivation and rapid diagnostic detection of disease-associated DNA methylation signatures.

Science.gov (United States)

Schwalbe, E C; Hicks, D; Rafiee, G; Bashton, M; Gohlke, H; Enshaei, A; Potluri, S; Matthiesen, J; Mather, M; Taleongpong, P; Chaston, R; Silmon, A; Curtis, A; Lindsey, J C; Crosier, S; Smith, A J; Goschzik, T; Doz, F; Rutkowski, S; Lannering, B; Pietsch, T; Bailey, S; Williamson, D; Clifford, S C

2017-10-18

Rapid and reliable detection of disease-associated DNA methylation patterns has major potential to advance molecular diagnostics and underpin research investigations. We describe the development and validation of minimal methylation classifier (MIMIC), combining CpG signature design from genome-wide datasets, multiplex-PCR and detection by single-base extension and MALDI-TOF mass spectrometry, in a novel method to assess multi-locus DNA methylation profiles within routine clinically-applicable assays. We illustrate the application of MIMIC to successfully identify the methylation-dependent diagnostic molecular subgroups of medulloblastoma (the most common malignant childhood brain tumour), using scant/low-quality samples remaining from the most recently completed pan-European medulloblastoma clinical trial, refractory to analysis by conventional genome-wide DNA methylation analysis. Using this approach, we identify critical DNA methylation patterns from previously inaccessible cohorts, and reveal novel survival differences between the medulloblastoma disease subgroups with significant potential for clinical exploitation.

[Quantitative analysis of landscape patterns at the juncture of Shaanxi, Shanxi and Inner Mongolia, based on remote sensing data--taking Yulin sheet TM image as an example].

Science.gov (United States)

Li, Tuansheng

2004-03-01

Based on the TM image of Yulin sheet and with the help of ERDAS, ARC/INFO and ARC/VIEW software, the landscape of Yulin sheet was classified. Using the spatial pattern analysis software FRAGSTATS of the vector version, a set of landscape indices were calculated at three scale levels of patches, classes and landscape. The results showed that landscape pattern indices could be successfully used in characterizing the spatial pattern of the studied area. However, this study should be further extended to the landscape of the same area in other period to analyze its dynamic change. FRAGSTATS was a good software, but should be improved by adding some indices such as PD2 developed by us.

Electrocardiogram Pattern Recognition and Analysis Based on Artificial Neural Networks and Support Vector Machines: A Review

Directory of Open Access Journals (Sweden)

Mario Sansone

2013-01-01

Full Text Available Computer systems for Electrocardiogram (ECG analysis support the clinician in tedious tasks (e.g., Holter ECG monitored in Intensive Care Units or in prompt detection of dangerous events (e.g., ventricular fibrillation. Together with clinical applications (arrhythmia detection and heart rate variability analysis, ECG is currently being investigated in biometrics (human identification, an emerging area receiving increasing attention. Methodologies for clinical applications can have both differences and similarities with respect to biometrics. This paper reviews methods of ECG processing from a pattern recognition perspective. In particular, we focus on features commonly used for heartbeat classification. Considering the vast literature in the field and the limited space of this review, we dedicated a detailed discussion only to a few classifiers (Artificial Neural Networks and Support Vector Machines because of their popularity; however, other techniques such as Hidden Markov Models and Kalman Filtering will be also mentioned.

Using pattern analysis methods to do fast detection of manufacturing pattern failures

Science.gov (United States)

Zhao, Evan; Wang, Jessie; Sun, Mason; Wang, Jeff; Zhang, Yifan; Sweis, Jason; Lai, Ya-Chieh; Ding, Hua

2016-03-01

At the advanced technology node, logic design has become extremely complex and is getting more challenging as the pattern geometry size decreases. The small sizes of layout patterns are becoming very sensitive to process variations. Meanwhile, the high pressure of yield ramp is always there due to time-to-market competition. The company that achieves patterning maturity earlier than others will have a great advantage and a better chance to realize maximum profit margins. For debugging silicon failures, DFT diagnostics can identify which nets or cells caused the yield loss. But normally, a long time period is needed with many resources to identify which failures are due to one common layout pattern or structure. This paper will present a new yield diagnostic flow, based on preliminary EFA results, to show how pattern analysis can more efficiently detect pattern related systematic defects. Increased visibility on design pattern related failures also allows more precise yield loss estimation.

Distinct patterns of Internet and smartphone-related problems among adolescents by gender: Latent class analysis.

Science.gov (United States)

Lee, Seung-Yup; Lee, Donghwan; Nam, Cho Rong; Kim, Da Yea; Park, Sera; Kwon, Jun-Gun; Kweon, Yong-Sil; Lee, Youngjo; Kim, Dai Jin; Choi, Jung-Seok

2018-05-23

Background and objectives The ubiquitous Internet connections by smartphones weakened the traditional boundaries between computers and mobile phones. We sought to explore whether smartphone-related problems differ from those of computer use according to gender using latent class analysis (LCA). Methods After informed consents, 555 Korean middle-school students completed surveys on gaming, Internet use, and smartphone usage patterns. They also completed various psychosocial instruments. LCA was performed for the whole group and by gender. In addition to ANOVA and χ 2 tests, post-hoc tests were conducted to examine differences among the LCA subgroups. Results In the whole group (n = 555), four subtypes were identified: dual-problem users (49.5%), problematic Internet users (7.7%), problematic smartphone users (32.1%), and "healthy" users (10.6%). Dual-problem users scored highest for addictive behaviors and other psychopathologies. The gender-stratified LCA revealed three subtypes for each gender. With dual-problem and healthy subgroup as common, problematic Internet subgroup was classified in the males, whereas problematic smartphone subgroup was classified in the females in the gender-stratified LCA. Thus, distinct patterns were observed according to gender with higher proportion of dual-problem present in males. While gaming was associated with problematic Internet use in males, aggression and impulsivity demonstrated associations with problematic smartphone use in females. Conclusions An increase in the number of digital media-related problems was associated with worse outcomes in various psychosocial scales. Gaming may play a crucial role in males solely displaying Internet-related problems. The heightened impulsivity and aggression seen in our female problematic smartphone users requires further research.

EEG analysis of seizure patterns using visibility graphs for detection of generalized seizures.

Science.gov (United States)

Wang, Lei; Long, Xi; Arends, Johan B A M; Aarts, Ronald M

2017-10-01

The traditional EEG features in the time and frequency domain show limited seizure detection performance in the epileptic population with intellectual disability (ID). In addition, the influence of EEG seizure patterns on detection performance was less studied. A single-channel EEG signal can be mapped into visibility graphs (VGS), including basic visibility graph (VG), horizontal VG (HVG), and difference VG (DVG). These graphs were used to characterize different EEG seizure patterns. To demonstrate its effectiveness in identifying EEG seizure patterns and detecting generalized seizures, EEG recordings of 615h on one EEG channel from 29 epileptic patients with ID were analyzed. A novel feature set with discriminative power for seizure detection was obtained by using the VGS method. The degree distributions (DDs) of DVG can clearly distinguish EEG of each seizure pattern. The degree entropy and power-law degree power in DVG were proposed here for the first time, and they show significant difference between seizure and non-seizure EEG. The connecting structure measured by HVG can better distinguish seizure EEG from background than those by VG and DVG. A traditional EEG feature set based on frequency analysis was used here as a benchmark feature set. With a support vector machine (SVM) classifier, the seizure detection performance of the benchmark feature set (sensitivity of 24%, FD t /h of 1.8s) can be improved by combining our proposed VGS features extracted from one EEG channel (sensitivity of 38%, FD t /h of 1.4s). The proposed VGS-based features can help improve seizure detection for ID patients. Copyright © 2017 Elsevier B.V. All rights reserved.

Pattern recognition in spaces of probability distributions for the analysis of edge-localized modes in tokamak plasmas

Energy Technology Data Exchange (ETDEWEB)

Shabbir, Aqsa

2016-07-07

scaling (MDS) and landmark multidimensional scaling (LMDS) for data visualization (dimensionality reduction). Furthermore, two new classification schemes are developed: a distance-to-centroid classifier (D2C) and a principal geodesic classifier (PGC). D2C classifies on the basis of the minimum GD to the class centroids and PGC considers the shape of the class on the manifold by determining the minimum distance to the principal geodesic of each class. The methods are validated by their application to the classification and retrieval of colored texture images represented in the wavelet domain. Both methods prove to be computationally efficient, yield high accuracy and also clearly exhibit the adequacy of the GD and its superiority over the Euclidean distance, for comparing PDFs. The second main goal of the work targets ELM analysis at three fronts, using pattern recognition and probabilistic modeling: (i) We first concentrate on visualization of ELM characteristics by creating maps containing projections of multidimensional ELM data, as well as the corresponding probabilistic models. In particular, GD-based MDS is used for representing the complete distributions of the multidimensional data characterizing the operational space of ELMs onto two-dimensional maps. Clusters corresponding to type I and type III ELMs are identified and the maps enable tracking of trends in plasma parameters across the operational space. It is shown that the maps can also be used with reasonable accuracy for predicting the values of the plasma parameters at a certain point in the operational space. (ii) Our second application concerns fast, standardized and automated classification of ELM types. The presented classification schemes are aimed at complementing the phenomenological characterization using standardized methods that are less susceptible to subjective interpretation, while considerably reducing the effort of ELM experts in identifying ELM types. To this end, different classification

Pattern recognition in spaces of probability distributions for the analysis of edge-localized modes in tokamak plasmas

International Nuclear Information System (INIS)

Shabbir, Aqsa

2016-01-01

scaling (MDS) and landmark multidimensional scaling (LMDS) for data visualization (dimensionality reduction). Furthermore, two new classification schemes are developed: a distance-to-centroid classifier (D2C) and a principal geodesic classifier (PGC). D2C classifies on the basis of the minimum GD to the class centroids and PGC considers the shape of the class on the manifold by determining the minimum distance to the principal geodesic of each class. The methods are validated by their application to the classification and retrieval of colored texture images represented in the wavelet domain. Both methods prove to be computationally efficient, yield high accuracy and also clearly exhibit the adequacy of the GD and its superiority over the Euclidean distance, for comparing PDFs. The second main goal of the work targets ELM analysis at three fronts, using pattern recognition and probabilistic modeling: (i) We first concentrate on visualization of ELM characteristics by creating maps containing projections of multidimensional ELM data, as well as the corresponding probabilistic models. In particular, GD-based MDS is used for representing the complete distributions of the multidimensional data characterizing the operational space of ELMs onto two-dimensional maps. Clusters corresponding to type I and type III ELMs are identified and the maps enable tracking of trends in plasma parameters across the operational space. It is shown that the maps can also be used with reasonable accuracy for predicting the values of the plasma parameters at a certain point in the operational space. (ii) Our second application concerns fast, standardized and automated classification of ELM types. The presented classification schemes are aimed at complementing the phenomenological characterization using standardized methods that are less susceptible to subjective interpretation, while considerably reducing the effort of ELM experts in identifying ELM types. To this end, different classification

A systems biology-based classifier for hepatocellular carcinoma diagnosis.

Directory of Open Access Journals (Sweden)

Yanqiong Zhang

Full Text Available AIM: The diagnosis of hepatocellular carcinoma (HCC in the early stage is crucial to the application of curative treatments which are the only hope for increasing the life expectancy of patients. Recently, several large-scale studies have shed light on this problem through analysis of gene expression profiles to identify markers correlated with HCC progression. However, those marker sets shared few genes in common and were poorly validated using independent data. Therefore, we developed a systems biology based classifier by combining the differential gene expression with topological features of human protein interaction networks to enhance the ability of HCC diagnosis. METHODS AND RESULTS: In the Oncomine platform, genes differentially expressed in HCC tissues relative to their corresponding normal tissues were filtered by a corrected Q value cut-off and Concept filters. The identified genes that are common to different microarray datasets were chosen as the candidate markers. Then, their networks were analyzed by GeneGO Meta-Core software and the hub genes were chosen. After that, an HCC diagnostic classifier was constructed by Partial Least Squares modeling based on the microarray gene expression data of the hub genes. Validations of diagnostic performance showed that this classifier had high predictive accuracy (85.88∼92.71% and area under ROC curve (approximating 1.0, and that the network topological features integrated into this classifier contribute greatly to improving the predictive performance. Furthermore, it has been demonstrated that this modeling strategy is not only applicable to HCC, but also to other cancers. CONCLUSION: Our analysis suggests that the systems biology-based classifier that combines the differential gene expression and topological features of human protein interaction network may enhance the diagnostic performance of HCC classifier.

Lifestyle Patterns and Weight Status in Spanish Adults: The ANIBES Study.

Science.gov (United States)

Pérez-Rodrigo, Carmen; Gianzo-Citores, Marta; Gil, Ángel; González-Gross, Marcela; Ortega, Rosa M; Serra-Majem, Lluis; Varela-Moreiras, Gregorio; Aranceta-Bartrina, Javier

2017-06-14

Limited knowledge is available on lifestyle patterns in Spanish adults. We investigated dietary patterns and possible meaningful clustering of physical activity, sedentary behavior, sleep time, and smoking in Spanish adults aged 18-64 years and their association with obesity. Analysis was based on a subsample ( n = 1617) of the cross-sectional ANIBES study in Spain. We performed exploratory factor analysis and subsequent cluster analysis of dietary patterns, physical activity, sedentary behaviors, sleep time, and smoking. Logistic regression analysis was used to explore the association between the cluster solutions and obesity. Factor analysis identified four dietary patterns, " Traditional DP ", " Mediterranean DP ", " Snack DP " and " Dairy-sweet DP ". Dietary patterns, physical activity behaviors, sedentary behaviors, sleep time, and smoking in Spanish adults aggregated into three different clusters of lifestyle patterns: " Mixed diet-physically active-low sedentary lifestyle pattern ", " Not poor diet-low physical activity-low sedentary lifestyle pattern " and " Poor diet-low physical activity-sedentary lifestyle pattern ". A higher proportion of people aged 18-30 years was classified into the " Poor diet-low physical activity-sedentary lifestyle pattern ". The prevalence odds ratio for obesity in men in the " Mixed diet-physically active-low sedentary lifestyle pattern " was significantly lower compared to those in the " Poor diet-low physical activity-sedentary lifestyle pattern ". Those behavior patterns are helpful to identify specific issues in population subgroups and inform intervention strategies. The findings in this study underline the importance of designing and implementing interventions that address multiple health risk practices, considering lifestyle patterns and associated determinants.

Energy-aware embedded classifier design for real-time emotion analysis.

Science.gov (United States)

Padmanabhan, Manoj; Murali, Srinivasan; Rincon, Francisco; Atienza, David

2015-01-01

Detection and classification of human emotions from multiple bio-signals has a wide variety of applications. Though electronic devices are available in the market today that acquire multiple body signals, the classification of human emotions in real-time, adapted to the tight energy budgets of wearable embedded systems is a big challenge. In this paper we present an embedded classifier for real-time emotion classification. We propose a system that operates at different energy budgeted modes, depending on the available energy, where each mode is constrained by an operating energy bound. The classifier has an offline training phase where feature selection is performed for each operating mode, with an energy-budget aware algorithm that we propose. Across the different operating modes, the classification accuracy ranges from 95% - 75% and 89% - 70% for arousal and valence respectively. The accuracy is traded off for less power consumption, which results in an increased battery life of up to 7.7 times (from 146.1 to 1126.9 hours).

Sentiment analysis system for movie review in Bahasa Indonesia using naive bayes classifier method

Science.gov (United States)

Nurdiansyah, Yanuar; Bukhori, Saiful; Hidayat, Rahmad

2018-04-01

There are many ways of implementing the use of sentiments often found in documents; one of which is the sentiments found on the product or service reviews. It is so important to be able to process and extract textual data from the documents. Therefore, we propose a system that is able to classify sentiments from review documents into two classes: positive sentiment and negative sentiment. We use Naive Bayes Classifier method in this document classification system that we build. We choose Movienthusiast, a movie reviews in Bahasa Indonesia website as the source of our review documents. From there, we were able to collect 1201 movie reviews: 783 positive reviews and 418 negative reviews that we use as the dataset for this machine learning classifier. The classifying accuracy yields an average of 88.37% from five times of accuracy measuring attempts using aforementioned dataset.

Patients on weaning trials classified with support vector machines

International Nuclear Information System (INIS)

Garde, Ainara; Caminal, Pere; Giraldo, Beatriz F; Schroeder, Rico; Voss, Andreas; Benito, Salvador

2010-01-01

The process of discontinuing mechanical ventilation is called weaning and is one of the most challenging problems in intensive care. An unnecessary delay in the discontinuation process and an early weaning trial are undesirable. This study aims to characterize the respiratory pattern through features that permit the identification of patients' conditions in weaning trials. Three groups of patients have been considered: 94 patients with successful weaning trials, who could maintain spontaneous breathing after 48 h (GSucc); 39 patients who failed the weaning trial (GFail) and 21 patients who had successful weaning trials, but required reintubation in less than 48 h (GRein). Patients are characterized by their cardiorespiratory interactions, which are described by joint symbolic dynamics (JSD) applied to the cardiac interbeat and breath durations. The most discriminating features in the classification of the different groups of patients (GSucc, GFail and GRein) are identified by support vector machines (SVMs). The SVM-based feature selection algorithm has an accuracy of 81% in classifying GSucc versus the rest of the patients, 83% in classifying GRein versus GSucc patients and 81% in classifying GRein versus the rest of the patients. Moreover, a good balance between sensitivity and specificity is achieved in all classifications

Spatial analysis of weed patterns

NARCIS (Netherlands)

Heijting, S.

2007-01-01

Keywords: Spatial analysis, weed patterns, Mead’s test, space-time correlograms, 2-D correlograms, dispersal, Generalized Linear Models, heterogeneity, soil, Taylor’s power law. Weeds in agriculture occur in patches. This thesis is a contribution to the characterization of this patchiness, to its

Patterns of Dysmorphic Features in Schizophrenia

Science.gov (United States)

Scutt, L.E.; Chow, E.W.C.; Weksberg, R.; Honer, W.G.; Bassett, Anne S.

2011-01-01

Congenital dysmorphic features are prevalent in schizophrenia and may reflect underlying neurodevelopmental abnormalities. A cluster analysis approach delineating patterns of dysmorphic features has been used in genetics to classify individuals into more etiologically homogeneous subgroups. In the present study, this approach was applied to schizophrenia, using a sample with a suspected genetic syndrome as a testable model. Subjects (n = 159) with schizophrenia or schizoaffective disorder were ascertained from chronic patient populations (random, n=123) or referred with possible 22q11 deletion syndrome (referred, n = 36). All subjects were evaluated for presence or absence of 70 reliably assessed dysmorphic features, which were used in a three-step cluster analysis. The analysis produced four major clusters with different patterns of dysmorphic features. Significant between-cluster differences were found for rates of 37 dysmorphic features (P dysmorphic features (P = 0.0001), and validating features not used in the cluster analysis: mild mental retardation (P = 0.001) and congenital heart defects (P = 0.002). Two clusters (1 and 4) appeared to represent more developmental subgroups of schizophrenia with elevated rates of dysmorphic features and validating features. Cluster 1 (n = 27) comprised mostly referred subjects. Cluster 4 (n= 18) had a different pattern of dysmorphic features; one subject had a mosaic Turner syndrome variant. Two other clusters had lower rates and patterns of features consistent with those found in previous studies of schizophrenia. Delineating patterns of dysmorphic features may help identify subgroups that could represent neurodevelopmental forms of schizophrenia with more homogeneous origins. PMID:11803519

Classifying adolescent attention-deficit/hyperactivity disorder (ADHD) based on functional and structural imaging.

Science.gov (United States)

Iannaccone, Reto; Hauser, Tobias U; Ball, Juliane; Brandeis, Daniel; Walitza, Susanne; Brem, Silvia

2015-10-01

Attention-deficit/hyperactivity disorder (ADHD) is a common disabling psychiatric disorder associated with consistent deficits in error processing, inhibition and regionally decreased grey matter volumes. The diagnosis is based on clinical presentation, interviews and questionnaires, which are to some degree subjective and would benefit from verification through biomarkers. Here, pattern recognition of multiple discriminative functional and structural brain patterns was applied to classify adolescents with ADHD and controls. Functional activation features in a Flanker/NoGo task probing error processing and inhibition along with structural magnetic resonance imaging data served to predict group membership using support vector machines (SVMs). The SVM pattern recognition algorithm correctly classified 77.78% of the subjects with a sensitivity and specificity of 77.78% based on error processing. Predictive regions for controls were mainly detected in core areas for error processing and attention such as the medial and dorsolateral frontal areas reflecting deficient processing in ADHD (Hart et al., in Hum Brain Mapp 35:3083-3094, 2014), and overlapped with decreased activations in patients in conventional group comparisons. Regions more predictive for ADHD patients were identified in the posterior cingulate, temporal and occipital cortex. Interestingly despite pronounced univariate group differences in inhibition-related activation and grey matter volumes the corresponding classifiers failed or only yielded a poor discrimination. The present study corroborates the potential of task-related brain activation for classification shown in previous studies. It remains to be clarified whether error processing, which performed best here, also contributes to the discrimination of useful dimensions and subtypes, different psychiatric disorders, and prediction of treatment success across studies and sites.

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.

Manual wheelchair propulsion patterns on natural surfaces during start-up propulsion.

Science.gov (United States)

Koontz, Alicia M; Roche, Bailey M; Collinger, Jennifer L; Cooper, Rory A; Boninger, Michael L

2009-11-01

To classify propulsion patterns over surfaces encountered in the natural environment during start-up and compare selected biomechanical variables between pattern types. Case series. National Veterans Wheelchair Games, Minneapolis, MN, 2005. Manual wheelchair users (N=29). Subjects pushed their wheelchairs from a resting position over high-pile carpet, over linoleum, and up a ramp with a 5 degrees incline while propulsion kinematics and kinetics were recorded with a motion capture system and an instrumented wheel. Three raters classified the first 3 strokes as 1 of 4 types on each surface: arc, semicircular (SC), single looping over propulsion (SL), and double looping over propulsion (DL). The Fisher exact test was used to assess pattern changes between strokes and surface type. A multiple analysis of variance test was used to compare peak and average resultant force and moment about the hub, average wheel velocity, stroke frequency, contact angle, and distance traveled between stroke patterns. SL was the most common pattern used during start-up propulsion (44.9%), followed by arc (35.9%), DL (14.1%), and SC (5.1%). Subjects who dropped their hands below the rim during recovery achieved faster velocities and covered greater distances (.016propulsion patterns is a difficult task that should use multiple raters. In addition, propulsion patterns change during start-up, with an arc pattern most prevalent initially. The biomechanical findings in this study agree with current clinical guidelines that recommend training users to drop the hand below the pushrim during recovery.

Cognitive approaches for patterns analysis and security applications

Science.gov (United States)

Ogiela, Marek R.; Ogiela, Lidia

2017-08-01

In this paper will be presented new opportunities for developing innovative solutions for semantic pattern classification and visual cryptography, which will base on cognitive and bio-inspired approaches. Such techniques can be used for evaluation of the meaning of analyzed patterns or encrypted information, and allow to involve such meaning into the classification task or encryption process. It also allows using some crypto-biometric solutions to extend personalized cryptography methodologies based on visual pattern analysis. In particular application of cognitive information systems for semantic analysis of different patterns will be presented, and also a novel application of such systems for visual secret sharing will be described. Visual shares for divided information can be created based on threshold procedure, which may be dependent on personal abilities to recognize some image details visible on divided images.

Quantum ensembles of quantum classifiers.

Science.gov (United States)

Schuld, Maria; Petruccione, Francesco

2018-02-09

Quantum machine learning witnesses an increasing amount of quantum algorithms for data-driven decision making, a problem with potential applications ranging from automated image recognition to medical diagnosis. Many of those algorithms are implementations of quantum classifiers, or models for the classification of data inputs with a quantum computer. Following the success of collective decision making with ensembles in classical machine learning, this paper introduces the concept of quantum ensembles of quantum classifiers. Creating the ensemble corresponds to a state preparation routine, after which the quantum classifiers are evaluated in parallel and their combined decision is accessed by a single-qubit measurement. This framework naturally allows for exponentially large ensembles in which - similar to Bayesian learning - the individual classifiers do not have to be trained. As an example, we analyse an exponentially large quantum ensemble in which each classifier is weighed according to its performance in classifying the training data, leading to new results for quantum as well as classical machine learning.

A unified classifier for robust face recognition based on combining multiple subspace algorithms

Science.gov (United States)

Ijaz Bajwa, Usama; Ahmad Taj, Imtiaz; Waqas Anwar, Muhammad

2012-10-01

Face recognition being the fastest growing biometric technology has expanded manifold in the last few years. Various new algorithms and commercial systems have been proposed and developed. However, none of the proposed or developed algorithm is a complete solution because it may work very well on one set of images with say illumination changes but may not work properly on another set of image variations like expression variations. This study is motivated by the fact that any single classifier cannot claim to show generally better performance against all facial image variations. To overcome this shortcoming and achieve generality, combining several classifiers using various strategies has been studied extensively also incorporating the question of suitability of any classifier for this task. The study is based on the outcome of a comprehensive comparative analysis conducted on a combination of six subspace extraction algorithms and four distance metrics on three facial databases. The analysis leads to the selection of the most suitable classifiers which performs better on one task or the other. These classifiers are then combined together onto an ensemble classifier by two different strategies of weighted sum and re-ranking. The results of the ensemble classifier show that these strategies can be effectively used to construct a single classifier that can successfully handle varying facial image conditions of illumination, aging and facial expressions.

Pattern formation of nanoflowers during the vapor-liquid-solid growth of silicon nanowires

International Nuclear Information System (INIS)

Bae, Joonho; Thompson-Flagg, Rebecca; Ekerdt, John G.; Shih, C.-K.

2008-01-01

Pattern formation of nanoflowers during the vapor-liquid-solid growth of Si nanowires is reported. Using transmission electron microscopy, scanning electron microscopy, and energy dispersive spectrometer analysis, we show that the flower consists of an Au/SiO x core-shell structure. Moreover, the growth of flower starts at the interface between the gold catalyst and the silicon nanowire, presumably by enhanced oxidation at this interface. The pattern formation can be classified as dense branching morphology (DBM). It is the first observation of DBM in a spherical geometry and at the nanoscale. The analysis of the average branching distance of this pattern shows that the pattern is most likely formed during the growth process, not the cooling process, and that the curvature of the gold droplet plays a crucial role in the frequency of branching

Improved pattern recognition systems by hybrid methods

International Nuclear Information System (INIS)

Duerr, B.; Haettich, W.; Tropf, H.; Winkler, G.; Fraunhofer-Gesellschaft zur Foerderung der Angewandten Forschung e.V., Karlsruhe

1978-12-01

This report describes a combination of statistical and syntactical pattern recongition methods. The hierarchically structured recognition system consists of a conventional statistical classifier, a structural classifier analysing the topological composition of the patterns, a stage reducing the number of hypotheses made by the first two stages, and a mixed stage based on a search for maximum similarity between syntactically generated prototypes and patterns. The stages work on different principles to avoid mistakes made in one stage in the other stages. This concept is applied to the recognition of numerals written without constraints. If no samples are rejected, a recognition rate of 99,5% is obtained. (orig.) [de

Dietary patterns and depression risk: A meta-analysis.

Science.gov (United States)

Li, Ye; Lv, Mei-Rong; Wei, Yan-Jin; Sun, Ling; Zhang, Ji-Xiang; Zhang, Huai-Guo; Li, Bin

2017-07-01

Although some studies have reported potential associations of dietary patterns with depression risk, a consistent perspective hasn't been estimated to date. Therefore, we conducted this meta-analysis to evaluate the relation between dietary patterns and the risk of depression. A literature research was conducted searching MEDLINE and EMBASE databases up to September 2016. In total, 21 studies from ten countries met the inclusion criteria and were included in the present meta-analysis. A dietary pattern characterized by a high intakes of fruit, vegetables, whole grain, fish, olive oil, low-fat dairy and antioxidants and low intakes of animal foods was apparently associated with a decreased risk of depression. A dietary pattern characterized by a high consumption of red and/or processed meat, refined grains, sweets, high-fat dairy products, butter, potatoes and high-fat gravy, and low intakes of fruits and vegetables is associated with an increased risk of depression. The results of this meta-analysis suggest that healthy pattern may decrease the risk of depression, whereas western-style may increase the risk of depression. However, more randomized controlled trails and cohort studies are urgently required to confirm this findings. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

Comparison of the CPU and memory performance of StatPatternRecognitions (SPR) and Toolkit for MultiVariate Analysis (TMVA)

International Nuclear Information System (INIS)

Palombo, G.

2012-01-01

High Energy Physics data sets are often characterized by a huge number of events. Therefore, it is extremely important to use statistical packages able to efficiently analyze these unprecedented amounts of data. We compare the performance of the statistical packages StatPatternRecognition (SPR) and Toolkit for MultiVariate Analysis (TMVA). We focus on how CPU time and memory usage of the learning process scale versus data set size. As classifiers, we consider Random Forests, Boosted Decision Trees and Neural Networks only, each with specific settings. For our tests, we employ a data set widely used in the machine learning community, “Threenorm” data set, as well as data tailored for testing various edge cases. For each data set, we constantly increase its size and check CPU time and memory needed to build the classifiers implemented in SPR and TMVA. We show that SPR is often significantly faster and consumes significantly less memory. For example, the SPR implementation of Random Forest is by an order of magnitude faster and consumes an order of magnitude less memory than TMVA on Threenorm data.

A proposed heuristic methodology for searching reloading pattern

International Nuclear Information System (INIS)

Choi, K. Y.; Yoon, Y. K.

1993-01-01

A new heuristic method for loading pattern search has been developed to overcome shortcomings of the algorithmic approach. To reduce the size of vast solution space, general shuffling rules, a regionwise shuffling method, and a pattern grouping method were introduced. The entropy theory was applied to classify possible loading patterns into groups with similarity between them. The pattern search program was implemented with use of the PROLOG language. A two-group nodal code MEDIUM-2D was used for analysis of power distribution in the core. The above mentioned methodology has been tested to show effectiveness in reducing of solution space down to a few hundred pattern groups. Burnable poison rods were then arranged in each pattern group in accordance with burnable poison distribution rules, which led to further reduction of the solution space to several scores of acceptable pattern groups. The method of maximizing cycle length (MCL) and minimizing power-peaking factor (MPF) were applied to search for specific useful loading patterns from the acceptable pattern groups. Thus, several specific loading patterns that have low power-peaking factor and large cycle length were successfully searched from the selected pattern groups. (Author)

Classifying carbon credit buyers according to their attitudes towards and involvement in CDM sustainability labels

Energy Technology Data Exchange (ETDEWEB)

Parnphumeesup, Piya, E-mail: pp66@hw.ac.uk [International Centre for Island Technology (ICIT), Institute of Petroleum Engineering, Heriot-Watt University, Old Academy, Back Road, Stromness, Orkney KW16 3AW, Scotland (United Kingdom); Kerr, Sandy A. [International Centre for Island Technology (ICIT), Institute of Petroleum Engineering, Heriot-Watt University, Old Academy, Back Road, Stromness, Orkney KW16 3AW, Scotland (United Kingdom)

2011-10-15

Carbon markets are increasingly conscious of the social and environmental 'quality' of credits delivered by CDM projects. Consequently carbon credits are no longer viewed as a homogenous good and buyers now differentiate between credits supplied by different types of CDM project. The objective of this paper is to classify CER buyers according to their attitudes towards and preferences for CDM sustainability labels. K-means clustering was used to segment a sample of buyers into two clusters. The results indicate that two clear clusters exist with distinct profile patterns. Moreover, the results of discriminant analysis confirmed that the two-cluster solution was valid. Finally, the results of the chi-square analysis and a cross-tabulation showed that these two clusters were significantly different in: organization type; level of paid up capital; perception of sustainable development benefits; perception of return on investment; perception of image of the sustainability labeling; participation in the voluntary market; the project priority; knowledge in the sustainability label; attitude towards the host country's duty; and their willingness to pay. - Highlights: > The K-means clustering was used to classify CER buyers in the primary market. > The carbon market is divided into two: the premium market; and the normal market. > Governments tend to be members of the premium market. > 82% of members in the premium market are willing to pay a price premium for CERs.

Classifying carbon credit buyers according to their attitudes towards and involvement in CDM sustainability labels

International Nuclear Information System (INIS)

Parnphumeesup, Piya; Kerr, Sandy A.

2011-01-01

Carbon markets are increasingly conscious of the social and environmental 'quality' of credits delivered by CDM projects. Consequently carbon credits are no longer viewed as a homogenous good and buyers now differentiate between credits supplied by different types of CDM project. The objective of this paper is to classify CER buyers according to their attitudes towards and preferences for CDM sustainability labels. K-means clustering was used to segment a sample of buyers into two clusters. The results indicate that two clear clusters exist with distinct profile patterns. Moreover, the results of discriminant analysis confirmed that the two-cluster solution was valid. Finally, the results of the chi-square analysis and a cross-tabulation showed that these two clusters were significantly different in: organization type; level of paid up capital; perception of sustainable development benefits; perception of return on investment; perception of image of the sustainability labeling; participation in the voluntary market; the project priority; knowledge in the sustainability label; attitude towards the host country's duty; and their willingness to pay. - Highlights: → The K-means clustering was used to classify CER buyers in the primary market. → The carbon market is divided into two: the premium market; and the normal market. → Governments tend to be members of the premium market. → 82% of members in the premium market are willing to pay a price premium for CERs.

Performance Analysis and Optimization for Cognitive Radio Networks with Classified Secondary Users and Impatient Packets

Directory of Open Access Journals (Sweden)

Yuan Zhao

2017-01-01

Full Text Available A cognitive radio network with classified Secondary Users (SUs is considered. There are two types of SU packets, namely, SU1 packets and SU2 packets, in the system. The SU1 packets have higher priority than the SU2 packets. Considering the diversity of the SU packets and the real-time need of the interrupted SU packets, a novel spectrum allocation strategy with classified SUs and impatient packets is proposed. Based on the number of PU packets, SU1 packets, and SU2 packets in the system, by modeling the queue dynamics of the networks users as a three-dimensional discrete-time Markov chain, the transition probability matrix of the Markov chain is given. Then with the steady-state analysis, some important performance measures of the SU2 packets are derived to show the system performance with numerical results. Specially, in order to optimize the system actions of the SU2 packets, the individually optimal strategy and the socially optimal strategy for the SU2 packets are demonstrated. Finally, a pricing mechanism is provided to oblige the SU2 packets to follow the socially optimal strategy.

Forest fragmentation in Massachusetts, USA: a town-level assessment using Morphological Spatial Pattern Analysis and affinity propagation

Science.gov (United States)

J. Rogan; T.M. Wright; J. Cardille; H. Pearsall; Y. Ogneva-Himmelberger; Rachel Riemann; Kurt Riitters; K. Partington

2016-01-01

Forest fragmentation has been studied extensively with respect to biodiversity loss, disruption of ecosystem services, and edge effects although the relationship between forest fragmentation and human activities is still not well understood. We classified the pattern of forests in Massachusetts using fragmentation indicators to address...

Similarity-dissimilarity plot for visualization of high dimensional data in biomedical pattern classification.

Science.gov (United States)

Arif, Muhammad

2012-06-01

In pattern classification problems, feature extraction is an important step. Quality of features in discriminating different classes plays an important role in pattern classification problems. In real life, pattern classification may require high dimensional feature space and it is impossible to visualize the feature space if the dimension of feature space is greater than four. In this paper, we have proposed a Similarity-Dissimilarity plot which can project high dimensional space to a two dimensional space while retaining important characteristics required to assess the discrimination quality of the features. Similarity-dissimilarity plot can reveal information about the amount of overlap of features of different classes. Separable data points of different classes will also be visible on the plot which can be classified correctly using appropriate classifier. Hence, approximate classification accuracy can be predicted. Moreover, it is possible to know about whom class the misclassified data points will be confused by the classifier. Outlier data points can also be located on the similarity-dissimilarity plot. Various examples of synthetic data are used to highlight important characteristics of the proposed plot. Some real life examples from biomedical data are also used for the analysis. The proposed plot is independent of number of dimensions of the feature space.

Patterns of Gram-stained fecal flora as a quick diagnostic marker in patients with severe SIRS.

Science.gov (United States)

Shimizu, Kentaro; Ogura, Hiroshi; Tomono, Kazunori; Tasaki, Osamu; Asahara, Takashi; Nomoto, Koji; Morotomi, Masami; Matsushima, Asako; Nakahori, Yasutaka; Yamano, Shuhei; Osuka, Akinori; Kuwagata, Yasuyuki; Sugimoto, Hisashi

2011-06-01

The gut is an important target organ of injury during critically ill conditions. Although Gram staining is a common and quick method for identifying bacteria, its clinical application has not been fully evaluated in critically ill conditions. This study's aims were to identify patterns of Gram-stained fecal flora and compare them to cultured bacterial counts and to investigate the association between the patterns and septic complications in patients with severe systemic inflammatory response syndrome (SIRS). Fifty-two patients with SIRS were included whose Gram-stained fecal flora was classified into three patterns. In a diverse pattern, large numbers of multiple kinds of bacteria completely covered the field. In a single pattern, one specific kind of bacteria or fungi predominantly covered the field. In a depleted pattern, most bacteria were diminished in the field. In the analysis of fecal flora, the numbers of total obligate anaerobes in the depleted pattern was significantly lower than those in the diverse pattern and single pattern (p Gram-stained fecal flora can be classified into three patterns and are associated with both cultured bacterial counts and clinical information. Gram-stained fecal bacteria can be used as a quick bedside diagnostic marker for severe SIRS patients.

Modeling activity patterns of wildlife using time-series analysis.

Science.gov (United States)

Zhang, Jindong; Hull, Vanessa; Ouyang, Zhiyun; He, Liang; Connor, Thomas; Yang, Hongbo; Huang, Jinyan; Zhou, Shiqiang; Zhang, Zejun; Zhou, Caiquan; Zhang, Hemin; Liu, Jianguo

2017-04-01

The study of wildlife activity patterns is an effective approach to understanding fundamental ecological and evolutionary processes. However, traditional statistical approaches used to conduct quantitative analysis have thus far had limited success in revealing underlying mechanisms driving activity patterns. Here, we combine wavelet analysis, a type of frequency-based time-series analysis, with high-resolution activity data from accelerometers embedded in GPS collars to explore the effects of internal states (e.g., pregnancy) and external factors (e.g., seasonal dynamics of resources and weather) on activity patterns of the endangered giant panda ( Ailuropoda melanoleuca ). Giant pandas exhibited higher frequency cycles during the winter when resources (e.g., water and forage) were relatively poor, as well as during spring, which includes the giant panda's mating season. During the summer and autumn when resources were abundant, pandas exhibited a regular activity pattern with activity peaks every 24 hr. A pregnant individual showed distinct differences in her activity pattern from other giant pandas for several months following parturition. These results indicate that animals adjust activity cycles to adapt to seasonal variation of the resources and unique physiological periods. Wavelet coherency analysis also verified the synchronization of giant panda activity level with air temperature and solar radiation at the 24-hr band. Our study also shows that wavelet analysis is an effective tool for analyzing high-resolution activity pattern data and its relationship to internal and external states, an approach that has the potential to inform wildlife conservation and management across species.

Refractory nonconvulsive status epilepticus in coma: analysis of the evolution of ictal patterns

Directory of Open Access Journals (Sweden)

Paulo Breno Noronha Liberalesso

2012-07-01

Full Text Available OBJECTIVE: Nonconvulsive status epilepticus (NCSE is currently considered as one of the most frequent types of status epilepticus (SE. The objective of the present study was to identify the natural history of the electrographical evolution of refractory NCSE and to establish the relationship between ictal patterns and prognosis. METHODS: We analyzed, retrospectively, 14 patients with loss of consciousness and NCSE. The ictal patterns were classified as discrete seizures (DS, merging seizures (MS, continuous ictal discharges (CID, continuous ictal discharges with flat periods (CID-F, and periodic lateralized epileptiform discharges (PLEDs. RESULTS: The ictal patterns were DS (n=7; 50.0%, PLEDs (n=3; 1.4%, CID (n=2; 14.3%, MS (n=1; 7.1%, and CID-F (n=1; 7.1%. CONCLUSIONS: NCSE electrographic findings are heterogeneous and do not follow a stereotyped sequence. PLEDs were related to a higher probability of neurological morbidity and mortality.

Recurrent daily rainfall patterns over South Africa and associated dynamics during the core of the austral summer

CSIR Research Space (South Africa)

Cretat, J

2010-12-01

Full Text Available field instead of atmospheric processes and dynamics. An original agglomerative hierarchical clustering approach is used to classify daily rainfall patterns recorded at 5352 stations from DJF 1971 to DJF 1999. Five clusters are retained for analysis...

A study on the extraction of feature variables for the pattern recognition for welding flaws

International Nuclear Information System (INIS)

Kim, J. Y.; Kim, C. H.; Kim, B. H.

1996-01-01

In this study, the researches classifying the artificial and natural flaws in welding parts are performed using the pattern recognition technology. For this purpose the signal pattern recognition package including the user defined function was developed and the total procedure including the digital signal processing, feature extraction, feature selection and classifier selection is treated by bulk. Specially it is composed with and discussed using the statistical classifier such as the linear discriminant function classifier, the empirical Bayesian classifier. Also, the pattern recognition technology is applied to classification problem of natural flaw(i.e multiple classification problem-crack, lack of penetration, lack of fusion, porosity, and slag inclusion, the planar and volumetric flaw classification problem). According to this results, if appropriately teamed the neural network classifier is better than stastical classifier in the classification problem of natural flaw. And it is possible to acquire the recognition rate of 80% above through it is different a little according to domain extracting the feature and the classifier.

Learning-induced pattern classification in a chaotic neural network

International Nuclear Information System (INIS)

Li, Yang; Zhu, Ping; Xie, Xiaoping; He, Guoguang; Aihara, Kazuyuki

2012-01-01

In this Letter, we propose a Hebbian learning rule with passive forgetting (HLRPF) for use in a chaotic neural network (CNN). We then define the indices based on the Euclidean distance to investigate the evolution of the weights in a simplified way. Numerical simulations demonstrate that, under suitable external stimulations, the CNN with the proposed HLRPF acts as a fuzzy-like pattern classifier that performs much better than an ordinary CNN. The results imply relationship between learning and recognition. -- Highlights: ► Proposing a Hebbian learning rule with passive forgetting (HLRPF). ► Defining indices to investigate the evolution of the weights simply. ► The chaotic neural network with HLRPF acts as a fuzzy-like pattern classifier. ► The pattern classifier ability of the network is improved much.

Use of information barriers to protect classified information

International Nuclear Information System (INIS)

MacArthur, D.; Johnson, M.W.; Nicholas, N.J.; Whiteson, R.

1998-01-01

This paper discusses the detailed requirements for an information barrier (IB) for use with verification systems that employ intrusive measurement technologies. The IB would protect classified information in a bilateral or multilateral inspection of classified fissile material. Such a barrier must strike a balance between providing the inspecting party the confidence necessary to accept the measurement while protecting the inspected party's classified information. The authors discuss the structure required of an IB as well as the implications of the IB on detector system maintenance. A defense-in-depth approach is proposed which would provide assurance to the inspected party that all sensitive information is protected and to the inspecting party that the measurements are being performed as expected. The barrier could include elements of physical protection (such as locks, surveillance systems, and tamper indicators), hardening of key hardware components, assurance of capabilities and limitations of hardware and software systems, administrative controls, validation and verification of the systems, and error detection and resolution. Finally, an unclassified interface could be used to display and, possibly, record measurement results. The introduction of an IB into an analysis system may result in many otherwise innocuous components (detectors, analyzers, etc.) becoming classified and unavailable for routine maintenance by uncleared personnel. System maintenance and updating will be significantly simplified if the classification status of as many components as possible can be made reversible (i.e. the component can become unclassified following the removal of classified objects)

Spatial pattern recognition of seismic events in South West Colombia

Science.gov (United States)

Benítez, Hernán D.; Flórez, Juan F.; Duque, Diana P.; Benavides, Alberto; Lucía Baquero, Olga; Quintero, Jiber

2013-09-01

Recognition of seismogenic zones in geographical regions supports seismic hazard studies. This recognition is usually based on visual, qualitative and subjective analysis of data. Spatial pattern recognition provides a well founded means to obtain relevant information from large amounts of data. The purpose of this work is to identify and classify spatial patterns in instrumental data of the South West Colombian seismic database. In this research, clustering tendency analysis validates whether seismic database possesses a clustering structure. A non-supervised fuzzy clustering algorithm creates groups of seismic events. Given the sensitivity of fuzzy clustering algorithms to centroid initial positions, we proposed a methodology to initialize centroids that generates stable partitions with respect to centroid initialization. As a result of this work, a public software tool provides the user with the routines developed for clustering methodology. The analysis of the seismogenic zones obtained reveals meaningful spatial patterns in South-West Colombia. The clustering analysis provides a quantitative location and dispersion of seismogenic zones that facilitates seismological interpretations of seismic activities in South West Colombia.

Description and Analysis Pattern for Theses and Dissertations

Directory of Open Access Journals (Sweden)

Sirous Alidousti

2009-07-01

Full Text Available Dissertations and theses that are generated in course of research at PhD and Masters levels are considered to be important scientific documents in every country. Data description and analysis of such documents collected together, could automatically - especially when compared with data from other resources - provide new information that is very valuable. Nevertheless, no comprehensive, integrated pattern exists for such description and analysis. The present paper offers the findings of a research conducted for devising an information analysis pattern for dissertations and theses. It also puts forward information categories derived from such documents that could be described and analyzed.

Improved Classification by Non Iterative and Ensemble Classifiers in Motor Fault Diagnosis

Directory of Open Access Journals (Sweden)

PANIGRAHY, P. S.

2018-02-01

Full Text Available Data driven approach for multi-class fault diagnosis of induction motor using MCSA at steady state condition is a complex pattern classification problem. This investigation has exploited the built-in ensemble process of non-iterative classifiers to resolve the most challenging issues in this area, including bearing and stator fault detection. Non-iterative techniques exhibit with an average 15% of increased fault classification accuracy against their iterative counterparts. Particularly RF has shown outstanding performance even at less number of training samples and noisy feature space because of its distributive feature model. The robustness of the results, backed by the experimental verification shows that the non-iterative individual classifiers like RF is the optimum choice in the area of automatic fault diagnosis of induction motor.

Rhythmic EEG patterns in extremely preterm infants: Classification and association with brain injury and outcome.

Science.gov (United States)

Weeke, Lauren C; van Ooijen, Inge M; Groenendaal, Floris; van Huffelen, Alexander C; van Haastert, Ingrid C; van Stam, Carolien; Benders, Manon J; Toet, Mona C; Hellström-Westas, Lena; de Vries, Linda S

2017-12-01

Classify rhythmic EEG patterns in extremely preterm infants and relate these to brain injury and outcome. Retrospective analysis of 77 infants born Rhythmic patterns were observed in 62.3% (ictal 1.3%, PEDs 44%, other waveforms 86.3%) with multiple patterns in 36.4%. Ictal discharges were only observed in one and excluded from further analyses. The EEG location of the other waveforms (pRhythmic waveforms related to head position are likely artefacts. Rhythmic EEG patterns may have a different significance in extremely preterm infants. Copyright © 2017 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.

Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations.

Science.gov (United States)

Zhang, Yi; Ren, Jinchang; Jiang, Jianmin

2015-01-01

Maximum likelihood classifier (MLC) and support vector machines (SVM) are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions.

Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations

Directory of Open Access Journals (Sweden)

Yi Zhang

2015-01-01

Full Text Available Maximum likelihood classifier (MLC and support vector machines (SVM are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions.

Pattern theory the stochastic analysis of real-world signals

CERN Document Server

Mumford, David

2010-01-01

Pattern theory is a distinctive approach to the analysis of all forms of real-world signals. At its core is the design of a large variety of probabilistic models whose samples reproduce the look and feel of the real signals, their patterns, and their variability. Bayesian statistical inference then allows you to apply these models in the analysis of new signals. This book treats the mathematical tools, the models themselves, and the computational algorithms for applying statistics to analyze six representative classes of signals of increasing complexity. The book covers patterns in text, sound

Radiation regression patterns after cobalt plaque insertion for retinoblastoma

International Nuclear Information System (INIS)

Buys, R.J.; Abramson, D.H.; Ellsworth, R.M.; Haik, B.

1983-01-01

An analysis of 31 eyes of 30 patients who had been treated with cobalt plaques for retinoblastoma disclosed that a type I radiation regression pattern developed in 15 patients; type II, in one patient, and type III, in five patients. Nine patients had a regression pattern characterized by complete destruction of the tumor, the surrounding choroid, and all of the vessels in the area into which the plaque was inserted. This resulting white scar, corresponding to the sclerae only, was classified as a type IV radiation regression pattern. There was no evidence of tumor recurrence in patients with type IV regression patterns, with an average follow-up of 6.5 years, after receiving cobalt plaque therapy. Twenty-nine of these 30 patients had been unsuccessfully treated with at least one other modality (ie, light coagulation, cryotherapy, external beam radiation, or chemotherapy)

Radiation regression patterns after cobalt plaque insertion for retinoblastoma

Energy Technology Data Exchange (ETDEWEB)

Buys, R.J.; Abramson, D.H.; Ellsworth, R.M.; Haik, B.

1983-08-01

An analysis of 31 eyes of 30 patients who had been treated with cobalt plaques for retinoblastoma disclosed that a type I radiation regression pattern developed in 15 patients; type II, in one patient, and type III, in five patients. Nine patients had a regression pattern characterized by complete destruction of the tumor, the surrounding choroid, and all of the vessels in the area into which the plaque was inserted. This resulting white scar, corresponding to the sclerae only, was classified as a type IV radiation regression pattern. There was no evidence of tumor recurrence in patients with type IV regression patterns, with an average follow-up of 6.5 years, after receiving cobalt plaque therapy. Twenty-nine of these 30 patients had been unsuccessfully treated with at least one other modality (ie, light coagulation, cryotherapy, external beam radiation, or chemotherapy).

Evaluating EMG Feature and Classifier Selection for Application to Partial-Hand Prosthesis Control

Directory of Open Access Journals (Sweden)

Adenike A. Adewuyi

2016-10-01

Full Text Available Pattern recognition-based myoelectric control of upper limb prostheses has the potential to restore control of multiple degrees of freedom. Though this control method has been extensively studied in individuals with higher-level amputations, few studies have investigated its effectiveness for individuals with partial-hand amputations. Most partial-hand amputees retain a functional wrist and the ability of pattern recognition-based methods to correctly classify hand motions from different wrist positions is not well studied. In this study, focusing on partial-hand amputees, we evaluate (1 the performance of non-linear and linear pattern recognition algorithms and (2 the performance of optimal EMG feature subsets for classification of four hand motion classes in different wrist positions for 16 non-amputees and 4 amputees. Our results show that linear discriminant analysis and linear and non-linear artificial neural networks perform significantly better than the quadratic discriminant analysis for both non-amputees and partial-hand amputees. For amputees, including information from multiple wrist positions significantly decreased error (p<0.001 but no further significant decrease in error occurred when more than 4, 2, or 3 positions were included for the extrinsic (p=0.07, intrinsic (p=0.06, or combined extrinsic and intrinsic muscle EMG (p=0.08, respectively. Finally, we found that a feature set determined by selecting optimal features from each channel outperformed the commonly used time domain (p<0.001 and time domain/autoregressive feature sets (p<0.01. This method can be used as a screening filter to select the features from each channel that provide the best classification of hand postures across different wrist positions.

Temporal fringe pattern analysis with parallel computing

International Nuclear Information System (INIS)

Tuck Wah Ng; Kar Tien Ang; Argentini, Gianluca

2005-01-01

Temporal fringe pattern analysis is invaluable in transient phenomena studies but necessitates long processing times. Here we describe a parallel computing strategy based on the single-program multiple-data model and hyperthreading processor technology to reduce the execution time. In a two-node cluster workstation configuration we found that execution periods were reduced by 1.6 times when four virtual processors were used. To allow even lower execution times with an increasing number of processors, the time allocated for data transfer, data read, and waiting should be minimized. Parallel computing is found here to present a feasible approach to reduce execution times in temporal fringe pattern analysis

Recurrent Patterns in Dst Time Series

Directory of Open Access Journals (Sweden)

Hee-Jeong Kim

2003-06-01

Full Text Available This study reports one approach for the classification of magnetic storms into recurrent patterns. A storm event is defined as a local minimum of Dst index. The analysis of Dst index for the period of year 1957 through year 2000 has demonstrated that a large portion of the storm events can be classified into a set of recurrent patterns. In our approach, the classification is performed by seeking a categorization that minimizes thermodynamic free energy which is defined as the sum of classification errors and entropy. The error is calculated as the squared sum of the value differences between events. The classification depends on the noise parameter T that represents the strength of the intrinsic error in the observation and classification process. The classification results would be applicable in space weather forecasting.

A fingertip force prediction model for grasp patterns characterised from the chaotic behaviour of EEG.

Science.gov (United States)

Roy, Rinku; Sikdar, Debdeep; Mahadevappa, Manjunatha; Kumar, C S

2018-05-19

A stable grasp is attained through appropriate hand preshaping and precise fingertip forces. Here, we have proposed a method to decode grasp patterns from motor imagery and subsequent fingertip force estimation model with a slippage avoidance strategy. We have developed a feature-based classification of electroencephalography (EEG) associated with imagination of the grasping postures. Chaotic behaviour of EEG for different grasping patterns has been utilised to capture the dynamics of associated motor activities. We have computed correlation dimension (CD) as the feature and classified with "one against one" multiclass support vector machine (SVM) to discriminate between different grasping patterns. The result of the analysis showed varying classification accuracies at different subband levels. Broad categories of grasping patterns, namely, power grasp and precision grasp, were classified at a 96.0% accuracy rate in the alpha subband. Furthermore, power grasp subtypes were classified with an accuracy of 97.2% in the upper beta subband, whereas precision grasp subtypes showed relatively lower 75.0% accuracy in the alpha subband. Following assessment of fingertip force distributions while grasping, a nonlinear autoregressive (NAR) model with proper prediction of fingertip forces was proposed for each grasp pattern. A slippage detection strategy has been incorporated with automatic recalibration of the regripping force. Intention of each grasp pattern associated with corresponding fingertip force model was virtualised in this work. This integrated system can be utilised as the control strategy for prosthetic hand in the future. The model to virtualise motor imagery based fingertip force prediction with inherent slippage correction for different grasp types ᅟ.

Neural Network for Principal Component Analysis with Applications in Image Compression

Directory of Open Access Journals (Sweden)

Luminita State

2007-04-01

Full Text Available Classical feature extraction and data projection methods have been extensively investigated in the pattern recognition and exploratory data analysis literature. Feature extraction and multivariate data projection allow avoiding the "curse of dimensionality", improve the generalization ability of classifiers and significantly reduce the computational requirements of pattern classifiers. During the past decade a large number of artificial neural networks and learning algorithms have been proposed for solving feature extraction problems, most of them being adaptive in nature and well-suited for many real environments where adaptive approach is required. Principal Component Analysis, also called Karhunen-Loeve transform is a well-known statistical method for feature extraction, data compression and multivariate data projection and so far it has been broadly used in a large series of signal and image processing, pattern recognition and data analysis applications.

A Comparison of Spectral Angle Mapper and Artificial Neural Network Classifiers Combined with Landsat TM Imagery Analysis for Obtaining Burnt Area Mapping

Directory of Open Access Journals (Sweden)

Marko Scholze

2010-03-01

Full Text Available Satellite remote sensing, with its unique synoptic coverage capabilities, can provide accurate and immediately valuable information on fire analysis and post-fire assessment, including estimation of burnt areas. In this study the potential for burnt area mapping of the combined use of Artificial Neural Network (ANN and Spectral Angle Mapper (SAM classifiers with Landsat TM satellite imagery was evaluated in a Mediterranean setting. As a case study one of the most catastrophic forest fires, which occurred near the capital of Greece during the summer of 2007, was used. The accuracy of the two algorithms in delineating the burnt area from the Landsat TM imagery, acquired shortly after the fire suppression, was determined by the classification accuracy results of the produced thematic maps. In addition, the derived burnt area estimates from the two classifiers were compared with independent estimates available for the study region, obtained from the analysis of higher spatial resolution satellite data. In terms of the overall classification accuracy, ANN outperformed (overall accuracy 90.29%, Kappa coefficient 0.878 the SAM classifier (overall accuracy 83.82%, Kappa coefficient 0.795. Total burnt area estimates from the two classifiers were found also to be in close agreement with the other available estimates for the study region, with a mean absolute percentage difference of ~1% for ANN and ~6.5% for SAM. The study demonstrates the potential of the examined here algorithms in detecting burnt areas in a typical Mediterranean setting.

Differentiation of several interstitial lung disease patterns in HRCT images using support vector machine: role of databases on performance

Science.gov (United States)

Kale, Mandar; Mukhopadhyay, Sudipta; Dash, Jatindra K.; Garg, Mandeep; Khandelwal, Niranjan

2016-03-01

Interstitial lung disease (ILD) is complicated group of pulmonary disorders. High Resolution Computed Tomography (HRCT) considered to be best imaging technique for analysis of different pulmonary disorders. HRCT findings can be categorised in several patterns viz. Consolidation, Emphysema, Ground Glass Opacity, Nodular, Normal etc. based on their texture like appearance. Clinician often find it difficult to diagnosis these pattern because of their complex nature. In such scenario computer-aided diagnosis system could help clinician to identify patterns. Several approaches had been proposed for classification of ILD patterns. This includes computation of textural feature and training /testing of classifier such as artificial neural network (ANN), support vector machine (SVM) etc. In this paper, wavelet features are calculated from two different ILD database, publically available MedGIFT ILD database and private ILD database, followed by performance evaluation of ANN and SVM classifiers in terms of average accuracy. It is found that average classification accuracy by SVM is greater than ANN where trained and tested on same database. Investigation continued further to test variation in accuracy of classifier when training and testing is performed with alternate database and training and testing of classifier with database formed by merging samples from same class from two individual databases. The average classification accuracy drops when two independent databases used for training and testing respectively. There is significant improvement in average accuracy when classifiers are trained and tested with merged database. It infers dependency of classification accuracy on training data. It is observed that SVM outperforms ANN when same database is used for training and testing.

Gaming Device Usage Patterns Predict Internet Gaming Disorder: Comparison across Different Gaming Device Usage Patterns

OpenAIRE

Soo-Hyun Paik; Hyun Cho; Ji-Won Chun; Jo-Eun Jeong; Dai-Jin Kim

2017-01-01

Gaming behaviors have been significantly influenced by smartphones. This study was designed to explore gaming behaviors and clinical characteristics across different gaming device usage patterns and the role of the patterns on Internet gaming disorder (IGD). Responders of an online survey regarding smartphone and online game usage were classified by different gaming device usage patterns: (1) individuals who played only computer games; (2) individuals who played computer games more than smart...

Classifying countries according to leading causes of death in the world at the beginning of the 21st century

Directory of Open Access Journals (Sweden)

Marinković Ivan

2010-01-01

Full Text Available Cause mortality of a population is an important segment in the analysis of mortality, because it sums up all factors which influence death indicators on a certain territory in a direct way. At the beginning of the 21st century, the situation is not the same everywhere in the world and countries do not share a unique pattern of the causes of deaths. Infectious and parasitic diseases are still dominant in underdeveloped countries, while the leading causes of deaths in developed countries are circulatory disorders and neoplasm. Cardiovascular diseases are the cause of 29% of total mortality in the world, infectious cause 19%, tumors 13% and violent deaths about 9% (based on data from 2002. This paper gives an analysis of the spatial distribution of the leading causes of deaths using the geographic information system (Arc-View GIS, based on the ratio of total mortality and death rates of the population from a certain group of diseases. Based on data analysis, a hypothesis has been set on the significance of the regional factor in forming a picture of population mortality according to causes of death. A regional factor implies a set of physical geographical as well as general social specificities of a certain region which form a pattern of population behavior. Based on death rates, cardiovascular diseases are represented the most in the mortality rates of countries in Eastern and Southeastern Europe. Infectious diseases imperil the population in the Sub-Saharan region of Africa; tumors are most common in Europe, North America and Japan. The highest rates of violent deaths are in countries of the former Soviet Union and the Sub- Saharan zone. Classifying death rates according to leading causes of death represents a prerequisite for forming a final picture of mortality according to causes of death in the world at the beginning of the 'new century'. The method of gathering together the causes of death is possible by applying a statistical model of

RECOG-ORNL, Pattern Recognition Data Analysis

International Nuclear Information System (INIS)

Begovich, C.L.; Larson, N.M.

2000-01-01

Description of program or function: RECOG-ORNL, a general-purpose pattern recognition code, is a modification of the RECOG program, written at Lawrence Livermore National Laboratory. RECOG-ORNL contains techniques for preprocessing, analyzing, and displaying data, and for unsupervised and supervised learning. Data preprocessing routines transform the data into useful representations by auto-calling, selecting important variables, and/or adding products or transformations of the variables of the data set. Data analysis routines use correlations to evaluate the data and interrelationships among the data. Display routines plot the multidimensional patterns in two dimensions or plot histograms, patterns, or one variable versus another. Unsupervised learning techniques search for classes contained inherently in the data. Supervised learning techniques use known information about some of the data to generate predicted properties for an unknown set

Supervised Learning for Visual Pattern Classification

Science.gov (United States)

Zheng, Nanning; Xue, Jianru

This chapter presents an overview of the topics and major ideas of supervised learning for visual pattern classification. Two prevalent algorithms, i.e., the support vector machine (SVM) and the boosting algorithm, are briefly introduced. SVMs and boosting algorithms are two hot topics of recent research in supervised learning. SVMs improve the generalization of the learning machine by implementing the rule of structural risk minimization (SRM). It exhibits good generalization even when little training data are available for machine training. The boosting algorithm can boost a weak classifier to a strong classifier by means of the so-called classifier combination. This algorithm provides a general way for producing a classifier with high generalization capability from a great number of weak classifiers.

On the pathologically altered pulmonary pattern

International Nuclear Information System (INIS)

Ginzburg, M.A.; Kinoshenko, Yu.T.

1982-01-01

The notions ''normal'' and ''pathologically altered pulmonary pattern'' are specified. A grouping of lung pattern alterations based on morphopathogenetic features is provided: blood and lymphatic vascular alterations, changes in the bronchi, lung stroma, and combined alterations. Radiologic appearance of the altered pulmonary pattern is classified in keeping with the basic principles of an X-ray shade examination. The terms, such as ''enriching'', ''strengthening'', ''deformation'', etc., used for describing the pathologically altered pulmonary pattern are defined

MELDOQ - astrophysical image and pattern analysis in medicine: early recognition of malignant melanomas of the skin by digital image analysis. Final report

International Nuclear Information System (INIS)

Bunk, W.; Pompl, R.; Morfill, G.; Stolz, W.; Abmayr, W.

1999-01-01

Dermatoscopy is at present the most powerful clinical method for early detection of malignant melanomas. However, the application requires a lot of expertise and experience. Therefore, a quantitative image analysis system has been developed in order to assist dermatologists in 'on site diagnosis' and to improve the detection efficiency. Based on a very extensive dataset of dermatoscopic images, recorded in a standardized manner, a number of features for quantitative characterization of complex patterns in melanocytic skin lesions has been developed. The derived classifier improved the detection rate of malignant and benign melanocytic lesions to over 90% (sensitivity =91.5% and specificity =93.4% in the test set), using only six measures. A distinguishing feature of the system is the visualization of the quantified characteristics that are based on the dermatoscopic ABCD-rule. The developed prototype of a dermatoscopic workplace consists of defined procedures for standardized image acquisition and documentation, components of a necessary data pre-processing (e.g. shading- and colour-correction, removal of artefacts), quantification algorithms (evaluating asymmetry properties, border characteristics, the content of colours and structural components) and classification routines. In 2000 an industrial partner will begin marketing the digital imaging system including the specialized software for the early detection of skin cancer, which is suitable for clinicians and practitioners. The primary used nonlinear analysis techniques (e.g. scaling index method and others) can identify and characterize complex patterns in images and have a diagnostic potential in many other applications. (orig.) [de

Maximum margin classifier working in a set of strings.

Science.gov (United States)

Koyano, Hitoshi; Hayashida, Morihiro; Akutsu, Tatsuya

2016-03-01

Numbers and numerical vectors account for a large portion of data. However, recently, the amount of string data generated has increased dramatically. Consequently, classifying string data is a common problem in many fields. The most widely used approach to this problem is to convert strings into numerical vectors using string kernels and subsequently apply a support vector machine that works in a numerical vector space. However, this non-one-to-one conversion involves a loss of information and makes it impossible to evaluate, using probability theory, the generalization error of a learning machine, considering that the given data to train and test the machine are strings generated according to probability laws. In this study, we approach this classification problem by constructing a classifier that works in a set of strings. To evaluate the generalization error of such a classifier theoretically, probability theory for strings is required. Therefore, we first extend a limit theorem for a consensus sequence of strings demonstrated by one of the authors and co-workers in a previous study. Using the obtained result, we then demonstrate that our learning machine classifies strings in an asymptotically optimal manner. Furthermore, we demonstrate the usefulness of our machine in practical data analysis by applying it to predicting protein-protein interactions using amino acid sequences and classifying RNAs by the secondary structure using nucleotide sequences.

Pinpointing the classifiers of English language writing ability: A discriminant function analysis approach

Directory of Open Access Journals (Sweden)

Mohammad Ali Shams

2013-02-01

Full Text Available     The major aim of this paper was to investigate the validity of language and intelligence factors for classifying Iranian English learners` writing performance. Iranian participants of the study took three tests for grammar, breadth, and depth of vocabulary, and two tests for verbal and narrative intelligence. They also produced a corpus of argumentative writings in answer to IELTS specimen. Several runs of discriminant function analyses were used to examine the classifying power of the five variables for discriminating between low and high ability L2 writers. The results revealed that among language factors, depth of vocabulary (collocational knowledge produces the best discriminant function. In general, narrative intelligence was found to be the most reliable predictor for membership in low or high groups. It was also found that, among the five sub-abilities of narrative intelligence, emplotment carries the highest classifying value. Finally, the applications and implications of the results for second language researchers, cognitive scientists, and applied linguists were discussed.Â

Multi-spatial analysis of aeolian dune-field patterns

Science.gov (United States)

Ewing, Ryan C.; McDonald, George D.; Hayes, Alex G.

2015-07-01

Aeolian dune-fields are composed of different spatial scales of bedform patterns that respond to changes in environmental boundary conditions over a wide range of time scales. This study examines how variations in spatial scales of dune and ripple patterns found within dune fields are used in environmental reconstructions on Earth, Mars and Titan. Within a single bedform type, different spatial scales of bedforms emerge as a pattern evolves from an initial state into a well-organized pattern, such as with the transition from protodunes to dunes. Additionally, different types of bedforms, such as ripples, coarse-grained ripples and dunes, coexist at different spatial scales within a dune-field. Analysis of dune-field patterns at the intersection of different scales and types of bedforms at different stages of development provides a more comprehensive record of sediment supply and wind regime than analysis of a single scale and type of bedform. Interpretations of environmental conditions from any scale of bedform, however, are limited to environmental signals associated with the response time of that bedform. Large-scale dune-field patterns integrate signals over long-term climate cycles and reveal little about short-term variations in wind or sediment supply. Wind ripples respond instantly to changing conditions, but reveal little about longer-term variations in wind or sediment supply. Recognizing the response time scales across different spatial scales of bedforms maximizes environmental interpretations from dune-field patterns.

Multivariate analysis of 2-DE protein patterns - Practical approaches

DEFF Research Database (Denmark)

Jacobsen, Charlotte; Jacobsen, Susanne; Grove, H.

2007-01-01

Practical approaches to the use of multivariate data analysis of 2-DE protein patterns are demonstrated by three independent strategies for the image analysis and the multivariate analysis on the same set of 2-DE data. Four wheat varieties were selected on the basis of their baking quality. Two...... of the varieties were of strong baking quality and hard wheat kernel and two were of weak baking quality and soft kernel. Gliadins at different stages of grain development were analyzed by the application of multivariate data analysis on images of 2-DEs. Patterns related to the wheat varieties, harvest times...

An Improvement To The k-Nearest Neighbor Classifier For ECG Database

Science.gov (United States)

Jaafar, Haryati; Hidayah Ramli, Nur; Nasir, Aimi Salihah Abdul

2018-03-01

The k nearest neighbor (kNN) is a non-parametric classifier and has been widely used for pattern classification. However, in practice, the performance of kNN often tends to fail due to the lack of information on how the samples are distributed among them. Moreover, kNN is no longer optimal when the training samples are limited. Another problem observed in kNN is regarding the weighting issues in assigning the class label before classification. Thus, to solve these limitations, a new classifier called Mahalanobis fuzzy k-nearest centroid neighbor (MFkNCN) is proposed in this study. Here, a Mahalanobis distance is applied to avoid the imbalance of samples distribition. Then, a surrounding rule is employed to obtain the nearest centroid neighbor based on the distributions of training samples and its distance to the query point. Consequently, the fuzzy membership function is employed to assign the query point to the class label which is frequently represented by the nearest centroid neighbor Experimental studies from electrocardiogram (ECG) signal is applied in this study. The classification performances are evaluated in two experimental steps i.e. different values of k and different sizes of feature dimensions. Subsequently, a comparative study of kNN, kNCN, FkNN and MFkCNN classifier is conducted to evaluate the performances of the proposed classifier. The results show that the performance of MFkNCN consistently exceeds the kNN, kNCN and FkNN with the best classification rates of 96.5%.

Development of a simple method for classifying the degree of importance of components in nuclear power plants using probabilistic analysis technique

International Nuclear Information System (INIS)

Shimada, Yoshio; Miyazaki, Takamasa

2006-01-01

In order to analyze large amounts of trouble information of overseas nuclear power plants, it is necessary to select information that is significant in terms of both safety and reliability. In this research, a method of efficiently and simply classifying degrees of importance of components in terms of safety and reliability while paying attention to root-cause components appearing in the information was developed. Regarding safety, the reactor core damage frequency (CDF), which is used in the probabilistic analysis of a reactor, was used. Regarding reliability, the automatic plant trip probability (APTP), which is used in the probabilistic analysis of automatic reactor trips, was used. These two aspects were reflected in the development of criteria for classifying degrees of importance of components. By applying these criteria, a method of quantitatively and simply judging the significance of trouble information of overseas nuclear power plants was developed. (author)

Spectroscopic vector analysis for fast pattern quality monitoring

Science.gov (United States)

Sohn, Younghoon; Ryu, Sungyoon; Lee, Chihoon; Yang, Yusin

2018-03-01

In semiconductor industry, fast and effective measurement of pattern variation has been key challenge for assuring massproduct quality. Pattern measurement techniques such as conventional CD-SEMs or Optical CDs have been extensively used, but these techniques are increasingly limited in terms of measurement throughput and time spent in modeling. In this paper we propose time effective pattern monitoring method through the direct spectrum-based approach. In this technique, a wavelength band sensitive to a specific pattern change is selected from spectroscopic ellipsometry signal scattered by pattern to be measured, and the amplitude and phase variation in the wavelength band are analyzed as a measurement index of the pattern change. This pattern change measurement technique is applied to several process steps and verified its applicability. Due to its fast and simple analysis, the methods can be adapted to the massive process variation monitoring maximizing measurement throughput.

Classifying features in CT imagery: accuracy for some single- and multiple-species classifiers

Science.gov (United States)

Daniel L. Schmoldt; Jing He; A. Lynn Abbott

1998-01-01

Our current approach to automatically label features in CT images of hardwood logs classifies each pixel of an image individually. These feature classifiers use a back-propagation artificial neural network (ANN) and feature vectors that include a small, local neighborhood of pixels and the distance of the target pixel to the center of the log. Initially, this type of...

Wavelet classifier used for diagnosing shock absorbers in cars

Directory of Open Access Journals (Sweden)

Janusz GARDULSKI

2007-01-01

Full Text Available The paper discusses some commonly used methods of hydraulic absorbertesting. Disadvantages of the methods are described. A vibro-acoustic method is presented and recommended for practical use on existing test rigs. The method is based on continuous wavelet analysis combined with neural classifier and 25-neuron, one-way, three-layer back propagation network. The analysis satisfies the intended aim.

Quantitative analysis of crystalline pharmaceuticals in tablets by pattern-fitting procedure using X-ray diffraction pattern.

Science.gov (United States)

Takehira, Rieko; Momose, Yasunori; Yamamura, Shigeo

2010-10-15

A pattern-fitting procedure using an X-ray diffraction pattern was applied to the quantitative analysis of binary system of crystalline pharmaceuticals in tablets. Orthorhombic crystals of isoniazid (INH) and mannitol (MAN) were used for the analysis. Tablets were prepared under various compression pressures using a direct compression method with various compositions of INH and MAN. Assuming that X-ray diffraction pattern of INH-MAN system consists of diffraction intensities from respective crystals, observed diffraction intensities were fitted to analytic expression based on X-ray diffraction theory and separated into two intensities from INH and MAN crystals by a nonlinear least-squares procedure. After separation, the contents of INH were determined by using the optimized normalization constants for INH and MAN. The correction parameter including all the factors that are beyond experimental control was required for quantitative analysis without calibration curve. The pattern-fitting procedure made it possible to determine crystalline phases in the range of 10-90% (w/w) of the INH contents. Further, certain characteristics of the crystals in the tablets, such as the preferred orientation, size of crystallite, and lattice disorder were determined simultaneously. This method can be adopted to analyze compounds whose crystal structures are known. It is a potentially powerful tool for the quantitative phase analysis and characterization of crystals in tablets and powders using X-ray diffraction patterns. Copyright 2010 Elsevier B.V. All rights reserved.

The cell pattern correction through design-based metrology

Science.gov (United States)

Kim, Yonghyeon; Lee, Kweonjae; Chang, Jinman; Kim, Taeheon; Han, Daehan; Lee, Kyusun; Hong, Aeran; Kang, Jinyoung; Choi, Bumjin; Lee, Joosung; Yeom, Kyehee; Lee, Jooyoung; Hong, Hyeongsun; Lee, Kyupil; Jin, Gyoyoung

2015-03-01

Starting with the sub 2Xnm node, the process window becomes smaller and tighter than before. Pattern related error budget is required for accurate critical-dimension control of Cell layers. Therefore, lithography has been faced with its various difficulties, such as weird distribution, overlay error, patterning difficulty etc. The distribution of cell pattern and overlay management are the most important factors in DRAM field. We had been experiencing that the fatal risk is caused by the patterns located in the tail of the distribution. The overlay also induces the various defect sources and misalignment issues. Even though we knew that these elements are important, we could not classify the defect type of Cell patterns. Because there is no way to gather massive small pattern CD samples in cell unit block and to compare layout with cell patterns by the CD-SEM. The CD- SEM is used in order to gather these data through high resolution, but CD-SEM takes long time to inspect and extract data because it measures the small FOV. (Field Of View) However, the NGR(E-beam tool) provides high speed with large FOV and high resolution. Also, it's possible to measure an accurate overlay between the target layout and cell patterns because they provide DBM. (Design Based Metrology) By using massive measured data, we extract the result that it is persuasive by applying the various analysis techniques, as cell distribution and defects, the pattern overlay error correction etc. We introduce how to correct cell pattern, by using the DBM measurement, and new analysis methods.

Analysis of blood flow patterns in aortic aneurysm by cine magnetic resonance imaging

International Nuclear Information System (INIS)

Matsuoka, Hiroshi

1993-01-01

Cine MRI (0.5 T) using rephased gradient echo technique was performed to study the patterns of blood flow in the aortic aneurysm of 16 patients with aortic aneurysm, and the data were compared with those of 5 healthy volunteers. In the transaxial section, the blood flow in normal aorta appeared as homogeneous high intensity during systole. On the other hand, the blood flow in the aneurysm appeared as inhomogeneous flow enhancement with flow void. In the sagittal scan, the homogeneous flow enhancement in a normal aorta was also observed during systole and its apex of flow enhancement was 'taper'. The blood flow patterns in the aneurysm were classified as 'irregular', 'zonal', 'eddy', and 'obscure' depending on the contrast of flow enhancement and flow void. Their apexes were 'taper' or 'round'. The blood flow patterns in the aneurysm were related to the size of aneurysm. In patients with a large size 'aneurysm, their flow patterns were 'eddy' or 'obscure' and the flow enhancement was 'round'. On the other hand, in patients with a small size aneurysm, their flow patterns were 'irregular' or 'zonal', and their flow enhancement was 'taper'. Though the exact mechanism of abnormal flow patterns in an aortic aneurysm remains to be determined, cine MRI gives helpful informations in assessing blood flow dynamics in the aneurysm. (author)

Sensing Urban Land-Use Patterns by Integrating Google Tensorflow and Scene-Classification Models

Science.gov (United States)

Yao, Y.; Liang, H.; Li, X.; Zhang, J.; He, J.

2017-09-01

With the rapid progress of China's urbanization, research on the automatic detection of land-use patterns in Chinese cities is of substantial importance. Deep learning is an effective method to extract image features. To take advantage of the deep-learning method in detecting urban land-use patterns, we applied a transfer-learning-based remote-sensing image approach to extract and classify features. Using the Google Tensorflow framework, a powerful convolution neural network (CNN) library was created. First, the transferred model was previously trained on ImageNet, one of the largest object-image data sets, to fully develop the model's ability to generate feature vectors of standard remote-sensing land-cover data sets (UC Merced and WHU-SIRI). Then, a random-forest-based classifier was constructed and trained on these generated vectors to classify the actual urban land-use pattern on the scale of traffic analysis zones (TAZs). To avoid the multi-scale effect of remote-sensing imagery, a large random patch (LRP) method was used. The proposed method could efficiently obtain acceptable accuracy (OA = 0.794, Kappa = 0.737) for the study area. In addition, the results show that the proposed method can effectively overcome the multi-scale effect that occurs in urban land-use classification at the irregular land-parcel level. The proposed method can help planners monitor dynamic urban land use and evaluate the impact of urban-planning schemes.

LCC: Light Curves Classifier

Science.gov (United States)

Vo, Martin

2017-08-01

Light Curves Classifier uses data mining and machine learning to obtain and classify desired objects. This task can be accomplished by attributes of light curves or any time series, including shapes, histograms, or variograms, or by other available information about the inspected objects, such as color indices, temperatures, and abundances. After specifying features which describe the objects to be searched, the software trains on a given training sample, and can then be used for unsupervised clustering for visualizing the natural separation of the sample. The package can be also used for automatic tuning parameters of used methods (for example, number of hidden neurons or binning ratio). Trained classifiers can be used for filtering outputs from astronomical databases or data stored locally. The Light Curve Classifier can also be used for simple downloading of light curves and all available information of queried stars. It natively can connect to OgleII, OgleIII, ASAS, CoRoT, Kepler, Catalina and MACHO, and new connectors or descriptors can be implemented. In addition to direct usage of the package and command line UI, the program can be used through a web interface. Users can create jobs for ”training” methods on given objects, querying databases and filtering outputs by trained filters. Preimplemented descriptors, classifier and connectors can be picked by simple clicks and their parameters can be tuned by giving ranges of these values. All combinations are then calculated and the best one is used for creating the filter. Natural separation of the data can be visualized by unsupervised clustering.

15 CFR 4.8 - Classified Information.

Science.gov (United States)

2010-01-01

... 15 Commerce and Foreign Trade 1 2010-01-01 2010-01-01 false Classified Information. 4.8 Section 4... INFORMATION Freedom of Information Act § 4.8 Classified Information. In processing a request for information..., the information shall be reviewed to determine whether it should remain classified. Ordinarily the...

Pattern Recognition Approaches for Breast Cancer DCE-MRI Classification: A Systematic Review.

Science.gov (United States)

Fusco, Roberta; Sansone, Mario; Filice, Salvatore; Carone, Guglielmo; Amato, Daniela Maria; Sansone, Carlo; Petrillo, Antonella

2016-01-01

We performed a systematic review of several pattern analysis approaches for classifying breast lesions using dynamic, morphological, and textural features in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Several machine learning approaches, namely artificial neural networks (ANN), support vector machines (SVM), linear discriminant analysis (LDA), tree-based classifiers (TC), and Bayesian classifiers (BC), and features used for classification are described. The findings of a systematic review of 26 studies are presented. The sensitivity and specificity are respectively 91 and 83 % for ANN, 85 and 82 % for SVM, 96 and 85 % for LDA, 92 and 87 % for TC, and 82 and 85 % for BC. The sensitivity and specificity are respectively 82 and 74 % for dynamic features, 93 and 60 % for morphological features, 88 and 81 % for textural features, 95 and 86 % for a combination of dynamic and morphological features, and 88 and 84 % for a combination of dynamic, morphological, and other features. LDA and TC have the best performance. A combination of dynamic and morphological features gives the best performance.

Novelty Detection Classifiers in Weed Mapping: Silybum marianum Detection on UAV Multispectral Images.

Science.gov (United States)

Alexandridis, Thomas K; Tamouridou, Afroditi Alexandra; Pantazi, Xanthoula Eirini; Lagopodi, Anastasia L; Kashefi, Javid; Ovakoglou, Georgios; Polychronos, Vassilios; Moshou, Dimitrios

2017-09-01

In the present study, the detection and mapping of Silybum marianum (L.) Gaertn. weed using novelty detection classifiers is reported. A multispectral camera (green-red-NIR) on board a fixed wing unmanned aerial vehicle (UAV) was employed for obtaining high-resolution images. Four novelty detection classifiers were used to identify S. marianum between other vegetation in a field. The classifiers were One Class Support Vector Machine (OC-SVM), One Class Self-Organizing Maps (OC-SOM), Autoencoders and One Class Principal Component Analysis (OC-PCA). As input features to the novelty detection classifiers, the three spectral bands and texture were used. The S. marianum identification accuracy using OC-SVM reached an overall accuracy of 96%. The results show the feasibility of effective S. marianum mapping by means of novelty detection classifiers acting on multispectral UAV imagery.

Identification of Design Work Patterns by Retrospective Analysis of Work Sheets

DEFF Research Database (Denmark)

Hansen, Claus Thorp

1999-01-01

project is carried out where we seek to identify design work patterns by retrospective analysis of documentation created during design projects.An elements to satisfy the wish for an efficient design process could be to identify work patterns applied by engineering designers, evaluate these patterns...... with respect to their efficiency, and reuse the most efficient in future projects. Thus, the objective of this research is to analyse design projects in order to identify the work patterns applied. Based on an evaluation of identified work patterns we expect a recommendation of work patterns supporting...... an efficient design process can be established.In this paper we describe the analysis method, and present observations from analyses of three projects....

High-resolution computed tomography to differentiate chronic diffuse interstitial lung diseases with predominant ground-glass pattern using logical analysis of data

International Nuclear Information System (INIS)

Martin, Sophie Grivaud; Brauner, Michel W.; Rety, Frederique; Kronek, Louis-Philippe; Brauner, Nadia; Valeyre, Dominique; Nunes, Hilario; Brillet, Pierre-Yves

2010-01-01

We evaluated the performance of high-resolution computed tomography (HRCT) to differentiate chronic diffuse interstitial lung diseases (CDILD) with predominant ground-glass pattern by using logical analysis of data (LAD). A total of 162 patients were classified into seven categories: sarcoidosis (n = 38), connective tissue disease (n = 32), hypersensitivity pneumonitis (n = 18), drug-induced lung disease (n = 15), alveolar proteinosis (n = 12), idiopathic non-specific interstitial pneumonia (n = 10) and miscellaneous (n = 37). First, 40 CT attributes were investigated by the LAD to build up patterns characterising a category. From the association of patterns, LAD determined models specific to each CDILD. Second, data were recomputed by adding eight clinical attributes to the analysis. The 20 x 5 cross-folding method was used for validation. Models could be individualised for sarcoidosis, hypersensitivity pneumonitis, connective tissue disease and alveolar proteinosis. An additional model was individualised for drug-induced lung disease by adding clinical data. No model was demonstrated for idiopathic non-specific interstitial pneumonia and the miscellaneous category. The results showed that HRCT had a good sensitivity (≥64%) and specificity (≥78%) and a high negative predictive value (≥93%) for diseases with a model. Higher sensitivity (≥78%) and specificity (≥89%) were achieved by adding clinical data. The diagnostic performance of HRCT is high and can be increased by adding clinical data. (orig.)

Classifying oxidative stress by F2-isoprostane levels across human diseases: A meta-analysis.

Science.gov (United States)

van 't Erve, Thomas J; Kadiiska, Maria B; London, Stephanie J; Mason, Ronald P

2017-08-01

The notion that oxidative stress plays a role in virtually every human disease and environmental exposure has become ingrained in everyday knowledge. However, mounting evidence regarding the lack of specificity of biomarkers traditionally used as indicators of oxidative stress in human disease and exposures now necessitates re-evaluation. To prioritize these re-evaluations, published literature was comprehensively analyzed in a meta-analysis to quantitatively classify the levels of systemic oxidative damage across human disease and in response to environmental exposures. In this meta-analysis, the F 2 -isoprostane, 8-iso-PGF 2α , was specifically chosen as the representative marker of oxidative damage. To combine published values across measurement methods and specimens, the standardized mean differences (Hedges' g) in 8-iso-PGF 2α levels between affected and control populations were calculated. The meta-analysis resulted in a classification of oxidative damage levels as measured by 8-iso-PGF 2α across 50 human health outcomes and exposures from 242 distinct publications. Relatively small increases in 8-iso-PGF 2α levels (ganalysis of published data. This analysis provides knowledge on the true involvement of oxidative damage across human health outcomes as well as utilizes past research to prioritize those conditions requiring further scrutiny on the mechanisms of biomarker generation. Copyright © 2017. Published by Elsevier B.V.

Control-group feature normalization for multivariate pattern analysis of structural MRI data using the support vector machine.

Science.gov (United States)

Linn, Kristin A; Gaonkar, Bilwaj; Satterthwaite, Theodore D; Doshi, Jimit; Davatzikos, Christos; Shinohara, Russell T

2016-05-15

Normalization of feature vector values is a common practice in machine learning. Generally, each feature value is standardized to the unit hypercube or by normalizing to zero mean and unit variance. Classification decisions based on support vector machines (SVMs) or by other methods are sensitive to the specific normalization used on the features. In the context of multivariate pattern analysis using neuroimaging data, standardization effectively up- and down-weights features based on their individual variability. Since the standard approach uses the entire data set to guide the normalization, it utilizes the total variability of these features. This total variation is inevitably dependent on the amount of marginal separation between groups. Thus, such a normalization may attenuate the separability of the data in high dimensional space. In this work we propose an alternate approach that uses an estimate of the control-group standard deviation to normalize features before training. We study our proposed approach in the context of group classification using structural MRI data. We show that control-based normalization leads to better reproducibility of estimated multivariate disease patterns and improves the classifier performance in many cases. Copyright © 2016 Elsevier Inc. All rights reserved.

Using quantitative image analysis to classify axillary lymph nodes on breast MRI: A new application for the Z 0011 Era

Energy Technology Data Exchange (ETDEWEB)

Schacht, David V., E-mail: dschacht@radiology.bsd.uchicago.edu; Drukker, Karen, E-mail: kdrukker@uchicago.edu; Pak, Iris, E-mail: irisgpak@gmail.com; Abe, Hiroyuki, E-mail: habe@radiology.bsd.uchicago.edu; Giger, Maryellen L., E-mail: m-giger@uchicago.edu

2015-03-15

Highlights: •Quantitative image analysis showed promise in evaluating axillary lymph nodes. •13 of 28 features performed better than guessing at metastatic status. •When all features were used in together, a considerably higher AUC was obtained. -- Abstract: Purpose: To assess the performance of computer extracted feature analysis of dynamic contrast enhanced (DCE) magnetic resonance images (MRI) of axillary lymph nodes. To determine which quantitative features best predict nodal metastasis. Methods: This institutional board-approved HIPAA compliant study, in which informed patient consent was waived, collected enhanced T1 images of the axilla from patients with breast cancer. Lesion segmentation and feature analysis were performed on 192 nodes using a laboratory-developed quantitative image analysis (QIA) workstation. The importance of 28 features were assessed. Classification used the features as input to a neural net classifier in a leave-one-case-out cross-validation and evaluated with receiver operating characteristic (ROC) analysis. Results: The area under the ROC curve (AUC) values for features in the task of distinguishing between positive and negative nodes ranged from just over 0.50 to 0.70. Five features yielded AUCs greater than 0.65: two morphological and three textural features. In cross-validation, the neural net classifier obtained an AUC of 0.88 (SE 0.03) for the task of distinguishing between positive and negative nodes. Conclusion: QIA of DCE MRI demonstrated promising performance in discriminating between positive and negative axillary nodes.

Two dimensional Fourier transform methods for fringe pattern analysis

Science.gov (United States)

Sciammarella, C. A.; Bhat, G.

An overview of the use of FFTs for fringe pattern analysis is presented, with emphasis on fringe patterns containing displacement information. The techniques are illustrated via analysis of the displacement and strain distributions in the direction perpendicular to the loading, in a disk under diametral compression. The experimental strain distribution is compared to the theoretical, and the agreement is found to be excellent in regions where the elasticity solution models well the actual problem.

Feature weighting using particle swarm optimization for learning vector quantization classifier

Science.gov (United States)

Dongoran, A.; Rahmadani, S.; Zarlis, M.; Zakarias

2018-03-01

This paper discusses and proposes a method of feature weighting in classification assignments on competitive learning artificial neural network LVQ. The weighting feature method is the search for the weight of an attribute using the PSO so as to give effect to the resulting output. This method is then applied to the LVQ-Classifier and tested on the 3 datasets obtained from the UCI Machine Learning repository. Then an accuracy analysis will be generated by two approaches. The first approach using LVQ1, referred to as LVQ-Classifier and the second approach referred to as PSOFW-LVQ, is a proposed model. The result shows that the PSO algorithm is capable of finding attribute weights that increase LVQ-classifier accuracy.

A Kinematic Method for Footstrike Pattern Detection in Barefoot and Shod Runners

OpenAIRE

Altman, Allison R.; Davis, Irene S.

2011-01-01

Footstrike patterns during running can be classified discretely into a rearfoot strike, midfoot strike and forefoot strike by visual observation. However, the footstrike pattern can also be classified on a continuum, ranging from 0–100% (extreme rearfoot to extreme forefoot) using the strike index, a measure requiring force plate data. When force data are not available, an alternative method to quantify the strike pattern must be used. The purpose of this paper was to quantify the continuum o...

Fingerprint prediction using classifier ensembles

CSIR Research Space (South Africa)

Molale, P

2011-11-01

Full Text Available ); logistic discrimination (LgD), k-nearest neighbour (k-NN), artificial neural network (ANN), association rules (AR) decision tree (DT), naive Bayes classifier (NBC) and the support vector machine (SVM). The performance of several multiple classifier systems...

Personality patterns predict the risk of antisocial behavior in Spanish-speaking adolescents.

Science.gov (United States)

Alcázar-Córcoles, Miguel A; Verdejo-García, Antonio; Bouso-Sáiz, José C; Revuelta-Menéndez, Javier; Ramírez-Lira, Ezequiel

2017-05-01

There is a renewed interest in incorporating personality variables in criminology theories in order to build models able to integrate personality variables and biological factors with psychosocial and sociocultural factors. The aim of this article is the assessment of personality dimensions that contribute to the prediction of antisocial behavior in adolescents. For this purpose, a sample of adolescents from El Salvador, Mexico, and Spain was obtained. The sample consisted of 1035 participants with a mean age of 16.2. There were 450 adolescents from a forensic population (those who committed a crime) and 585 adolescents from the normal population (no crime committed). All of participants answered personality tests about neuroticism, extraversion, psychoticism, sensation seeking, impulsivity, and violence risk. Principal component analysis of the data identified two independent factors: (i) the disinhibited behavior pattern (PDC), formed by the dimensions of neuroticism, psychoticism, impulsivity and risk of violence; and (ii) the extrovert behavior pattern (PEC), formed by the dimensions of sensation risk and extraversion. Both patterns significantly contributed to the prediction of adolescent antisocial behavior in a logistic regression model which properly classifies a global percentage of 81.9%, 86.8% for non-offense and 72.5% for offense behavior. The classification power of regression equations allows making very satisfactory predictions about adolescent offense commission. Educational level has been classified as a protective factor, while age and gender (male) have been classified as risk factors.

Applying Learning Analytics to Explore the Effects of Motivation on Online Students' Reading Behavioral Patterns

Science.gov (United States)

Sun, Jerry Chih-Yuan; Lin, Che-Tsun; Chou, Chien

2018-01-01

This study aims to apply a sequential analysis to explore the effect of learning motivation on online reading behavioral patterns. The study's participants consisted of 160 graduate students who were classified into three group types: low reading duration with low motivation, low reading duration with high motivation, and high reading duration…

A Feature-Free 30-Disease Pathological Brain Detection System by Linear Regression Classifier.

Science.gov (United States)

Chen, Yi; Shao, Ying; Yan, Jie; Yuan, Ti-Fei; Qu, Yanwen; Lee, Elizabeth; Wang, Shuihua

2017-01-01

Alzheimer's disease patients are increasing rapidly every year. Scholars tend to use computer vision methods to develop automatic diagnosis system. (Background) In 2015, Gorji et al. proposed a novel method using pseudo Zernike moment. They tested four classifiers: learning vector quantization neural network, pattern recognition neural network trained by Levenberg-Marquardt, by resilient backpropagation, and by scaled conjugate gradient. This study presents an improved method by introducing a relatively new classifier-linear regression classification. Our method selects one axial slice from 3D brain image, and employed pseudo Zernike moment with maximum order of 15 to extract 256 features from each image. Finally, linear regression classification was harnessed as the classifier. The proposed approach obtains an accuracy of 97.51%, a sensitivity of 96.71%, and a specificity of 97.73%. Our method performs better than Gorji's approach and five other state-of-the-art approaches. Therefore, it can be used to detect Alzheimer's disease. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Pattern Decomposition Method and a New Vegetation Index for Hyper-Multispectral Satellite Data Analysis

Science.gov (United States)

Muramatsu, K.; Furumi, S.; Hayashi, A.; Shiono, Y.; Ono, A.; Fujiwara, N.; Daigo, M.; Ochiai, F.

We have developed the ``pattern decomposition method'' based on linear spectral mixing of ground objects for n-dimensional satellite data. In this method, spectral response patterns for each pixel in an image are decomposed into three components using three standard spectral shape patterns determined from the image data. Applying this method to AMSS (Airborne Multi-Spectral Scanner) data, eighteen-dimensional data are successfully transformed into three-dimensional data. Using the three components, we have developed a new vegetation index in which all the multispectral data are reflected. We consider that the index should be linear to the amount of vegetation and vegetation vigor. To validate the index, its relations to vegetation types, vegetation cover ratio, and chlorophyll contents of a leaf were studied using spectral reflectance data measured in the field with a spectrometer. The index was sensitive to vegetation types and vegetation vigor. This method and index are very useful for assessment of vegetation vigor, classifying land cover types and monitoring vegetation changes

Lifestyle Patterns and Weight Status in Spanish Adults: The ANIBES Study

Directory of Open Access Journals (Sweden)

Carmen Pérez-Rodrigo

2017-06-01

Full Text Available Limited knowledge is available on lifestyle patterns in Spanish adults. We investigated dietary patterns and possible meaningful clustering of physical activity, sedentary behavior, sleep time, and smoking in Spanish adults aged 18–64 years and their association with obesity. Analysis was based on a subsample (n = 1617 of the cross-sectional ANIBES study in Spain. We performed exploratory factor analysis and subsequent cluster analysis of dietary patterns, physical activity, sedentary behaviors, sleep time, and smoking. Logistic regression analysis was used to explore the association between the cluster solutions and obesity. Factor analysis identified four dietary patterns, “Traditional DP”, “Mediterranean DP”, “Snack DP” and “Dairy-sweet DP”. Dietary patterns, physical activity behaviors, sedentary behaviors, sleep time, and smoking in Spanish adults aggregated into three different clusters of lifestyle patterns: “Mixed diet-physically active-low sedentary lifestyle pattern”, “Not poor diet-low physical activity-low sedentary lifestyle pattern” and “Poor diet-low physical activity-sedentary lifestyle pattern”. A higher proportion of people aged 18–30 years was classified into the “Poor diet-low physical activity-sedentary lifestyle pattern”. The prevalence odds ratio for obesity in men in the “Mixed diet-physically active-low sedentary lifestyle pattern” was significantly lower compared to those in the “Poor diet-low physical activity-sedentary lifestyle pattern”. Those behavior patterns are helpful to identify specific issues in population subgroups and inform intervention strategies. The findings in this study underline the importance of designing and implementing interventions that address multiple health risk practices, considering lifestyle patterns and associated determinants.

Pain patterns during adolescence can be grouped into four pain classes with distinct profiles

DEFF Research Database (Denmark)

Holden, Sinead; Rathleff, Michael Skovdal; Roos, E. M.

2018-01-01

L (assessed by Euro-QoL 5D-3L). Latent class analysis was used to classify spatial pain patterns, based on the pain sites. The analysis included 2953 adolescents. RESULTS: Four classes were identified as follows: (1) little or no pain (63% of adolescents), (2) majority lower extremity pain (10%), (3) multi......-site bodily pain (22%) and (4) head and stomach pain (3%). The lower extremity multi-site pain group reported highest weekly sports participation (p ....001). Males were more likely to belong to the little or no pain class, whereas females were more likely to belong to the multi-site bodily pain class. CONCLUSIONS: Latent class analysis identified distinct classes of pain patterns in adolescents, characterized by sex, differences in HRQoL and sports...

Classifying Sluice Occurrences in Dialogue

DEFF Research Database (Denmark)

Baird, Austin; Hamza, Anissa; Hardt, Daniel

2018-01-01

perform manual annotation with acceptable inter-coder agreement. We build classifier models with Decision Trees and Naive Bayes, with accuracy of 67%. We deploy a classifier to automatically classify sluice occurrences in OpenSubtitles, resulting in a corpus with 1.7 million occurrences. This will support....... Despite this, the corpus can be of great use in research on sluicing and development of systems, and we are making the corpus freely available on request. Furthermore, we are in the process of improving the accuracy of sluice identification and annotation for the purpose of created a subsequent version...

Data analysis and pattern recognition in multiple databases

CERN Document Server

Adhikari, Animesh; Pedrycz, Witold

2014-01-01

Pattern recognition in data is a well known classical problem that falls under the ambit of data analysis. As we need to handle different data, the nature of patterns, their recognition and the types of data analyses are bound to change. Since the number of data collection channels increases in the recent time and becomes more diversified, many real-world data mining tasks can easily acquire multiple databases from various sources. In these cases, data mining becomes more challenging for several essential reasons. We may encounter sensitive data originating from different sources - those cannot be amalgamated. Even if we are allowed to place different data together, we are certainly not able to analyse them when local identities of patterns are required to be retained. Thus, pattern recognition in multiple databases gives rise to a suite of new, challenging problems different from those encountered before. Association rule mining, global pattern discovery, and mining patterns of select items provide different...

General and Local: Averaged k-Dependence Bayesian Classifiers

Directory of Open Access Journals (Sweden)

Limin Wang

2015-06-01

Full Text Available The inference of a general Bayesian network has been shown to be an NP-hard problem, even for approximate solutions. Although k-dependence Bayesian (KDB classifier can construct at arbitrary points (values of k along the attribute dependence spectrum, it cannot identify the changes of interdependencies when attributes take different values. Local KDB, which learns in the framework of KDB, is proposed in this study to describe the local dependencies implicated in each test instance. Based on the analysis of functional dependencies, substitution-elimination resolution, a new type of semi-naive Bayesian operation, is proposed to substitute or eliminate generalization to achieve accurate estimation of conditional probability distribution while reducing computational complexity. The final classifier, averaged k-dependence Bayesian (AKDB classifiers, will average the output of KDB and local KDB. Experimental results on the repository of machine learning databases from the University of California Irvine (UCI showed that AKDB has significant advantages in zero-one loss and bias relative to naive Bayes (NB, tree augmented naive Bayes (TAN, Averaged one-dependence estimators (AODE, and KDB. Moreover, KDB and local KDB show mutually complementary characteristics with respect to variance.

Entropy based classifier for cross-domain opinion mining

Directory of Open Access Journals (Sweden)

Jyoti S. Deshmukh

2018-01-01

Full Text Available In recent years, the growth of social network has increased the interest of people in analyzing reviews and opinions for products before they buy them. Consequently, this has given rise to the domain adaptation as a prominent area of research in sentiment analysis. A classifier trained from one domain often gives poor results on data from another domain. Expression of sentiment is different in every domain. The labeling cost of each domain separately is very high as well as time consuming. Therefore, this study has proposed an approach that extracts and classifies opinion words from one domain called source domain and predicts opinion words of another domain called target domain using a semi-supervised approach, which combines modified maximum entropy and bipartite graph clustering. A comparison of opinion classification on reviews on four different product domains is presented. The results demonstrate that the proposed method performs relatively well in comparison to the other methods. Comparison of SentiWordNet of domain-specific and domain-independent words reveals that on an average 72.6% and 88.4% words, respectively, are correctly classified.

ELM BASED CAD SYSTEM TO CLASSIFY MAMMOGRAMS BY THE COMBINATION OF CLBP AND CONTOURLET

Directory of Open Access Journals (Sweden)

S Venkatalakshmi

2017-05-01

Full Text Available Breast cancer is a serious life threat to the womanhood, worldwide. Mammography is the promising screening tool, which can show the abnormality being detected. However, the physicians find it difficult to detect the affected regions, as the size of microcalcifications is very small. Hence it would be better, if a CAD system can accompany the physician in detecting the malicious regions. Taking this as a challenge, this paper presents a CAD system for mammogram classification which is proven to be accurate and reliable. The entire work is decomposed into four different stages and the outcome of a phase is passed as the input of the following phase. Initially, the mammogram is pre-processed by adaptive median filter and the segmentation is done by GHFCM. The features are extracted by combining the texture feature descriptors Completed Local Binary Pattern (CLBP and contourlet to frame the feature sets. In the training phase, Extreme Learning Machine (ELM is trained with the feature sets. During the testing phase, the ELM can classify between normal, malignant and benign type of cancer. The performance of the proposed approach is analysed by varying the classifier, feature extractors and parameters of the feature extractor. From the experimental analysis, it is evident that the proposed work outperforms the analogous techniques in terms of accuracy, sensitivity and specificity.

Optimizing pattern recognition-based control for partial-hand prosthesis application.

Science.gov (United States)

Earley, Eric J; Adewuyi, Adenike A; Hargrove, Levi J

2014-01-01

Partial-hand amputees often retain good residual wrist motion, which is essential for functional activities involving use of the hand. Thus, a crucial design criterion for a myoelectric, partial-hand prosthesis control scheme is that it allows the user to retain residual wrist motion. Pattern recognition (PR) of electromyographic (EMG) signals is a well-studied method of controlling myoelectric prostheses. However, wrist motion degrades a PR system's ability to correctly predict hand-grasp patterns. We studied the effects of (1) window length and number of hand-grasps, (2) static and dynamic wrist motion, and (3) EMG muscle source on the ability of a PR-based control scheme to classify functional hand-grasp patterns. Our results show that training PR classifiers with both extrinsic and intrinsic muscle EMG yields a lower error rate than training with either group by itself (pgrasps available to the classifier significantly decrease classification error (pgrasp.

Classifiers based on optimal decision rules

KAUST Repository

Amin, Talha

2013-11-25

Based on dynamic programming approach we design algorithms for sequential optimization of exact and approximate decision rules relative to the length and coverage [3, 4]. In this paper, we use optimal rules to construct classifiers, and study two questions: (i) which rules are better from the point of view of classification-exact or approximate; and (ii) which order of optimization gives better results of classifier work: length, length+coverage, coverage, or coverage+length. Experimental results show that, on average, classifiers based on exact rules are better than classifiers based on approximate rules, and sequential optimization (length+coverage or coverage+length) is better than the ordinary optimization (length or coverage).

Classifiers based on optimal decision rules

KAUST Repository

Amin, Talha M.; Chikalov, Igor; Moshkov, Mikhail; Zielosko, Beata

2013-01-01

Based on dynamic programming approach we design algorithms for sequential optimization of exact and approximate decision rules relative to the length and coverage [3, 4]. In this paper, we use optimal rules to construct classifiers, and study two questions: (i) which rules are better from the point of view of classification-exact or approximate; and (ii) which order of optimization gives better results of classifier work: length, length+coverage, coverage, or coverage+length. Experimental results show that, on average, classifiers based on exact rules are better than classifiers based on approximate rules, and sequential optimization (length+coverage or coverage+length) is better than the ordinary optimization (length or coverage).

CASAnova: a multiclass support vector machine model for the classification of human sperm motility patterns.

Science.gov (United States)

Goodson, Summer G; White, Sarah; Stevans, Alicia M; Bhat, Sanjana; Kao, Chia-Yu; Jaworski, Scott; Marlowe, Tamara R; Kohlmeier, Martin; McMillan, Leonard; Zeisel, Steven H; O'Brien, Deborah A

2017-11-01

The ability to accurately monitor alterations in sperm motility is paramount to understanding multiple genetic and biochemical perturbations impacting normal fertilization. Computer-aided sperm analysis (CASA) of human sperm typically reports motile percentage and kinematic parameters at the population level, and uses kinematic gating methods to identify subpopulations such as progressive or hyperactivated sperm. The goal of this study was to develop an automated method that classifies all patterns of human sperm motility during in vitro capacitation following the removal of seminal plasma. We visually classified CASA tracks of 2817 sperm from 18 individuals and used a support vector machine-based decision tree to compute four hyperplanes that separate five classes based on their kinematic parameters. We then developed a web-based program, CASAnova, which applies these equations sequentially to assign a single classification to each motile sperm. Vigorous sperm are classified as progressive, intermediate, or hyperactivated, and nonvigorous sperm as slow or weakly motile. This program correctly classifies sperm motility into one of five classes with an overall accuracy of 89.9%. Application of CASAnova to capacitating sperm populations showed a shift from predominantly linear patterns of motility at initial time points to more vigorous patterns, including hyperactivated motility, as capacitation proceeds. Both intermediate and hyperactivated motility patterns were largely eliminated when sperm were incubated in noncapacitating medium, demonstrating the sensitivity of this method. The five CASAnova classifications are distinctive and reflect kinetic parameters of washed human sperm, providing an accurate, quantitative, and high-throughput method for monitoring alterations in motility. © The Authors 2017. Published by Oxford University Press on behalf of Society for the Study of Reproduction. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Selectivity in Genetic Association with Sub-classified Migraine in Women

Science.gov (United States)

Chasman, Daniel I.; Anttila, Verneri; Buring, Julie E.; Ridker, Paul M.; Schürks, Markus; Kurth, Tobias

2014-01-01

Migraine can be sub-classified not only according to presence of migraine aura (MA) or absence of migraine aura (MO), but also by additional features accompanying migraine attacks, e.g. photophobia, phonophobia, nausea, etc. all of which are formally recognized by the International Classification of Headache Disorders. It remains unclear how aura status and the other migraine features may be related to underlying migraine pathophysiology. Recent genome-wide association studies (GWAS) have identified 12 independent loci at which single nucleotide polymorphisms (SNPs) are associated with migraine. Using a likelihood framework, we explored the selective association of these SNPs with migraine, sub-classified according to aura status and the other features in a large population-based cohort of women including 3,003 active migraineurs and 18,108 free of migraine. Five loci met stringent significance for association with migraine, among which four were selective for sub-classified migraine, including rs11172113 (LRP1) for MO. The number of loci associated with migraine increased to 11 at suggestive significance thresholds, including five additional selective associations for MO but none for MA. No two SNPs showed similar patterns of selective association with migraine characteristics. At one extreme, SNPs rs6790925 (near TGFBR2) and rs2274316 (MEF2D) were not associated with migraine overall, MA, or MO but were selective for migraine sub-classified by the presence of one or more of the additional migraine features. In contrast, SNP rs7577262 (TRPM8) was associated with migraine overall and showed little or no selectivity for any of the migraine characteristics. The results emphasize the multivalent nature of migraine pathophysiology and suggest that a complete understanding of the genetic influence on migraine may benefit from analyses that stratify migraine according to both aura status and the additional diagnostic features used for clinical characterization of

Deconstructing Cross-Entropy for Probabilistic Binary Classifiers

Directory of Open Access Journals (Sweden)

Daniel Ramos

2018-03-01

Full Text Available In this work, we analyze the cross-entropy function, widely used in classifiers both as a performance measure and as an optimization objective. We contextualize cross-entropy in the light of Bayesian decision theory, the formal probabilistic framework for making decisions, and we thoroughly analyze its motivation, meaning and interpretation from an information-theoretical point of view. In this sense, this article presents several contributions: First, we explicitly analyze the contribution to cross-entropy of (i prior knowledge; and (ii the value of the features in the form of a likelihood ratio. Second, we introduce a decomposition of cross-entropy into two components: discrimination and calibration. This decomposition enables the measurement of different performance aspects of a classifier in a more precise way; and justifies previously reported strategies to obtain reliable probabilities by means of the calibration of the output of a discriminating classifier. Third, we give different information-theoretical interpretations of cross-entropy, which can be useful in different application scenarios, and which are related to the concept of reference probabilities. Fourth, we present an analysis tool, the Empirical Cross-Entropy (ECE plot, a compact representation of cross-entropy and its aforementioned decomposition. We show the power of ECE plots, as compared to other classical performance representations, in two diverse experimental examples: a speaker verification system, and a forensic case where some glass findings are present.

Reactor noise analysis by statistical pattern recognition methods

International Nuclear Information System (INIS)

Howington, L.C.; Gonzalez, R.C.

1976-01-01

A multivariate statistical pattern recognition system for reactor noise analysis is presented. The basis of the system is a transformation for decoupling correlated variables and algorithms for inferring probability density functions. The system is adaptable to a variety of statistical properties of the data, and it has learning, tracking, updating, and data compacting capabilities. System design emphasizes control of the false-alarm rate. Its abilities to learn normal patterns, to recognize deviations from these patterns, and to reduce the dimensionality of data with minimum error were evaluated by experiments at the Oak Ridge National Laboratory (ORNL) High-Flux Isotope Reactor. Power perturbations of less than 0.1 percent of the mean value in selected frequency ranges were detected by the pattern recognition system

Explorative data analysis of two-dimensional electrophoresis gels

DEFF Research Database (Denmark)

Schultz, J.; Gottlieb, D.M.; Petersen, Marianne Kjerstine

2004-01-01

of gels is presented. First, an approach is demonstrated in which no prior knowledge of the separated proteins is used. Alignment of the gels followed by a simple transformation of data makes it possible to analyze the gels in an automated explorative manner by principal component analysis, to determine......Methods for classification of two-dimensional (2-DE) electrophoresis gels based on multivariate data analysis are demonstrated. Two-dimensional gels of ten wheat varieties are analyzed and it is demonstrated how to classify the wheat varieties in two qualities and a method for initial screening...... if the gels should be further analyzed. A more detailed approach is done by analyzing spot volume lists by principal components analysis and partial least square regression. The use of spot volume data offers a mean to investigate the spot pattern and link the classified protein patterns to distinct spots...

Substance Use Patterns Among Adolescents in Europe: A Latent Class Analysis.

Science.gov (United States)

Göbel, Kristin; Scheithauer, Herbert; Bräker, Astrid-Britta; Jonkman, Harrie; Soellner, Renate

2016-07-28

Several researchers have investigated substance use patterns using a latent class analysis; however, hardly no studies exist on substance use patterns across countries. Adolescent substance use patterns, demographic factors, and international differences in the prevalence of substance use patterns were explored. Data from 25 European countries were used to identify patterns of adolescent (12-16 years, 50.6% female) substance use (N = 33,566). Latent class analysis revealed four substance use classes: nonusers (68%), low-alcohol users (recent use of beer, wine, and alcopops; 16.1%), alcohol users (recent use of alcohol and lifetime use of marijuana; 11.2%), and polysubstance users (recent use of alcohol, marijuana, and other illicit drugs; 4.7%). Results support a general pattern of adolescent substance use across all countries; however, the prevalence rates of use patterns vary for each country. The present research provides insight into substance use patterns across Europe by using a large international adolescent sample, multidimensional indicators and a variety of substances. Substance use patterns are helpful when targeting policy and prevention strategies.

SENSING URBAN LAND-USE PATTERNS BY INTEGRATING GOOGLE TENSORFLOW AND SCENE-CLASSIFICATION MODELS

Directory of Open Access Journals (Sweden)

Y. Yao

2017-09-01

Full Text Available With the rapid progress of China’s urbanization, research on the automatic detection of land-use patterns in Chinese cities is of substantial importance. Deep learning is an effective method to extract image features. To take advantage of the deep-learning method in detecting urban land-use patterns, we applied a transfer-learning-based remote-sensing image approach to extract and classify features. Using the Google Tensorflow framework, a powerful convolution neural network (CNN library was created. First, the transferred model was previously trained on ImageNet, one of the largest object-image data sets, to fully develop the model’s ability to generate feature vectors of standard remote-sensing land-cover data sets (UC Merced and WHU-SIRI. Then, a random-forest-based classifier was constructed and trained on these generated vectors to classify the actual urban land-use pattern on the scale of traffic analysis zones (TAZs. To avoid the multi-scale effect of remote-sensing imagery, a large random patch (LRP method was used. The proposed method could efficiently obtain acceptable accuracy (OA = 0.794, Kappa = 0.737 for the study area. In addition, the results show that the proposed method can effectively overcome the multi-scale effect that occurs in urban land-use classification at the irregular land-parcel level. The proposed method can help planners monitor dynamic urban land use and evaluate the impact of urban-planning schemes.

Robust Framework to Combine Diverse Classifiers Assigning Distributed Confidence to Individual Classifiers at Class Level

Directory of Open Access Journals (Sweden)

Shehzad Khalid

2014-01-01

Full Text Available We have presented a classification framework that combines multiple heterogeneous classifiers in the presence of class label noise. An extension of m-Mediods based modeling is presented that generates model of various classes whilst identifying and filtering noisy training data. This noise free data is further used to learn model for other classifiers such as GMM and SVM. A weight learning method is then introduced to learn weights on each class for different classifiers to construct an ensemble. For this purpose, we applied genetic algorithm to search for an optimal weight vector on which classifier ensemble is expected to give the best accuracy. The proposed approach is evaluated on variety of real life datasets. It is also compared with existing standard ensemble techniques such as Adaboost, Bagging, and Random Subspace Methods. Experimental results show the superiority of proposed ensemble method as compared to its competitors, especially in the presence of class label noise and imbalance classes.

Modeling and Classification of Kinetic Patterns of Dynamic Metabolic Biomarkers in Physical Activity.

Directory of Open Access Journals (Sweden)

Marc Breit

2015-08-01

Full Text Available The objectives of this work were the classification of dynamic metabolic biomarker candidates and the modeling and characterization of kinetic regulatory mechanisms in human metabolism with response to external perturbations by physical activity. Longitudinal metabolic concentration data of 47 individuals from 4 different groups were examined, obtained from a cycle ergometry cohort study. In total, 110 metabolites (within the classes of acylcarnitines, amino acids, and sugars were measured through a targeted metabolomics approach, combining tandem mass spectrometry (MS/MS with the concept of stable isotope dilution (SID for metabolite quantitation. Biomarker candidates were selected by combined analysis of maximum fold changes (MFCs in concentrations and P-values resulting from statistical hypothesis testing. Characteristic kinetic signatures were identified through a mathematical modeling approach utilizing polynomial fitting. Modeled kinetic signatures were analyzed for groups with similar behavior by applying hierarchical cluster analysis. Kinetic shape templates were characterized, defining different forms of basic kinetic response patterns, such as sustained, early, late, and other forms, that can be used for metabolite classification. Acetylcarnitine (C2, showing a late response pattern and having the highest values in MFC and statistical significance, was classified as late marker and ranked as strong predictor (MFC = 1.97, P < 0.001. In the class of amino acids, highest values were shown for alanine (MFC = 1.42, P < 0.001, classified as late marker and strong predictor. Glucose yields a delayed response pattern, similar to a hockey stick function, being classified as delayed marker and ranked as moderate predictor (MFC = 1.32, P < 0.001. These findings coincide with existing knowledge on central metabolic pathways affected in exercise physiology, such as β-oxidation of fatty acids, glycolysis, and glycogenolysis. The presented modeling

Quantitative texture analysis of electrodeposited line patterns

DEFF Research Database (Denmark)

Pantleon, Karen; Somers, Marcel A.J.

2005-01-01

Free-standing line patterns of Cu and Ni were manufactured by electrochemical deposition into lithographically prepared patterns. Electrodeposition was carried out on top of a highly oriented Au-layer physically vapor deposited on glass. Quantitative texture analysis carried out by means of x......-ray diffraction for both the substrate layer and the electrodeposits yielded experimental evidence for epitaxy between Cu and Au. An orientation relation between film and substrate was discussed with respect to various concepts of epitaxy. While the conventional mode of epitaxy fails for the Cu...

A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification

Science.gov (United States)

Zhang, Ce; Pan, Xin; Li, Huapeng; Gardiner, Andy; Sargent, Isabel; Hare, Jonathon; Atkinson, Peter M.

2018-06-01

The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based multilayer perceptron (MLP) with shallow structure are well-recognized neural network algorithms, representing the state-of-the-art deep learning method and the classical non-parametric machine learning approach, respectively. The two algorithms, which have very different behaviours, were integrated in a concise and effective way using a rule-based decision fusion approach for the classification of very fine spatial resolution (VFSR) remotely sensed imagery. The decision fusion rules, designed primarily based on the classification confidence of the CNN, reflect the generally complementary patterns of the individual classifiers. In consequence, the proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination. Meanwhile, limitations of the CNN due to the adoption of convolutional filters such as the uncertainty in object boundary partition and loss of useful fine spatial resolution detail were compensated. The effectiveness of the ensemble MLP-CNN classifier was tested in both urban and rural areas using aerial photography together with an additional satellite sensor dataset. The MLP-CNN classifier achieved promising performance, consistently outperforming the pixel-based MLP, spectral and textural-based MLP, and the contextual-based CNN in terms of classification accuracy. This research paves the way to effectively address the complicated problem of VFSR image classification.

A Novel Design of 4-Class BCI Using Two Binary Classifiers and Parallel Mental Tasks

Directory of Open Access Journals (Sweden)

Tao Geng

2008-01-01

Full Text Available A novel 4-class single-trial brain computer interface (BCI based on two (rather than four or more binary linear discriminant analysis (LDA classifiers is proposed, which is called a “parallel BCI.” Unlike other BCIs where mental tasks are executed and classified in a serial way one after another, the parallel BCI uses properly designed parallel mental tasks that are executed on both sides of the subject body simultaneously, which is the main novelty of the BCI paradigm used in our experiments. Each of the two binary classifiers only classifies the mental tasks executed on one side of the subject body, and the results of the two binary classifiers are combined to give the result of the 4-class BCI. Data was recorded in experiments with both real movement and motor imagery in 3 able-bodied subjects. Artifacts were not detected or removed. Offline analysis has shown that, in some subjects, the parallel BCI can generate a higher accuracy than a conventional 4-class BCI, although both of them have used the same feature selection and classification algorithms.

Avaliação comparativa entre agradabilidade facial e análise subjetiva do Padrão Facial Comparative evaluation among facial attractiveness and subjective analysis of Facial Pattern

Directory of Open Access Journals (Sweden)

Olívia Morihisa

2009-12-01

Full Text Available OBJETIVO: estudar duas análises subjetivas faciais utilizadas para o diagnóstico ortodôntico, avaliação da agradabilidade facial e definição de Padrão Facial, e verificar a associação existente entre elas. MÉTODOS: utilizou-se 208 fotografias faciais padronizadas (104 laterais e 104 frontais de 104 indivíduos escolhidos aleatoriamente, as quais foram submetidas à avaliação da agradabilidade por dois grupos distintos (Grupo " Ortodontia" e Grupo " Leigos" , que classificaram os indivíduos em " agradável" , " aceitável" ou " desagradável" . Os indivíduos também foram classificados quanto ao Padrão Facial por três examinadores calibrados, utilizando-se apenas a vista lateral. RESULTADOS E CONCLUSÃO: após a análise estatística, verificou-se que houve associação fortemente positiva entre a agradabilidade facial e o Padrão Facial para a norma lateral, porém não para a frontal, em que os indivíduos tenderam a ser bem classificados mesmo no Padrão II.AIM: To study two subjective facial analysis commonly used on orthodontic diagnosis and to verify the association between the evaluation of facial attractiveness and Facial Pattern definition. METHODS: Two hundred and eight standardized face photographs (104 in lateral view and 104 in frontal view of 104 randomly chosen individuals were used in the present study. They were classified as " pleasant" , " acceptable" and " not pleasant" by two distinct groups: " Lay people" and " Orthodontists" . The individuals were either classified according to their Facial Pattern using lateral view images. RESULTS AND CONCLUSION: After statistical analysis, it was noted a strong positive concordance between facial attractiveness in lateral view and Facial Pattern, however, frontal view attractiveness classification did not have good concordance with Facial Pattern, tending to have good attractiveness classification even in Facial Pattern II.

Vandalism Detection in Wikipedia: a Bag-of-Words Classifier Approach

OpenAIRE

Belani, Amit

2010-01-01

A bag-of-words based probabilistic classifier is trained using regularized logistic regression to detect vandalism in the English Wikipedia. Isotonic regression is used to calibrate the class membership probabilities. Learning curve, reliability, ROC, and cost analysis are performed.

EVALUATING A COMPUTER BASED SKILLS ACQUISITION TRAINER TO CLASSIFY BADMINTON PLAYERS

Directory of Open Access Journals (Sweden)

Minh Vu Huynh

2011-09-01

Full Text Available The aim of the present study was to compare the statistical ability of both neural networks and discriminant function analysis on the newly developed SATB program. Using these statistical tools, we identified the accuracy of the SATB in classifying badminton players into different skill level groups. Forty-one participants, classified as advanced, intermediate, or beginner skilled level, participated in this study. Results indicated neural networks are more effective in predicting group membership, and displayed higher predictive validity when compared to discriminant analysis. Using these outcomes, in conjunction with the physiological and biomechanical variables of the participants, we assessed the authenticity and accuracy of the SATB and commented on the overall effectiveness of the visual based training approach to training badminton athletes

Movement Pattern Analysis Based on Sequence Signatures

Directory of Open Access Journals (Sweden)

Seyed Hossein Chavoshi

2015-09-01

Full Text Available Increased affordability and deployment of advanced tracking technologies have led researchers from various domains to analyze the resulting spatio-temporal movement data sets for the purpose of knowledge discovery. Two different approaches can be considered in the analysis of moving objects: quantitative analysis and qualitative analysis. This research focuses on the latter and uses the qualitative trajectory calculus (QTC, a type of calculus that represents qualitative data on moving point objects (MPOs, and establishes a framework to analyze the relative movement of multiple MPOs. A visualization technique called sequence signature (SESI is used, which enables to map QTC patterns in a 2D indexed rasterized space in order to evaluate the similarity of relative movement patterns of multiple MPOs. The applicability of the proposed methodology is illustrated by means of two practical examples of interacting MPOs: cars on a highway and body parts of a samba dancer. The results show that the proposed method can be effectively used to analyze interactions of multiple MPOs in different domains.

Multitemporal spatial pattern analysis of Tulum's tropical coastal landscape

Science.gov (United States)

Ramírez-Forero, Sandra Carolina; López-Caloca, Alejandra; Silván-Cárdenas, José Luis

2011-11-01

The tropical coastal landscape of Tulum in Quintana Roo, Mexico has a high ecological, economical, social and cultural value, it provides environmental and tourism services at global, national, regional and local levels. The landscape of the area is heterogeneous and presents random fragmentation patterns. In recent years, tourist services of the region has been increased promoting an accelerate expansion of hotels, transportation and recreation infrastructure altering the complex landscape. It is important to understand the environmental dynamics through temporal changes on the spatial patterns and to propose a better management of this ecological area to the authorities. This paper addresses a multi-temporal analysis of land cover changes from 1993 to 2000 in Tulum using Thematic Mapper data acquired by Landsat-5. Two independent methodologies were applied for the analysis of changes in the landscape and for the definition of fragmentation patterns. First, an Iteratively Multivariate Alteration Detection (IR-MAD) algorithm was used to detect and localize land cover change/no-change areas. Second, the post-classification change detection evaluated using the Support Vector Machine (SVM) algorithm. Landscape metrics were calculated from the results of IR-MAD and SVM. The analysis of the metrics indicated, among other things, a higher fragmentation pattern along roadways.

Comparative analysis on some spatial-domain filters for fringe pattern denoising.

Science.gov (United States)

Wang, Haixia; Kemao, Qian

2011-04-20

Fringe patterns produced by various optical interferometric techniques encode information such as shape, deformation, and refractive index. Noise affects further processing of the fringe patterns. Denoising is often needed before fringe pattern demodulation. Filtering along the fringe orientation is an effective option. Such filters include coherence enhancing diffusion, spin filtering with curve windows, second-order oriented partial-differential equations, and the regularized quadratic cost function for oriented fringe pattern filtering. These filters are analyzed to establish the relationships among them. Theoretical analysis shows that the four filters are largely equivalent to each other. Quantitative results are given on simulated fringe patterns to validate the theoretical analysis and to compare the performance of these filters. © 2011 Optical Society of America

76 FR 34761 - Classified National Security Information

Science.gov (United States)

2011-06-14

... MARINE MAMMAL COMMISSION Classified National Security Information [Directive 11-01] AGENCY: Marine... Commission's (MMC) policy on classified information, as directed by Information Security Oversight Office... of Executive Order 13526, ``Classified National Security Information,'' and 32 CFR part 2001...

Error minimizing algorithms for nearest eighbor classifiers

Energy Technology Data Exchange (ETDEWEB)

Porter, Reid B [Los Alamos National Laboratory; Hush, Don [Los Alamos National Laboratory; Zimmer, G. Beate [TEXAS A& M

2011-01-03

Stack Filters define a large class of discrete nonlinear filter first introd uced in image and signal processing for noise removal. In recent years we have suggested their application to classification problems, and investigated their relationship to other types of discrete classifiers such as Decision Trees. In this paper we focus on a continuous domain version of Stack Filter Classifiers which we call Ordered Hypothesis Machines (OHM), and investigate their relationship to Nearest Neighbor classifiers. We show that OHM classifiers provide a novel framework in which to train Nearest Neighbor type classifiers by minimizing empirical error based loss functions. We use the framework to investigate a new cost sensitive loss function that allows us to train a Nearest Neighbor type classifier for low false alarm rate applications. We report results on both synthetic data and real-world image data.

Heterogeneity wavelet kinetics from DCE-MRI for classifying gene expression based breast cancer recurrence risk.

Science.gov (United States)

Mahrooghy, Majid; Ashraf, Ahmed B; Daye, Dania; Mies, Carolyn; Feldman, Michael; Rosen, Mark; Kontos, Despina

2013-01-01

Breast tumors are heterogeneous lesions. Intra-tumor heterogeneity presents a major challenge for cancer diagnosis and treatment. Few studies have worked on capturing tumor heterogeneity from imaging. Most studies to date consider aggregate measures for tumor characterization. In this work we capture tumor heterogeneity by partitioning tumor pixels into subregions and extracting heterogeneity wavelet kinetic (HetWave) features from breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) to obtain the spatiotemporal patterns of the wavelet coefficients and contrast agent uptake from each partition. Using a genetic algorithm for feature selection, and a logistic regression classifier with leave one-out cross validation, we tested our proposed HetWave features for the task of classifying breast cancer recurrence risk. The classifier based on our features gave an ROC AUC of 0.78, outperforming previously proposed kinetic, texture, and spatial enhancement variance features which give AUCs of 0.69, 0.64, and 0.65, respectively.

Polypharmacy patterns: unravelling systematic associations between prescribed medications.

Directory of Open Access Journals (Sweden)

Amaia Calderón-Larrañaga

Full Text Available OBJECTIVES: The aim of this study was to demonstrate the existence of systematic associations in drug prescription that lead to the establishment of patterns of polypharmacy, and the clinical interpretation of the associations found in each pattern. METHODS: A cross-sectional study was conducted based on information obtained from electronic medical records and the primary care pharmacy database in 2008. An exploratory factor analysis of drug dispensing information regarding 79,089 adult patients was performed to identify the patterns of polypharmacy. The analysis was stratified by age and sex. RESULTS: Seven patterns of polypharmacy were identified, which may be classified depending on the type of disease they are intended to treat: cardiovascular, depression-anxiety, acute respiratory infection (ARI, chronic obstructive pulmonary disease (COPD, rhinitis-asthma, pain, and menopause. Some of these patterns revealed a clear clinical consistency and included drugs that are prescribed together for the same clinical indication (i.e., ARI and COPD patterns. Other patterns were more complex but also clinically consistent: in the cardiovascular pattern, drugs for the treatment of known risk factors-such as hypertension or dyslipidemia-were combined with other medications for the treatment of diabetes or established cardiovascular pathology (e.g., antiplatelet agents. Almost all of the patterns included drugs for preventing or treating potential side effects of other drugs in the same pattern. CONCLUSIONS: The present study demonstrated the existence of non-random associations in drug prescription, resulting in patterns of polypharmacy that are sound from the pharmacological and clinical viewpoints and that exist in a significant proportion of the population. This finding necessitates future longitudinal studies to confirm some of the proposed causal associations. The information discovered would further the development and/or adaptation of clinical

Mycoplasma pneumonia in children: radiographic pattern analysis and difference in resolution

Energy Technology Data Exchange (ETDEWEB)

Jeong, Myeong Ja; Jeong, Sung Eun; Kim, Joung Sook; Hur, Gham; Park, Jeung Uk [Inje Univ. College of Medicine, Seoul (Korea, Republic of)

1997-11-01

By analysing frequency and disease progression, this study aimed to investigate and predict the prognosis of mycoplasma pneumonia according to radiographic pattern. We retrospectively reviewed plain chest radiographs of 230 patients in whom mycoplasm pneumonia had been serologically confirmed. Their age ranged from two months to 14 years and two months, and 203(88.3%) were younger than eight years. Radiographic patterns were classified as air space consolidation, bronchopneumonic, interstitial pneumonic or diffuse mixed infiltrating type. The radiologic resolution period for each type was analysed by the resolution of symptoms and normalization of radiologic findings. The bronchopneumonic type, which was the most common, was seen in 82 patients(35.6%), airspace consolidation in 58(25.2%), interstitial in 55(23.9%), and diffuse mixed in 22(9.57%). In thirteen patients(5.7%), chest radiographs were normal, though the clinical and radiologic resolution period for each type was variable. The mean resolution period of the air space consolidation type was 14.5 days, bronchopneumonic, 7.6 days ; interstitial, 10.5 days, and diffuse mixed, 15.6 days. The airspace consolidation type needed the longest recovery period, exceeded only by the diffuse mixed type. The bronchopneumonic type was the most common radiographic pattern of mycoplasma pneumonia. The prognosis of the airspace consolidation type seems to be poorest, since this required the longest recovery period.

Value of self-monitoring blood glucose pattern analysis in improving diabetes outcomes.

Science.gov (United States)

Parkin, Christopher G; Davidson, Jaime A

2009-05-01

Self-monitoring of blood glucose (SMBG) is an important adjunct to hemoglobin A1c (HbA1c) testing. This action can distinguish between fasting, preprandial, and postprandial hyperglycemia; detect glycemic excursions; identify and monitor resolution of hypoglycemia; and provide immediate feedback to patients about the effect of food choices, activity, and medication on glycemic control. Pattern analysis is a systematic approach to identifying glycemic patterns within SMBG data and then taking appropriate action based upon those results. The use of pattern analysis involves: (1) establishing pre- and postprandial glucose targets; (2) obtaining data on glucose levels, carbohydrate intake, medication administration (type, dosages, timing), activity levels and physical/emotional stress; (3) analyzing data to identify patterns of glycemic excursions, assessing any influential factors, and implementing appropriate action(s); and (4) performing ongoing SMBG to assess the impact of any therapeutic changes made. Computer-based and paper-based data collection and management tools can be developed to perform pattern analysis for identifying patterns in SMBG data. This approach to interpreting SMBG data facilitates rational therapeutic adjustments in response to this information. Pattern analysis of SMBG data can be of equal or greater value than measurement of HbA1c levels. 2009 Diabetes Technology Society.

Laban movement analysis to classify emotions from motion

Science.gov (United States)

Dewan, Swati; Agarwal, Shubham; Singh, Navjyoti

2018-04-01

In this paper, we present the study of Laban Movement Analysis (LMA) to understand basic human emotions from nonverbal human behaviors. While there are a lot of studies on understanding behavioral patterns based on natural language processing and speech processing applications, understanding emotions or behavior from non-verbal human motion is still a very challenging and unexplored field. LMA provides a rich overview of the scope of movement possibilities. These basic elements can be used for generating movement or for describing movement. They provide an inroad to understanding movement and for developing movement efficiency and expressiveness. Each human being combines these movement factors in his/her own unique way and organizes them to create phrases and relationships which reveal personal, artistic, or cultural style. In this work, we build a motion descriptor based on a deep understanding of Laban theory. The proposed descriptor builds up on previous works and encodes experiential features by using temporal windows. We present a more conceptually elaborate formulation of Laban theory and test it in a relatively new domain of behavioral research with applications in human-machine interaction. The recognition of affective human communication may be used to provide developers with a rich source of information for creating systems that are capable of interacting well with humans. We test our algorithm on UCLIC dataset which consists of body motions of 13 non-professional actors portraying angry, fear, happy and sad emotions. We achieve an accuracy of 87.30% on this dataset.

Association between yogurt consumption, dietary patterns, and cardio-metabolic risk factors.

Science.gov (United States)

Cormier, Hubert; Thifault, Élisabeth; Garneau, Véronique; Tremblay, Angelo; Drapeau, Vicky; Pérusse, Louis; Vohl, Marie-Claude

2016-03-01

To examine whether yogurt consumption is associated with a healthier dietary pattern and with a better cardio-metabolic risk profile among healthy individuals classified on the basis of their body mass index (BMI). A 91-item food frequency questionnaire, including data on yogurt consumption, was administered to 664 subjects from the INFOGENE study. After principal component analysis, two factors were retained, thus classified as the Prudent and Western dietary patterns. Yogurt was a significant contributor to the Prudent dietary pattern. Moreover, yogurt consumption was associated with lower body weight, waist-to-hip ratio, and waist circumference and tended to be associated with a lower BMI. Consumers had lower levels of fasting total cholesterol and insulin. Consumers of yogurt had a positive Prudent dietary pattern mean score, while the opposite trend was observed in non-consumers of yogurt. Overweight/obese individuals who were consumers of yogurts exhibited a more favorable cardio-metabolic profile characterized by lower plasma triglyceride and insulin levels than non-consumers within the same range of BMI. There was no difference in total yogurt consumption between normal-weight individuals and overweight/obese individuals. However, normal-weight subjects had more daily servings of high-fat yogurt and less daily servings of fat-free yogurt compared to overweight/obese individuals. Being a significant contributor to the Prudent dietary pattern, yogurt consumption may be associated with healthy eating. Also, yogurt consumption may be associated with lower anthropometric indicators and a more beneficial cardio-metabolic risk profile in overweight/obese individuals.

Unsupervised classification of neocortical activity patterns in neonatal and pre-juvenile rodents

Directory of Open Access Journals (Sweden)

Nicole eCichon

2014-05-01

Full Text Available Flexible communication within the brain, which relies on oscillatory activity, is not confined to adult neuronal networks. Experimental evidence has documented the presence of discontinuous patterns of oscillatory activity already during early development. Their highly variable spatial and time-frequency organization has been related to region specificity. However, it might be equally due to the absence of unitary criteria for classifying the early activity patterns, since they have been mainly characterized by visual inspection. Therefore, robust and unbiased methods for categorizing these discontinuous oscillations are needed for increasingly complex data sets from different labs. Here, we introduce an unsupervised detection and classification algorithm for the discontinuous activity patterns of rodents during early development. For this, firstly time windows with discontinuous oscillations vs. epochs of network silence were identified. In a second step, the major features of detected events were identified and processed by principal component analysis for deciding on their contribution to the classification of different oscillatory patterns. Finally, these patterns were categorized using an unsupervised cluster algorithm. The results were validated on manually characterized neonatal spindle bursts, which ubiquitously entrain neocortical areas of rats and mice, and prelimbic nested gamma spindle bursts. Moreover, the algorithm led to satisfactory results for oscillatory events that, due to increased similarity of their features, were more difficult to classify, e.g. during the pre-juvenile developmental period. Based on a linear classification, the optimal number of features to consider increased with the difficulty of detection. This algorithm allows the comparison of neonatal and pre-juvenile oscillatory patterns in their spatial and temporal organization. It might represent a first step for the unbiased elucidation of activity patterns

Composite Classifiers for Automatic Target Recognition

National Research Council Canada - National Science Library

Wang, Lin-Cheng

1998-01-01

...) using forward-looking infrared (FLIR) imagery. Two existing classifiers, one based on learning vector quantization and the other on modular neural networks, are used as the building blocks for our composite classifiers...

WAVELET ANALYSIS AND NEURAL NETWORK CLASSIFIERS TO DETECT MID-SAGITTAL SECTIONS FOR NUCHAL TRANSLUCENCY MEASUREMENT

Directory of Open Access Journals (Sweden)

Giuseppa Sciortino

2016-04-01

Full Text Available We propose a methodology to support the physician in the automatic identification of mid-sagittal sections of the fetus in ultrasound videos acquired during the first trimester of pregnancy. A good mid-sagittal section is a key requirement to make the correct measurement of nuchal translucency which is one of the main marker for screening of chromosomal defects such as trisomy 13, 18 and 21. NT measurement is beyond the scope of this article. The proposed methodology is mainly based on wavelet analysis and neural network classifiers to detect the jawbone and on radial symmetry analysis to detect the choroid plexus. Those steps allow to identify the frames which represent correct mid-sagittal sections to be processed. The performance of the proposed methodology was analyzed on 3000 random frames uniformly extracted from 10 real clinical ultrasound videos. With respect to a ground-truth provided by an expert physician, we obtained a true positive, a true negative and a balanced accuracy equal to 87.26%, 94.98% and 91.12% respectively.

A novel ultrasound based technique for classifying gas bubble sizes in liquids

International Nuclear Information System (INIS)

Hussein, Walid; Khan, Muhammad Salman; Zamorano, Juan; Espic, Felipe; Yoma, Nestor Becerra

2014-01-01

Characterizing gas bubbles in liquids is crucial to many biomedical, environmental and industrial applications. In this paper a novel method is proposed for the classification of bubble sizes using ultrasound analysis, which is widely acknowledged for being non-invasive, non-contact and inexpensive. This classification is based on 2D templates, i.e. the average spectrum of events representing the trace of bubbles when they cross an ultrasound field. The 2D patterns are obtained by capturing ultrasound signals reflected by bubbles. Frequency-domain based features are analyzed that provide discrimination between bubble sizes. These features are then fed to an artificial neural network, which is designed and trained to classify bubble sizes. The benefits of the proposed method are that it facilitates the processing of multiple bubbles simultaneously, the issues concerning masking interference among bubbles are potentially reduced and using a single sinusoidal component makes the transmitter–receiver electronics relatively simpler. Results from three bubble sizes indicate that the proposed scheme can achieve an accuracy in their classification that is as high as 99%. (paper)

Support Vector Machines for Pattern Classification

CERN Document Server

Abe, Shigeo

2010-01-01

A guide on the use of SVMs in pattern classification, including a rigorous performance comparison of classifiers and regressors. The book presents architectures for multiclass classification and function approximation problems, as well as evaluation criteria for classifiers and regressors. Features: Clarifies the characteristics of two-class SVMs; Discusses kernel methods for improving the generalization ability of neural networks and fuzzy systems; Contains ample illustrations and examples; Includes performance evaluation using publicly available data sets; Examines Mahalanobis kernels, empir

Evaluation of LDA Ensembles Classifiers for Brain Computer Interface

International Nuclear Information System (INIS)

Arjona, Cristian; Pentácolo, José; Gareis, Iván; Atum, Yanina; Gentiletti, Gerardo; Acevedo, Rubén; Rufiner, Leonardo

2011-01-01

The Brain Computer Interface (BCI) translates brain activity into computer commands. To increase the performance of the BCI, to decode the user intentions it is necessary to get better the feature extraction and classification techniques. In this article the performance of a three linear discriminant analysis (LDA) classifiers ensemble is studied. The system based on ensemble can theoretically achieved better classification results than the individual counterpart, regarding individual classifier generation algorithm and the procedures for combine their outputs. Classic algorithms based on ensembles such as bagging and boosting are discussed here. For the application on BCI, it was concluded that the generated results using ER and AUC as performance index do not give enough information to establish which configuration is better.

Masticatory path pattern during mastication of chewing gum with regard to gender difference.

Science.gov (United States)

Kobayashi, Yoshinori; Shiga, Hiroshi; Arakawa, Ichiro; Yokoyama, Masaoki; Nakajima, Kunihisa

2009-01-01

To clarify the masticatory path patterns of the mandibular incisal point during mastication of softened chewing gum with regard to gender difference. One hundred healthy subjects (50 males and 50 females) were asked to chew softened chewing gum on one side at a time (right side and left side) and the movement of the mandibular incisal point was recorded using MKG K6I. After a catalog of path patterns was made, the movement path was classified into one of the pattern groups, and then the frequency of each pattern was investigated. A catalog of path patterns consisting of the three types of opening path (op1, linear or concave path; op2, path toward the chewing side after toward the non-working side; op3, convex path) and two types of closing path (cl1, convex path; cl2, concave path) was made. The movement path was classified into one of seven patterns, with six patterns being from the catalog and a final extra pattern in which the opening and closing paths crossed. The most common pattern among the subjects was Pattern I, followed by Patterns III, II, IV, V, VII, and VI, in that order. The majority of cases, 149 (74.5%) of 200 cases, showed either Pattern I (op1 and cl1) or Pattern III (op2 and cl1). There was no significant difference between the two genders in the frequency of each pattern. The movement path could be classified into seven patterns and no gender-related difference was found in the frequency of each pattern.

Hybrid Neuro-Fuzzy Classifier Based On Nefclass Model

Directory of Open Access Journals (Sweden)

Bogdan Gliwa

2011-01-01

Full Text Available The paper presents hybrid neuro-fuzzy classifier, based on NEFCLASS model, which wasmodified. The presented classifier was compared to popular classifiers – neural networks andk-nearest neighbours. Efficiency of modifications in classifier was compared with methodsused in original model NEFCLASS (learning methods. Accuracy of classifier was testedusing 3 datasets from UCI Machine Learning Repository: iris, wine and breast cancer wisconsin.Moreover, influence of ensemble classification methods on classification accuracy waspresented.

Classifying Transition Behaviour in Postural Activity Monitoring

Directory of Open Access Journals (Sweden)

James BRUSEY

2009-10-01

Full Text Available A few accelerometers positioned on different parts of the body can be used to accurately classify steady state behaviour, such as walking, running, or sitting. Such systems are usually built using supervised learning approaches. Transitions between postures are, however, difficult to deal with using posture classification systems proposed to date, since there is no label set for intermediary postures and also the exact point at which the transition occurs can sometimes be hard to pinpoint. The usual bypass when using supervised learning to train such systems is to discard a section of the dataset around each transition. This leads to poorer classification performance when the systems are deployed out of the laboratory and used on-line, particularly if the regimes monitored involve fast paced activity changes. Time-based filtering that takes advantage of sequential patterns is a potential mechanism to improve posture classification accuracy in such real-life applications. Also, such filtering should reduce the number of event messages needed to be sent across a wireless network to track posture remotely, hence extending the system’s life. To support time-based filtering, understanding transitions, which are the major event generators in a classification system, is a key. This work examines three approaches to post-process the output of a posture classifier using time-based filtering: a naïve voting scheme, an exponentially weighted voting scheme, and a Bayes filter. Best performance is obtained from the exponentially weighted voting scheme although it is suspected that a more sophisticated treatment of the Bayes filter might yield better results.

Landscape object-based analysis of wetland plant functional types: the effects of spatial scale, vegetation classes and classifier methods

Science.gov (United States)

Dronova, I.; Gong, P.; Wang, L.; Clinton, N.; Fu, W.; Qi, S.

2011-12-01

Remote sensing-based vegetation classifications representing plant function such as photosynthesis and productivity are challenging in wetlands with complex cover and difficult field access. Recent advances in object-based image analysis (OBIA) and machine-learning algorithms offer new classification tools; however, few comparisons of different algorithms and spatial scales have been discussed to date. We applied OBIA to delineate wetland plant functional types (PFTs) for Poyang Lake, the largest freshwater lake in China and Ramsar wetland conservation site, from 30-m Landsat TM scene at the peak of spring growing season. We targeted major PFTs (C3 grasses, C3 forbs and different types of C4 grasses and aquatic vegetation) that are both key players in system's biogeochemical cycles and critical providers of waterbird habitat. Classification results were compared among: a) several object segmentation scales (with average object sizes 900-9000 m2); b) several families of statistical classifiers (including Bayesian, Logistic, Neural Network, Decision Trees and Support Vector Machines) and c) two hierarchical levels of vegetation classification, a generalized 3-class set and more detailed 6-class set. We found that classification benefited from object-based approach which allowed including object shape, texture and context descriptors in classification. While a number of classifiers achieved high accuracy at the finest pixel-equivalent segmentation scale, the highest accuracies and best agreement among algorithms occurred at coarser object scales. No single classifier was consistently superior across all scales, although selected algorithms of Neural Network, Logistic and K-Nearest Neighbors families frequently provided the best discrimination of classes at different scales. The choice of vegetation categories also affected classification accuracy. The 6-class set allowed for higher individual class accuracies but lower overall accuracies than the 3-class set because

A subject-independent pattern-based Brain-Computer Interface

Directory of Open Access Journals (Sweden)

Andreas Markus Ray

2015-10-01

Full Text Available While earlier Brain-Computer Interface (BCI studies have mostly focused on modulating specific brain regions or signals, new developments in pattern classification of brain states are enabling real-time decoding and modulation of an entire functional network. The present study proposes a new method for real-time pattern classification and neurofeedback of brain states from electroencephalographic (EEG signals. It involves the creation of a fused classification model based on the method of Common Spatial Patterns (CSPs from data of several healthy individuals. The subject-independent model is then used to classify EEG data in real-time and provide feedback to new individuals. In a series of offline experiments involving training and testing of the classifier with individual data from 27 healthy subjects, a mean classification accuracy of 75.30% was achieved, demonstrating that the classification system at hand can reliably decode two types of imagery used in our experiments, i.e. happy emotional imagery and motor imagery. In a subsequent experiment it is shown that the classifier can be used to provide neurofeedback to new subjects, and that these subjects learn to match their brain pattern to that of the fused classification model in a few days of neurofeedback training. This finding can have important implications for future studies on neurofeedback and its clinical applications on neuropsychiatric disorders.

Spiking Neural Classifier with Lumped Dendritic Nonlinearity and Binary Synapses: A Current Mode VLSI Implementation and Analysis.

Science.gov (United States)

Bhaduri, Aritra; Banerjee, Amitava; Roy, Subhrajit; Kar, Sougata; Basu, Arindam

2018-03-01

We present a neuromorphic current mode implementation of a spiking neural classifier with lumped square law dendritic nonlinearity. It has been shown previously in software simulations that such a system with binary synapses can be trained with structural plasticity algorithms to achieve comparable classification accuracy with fewer synaptic resources than conventional algorithms. We show that even in real analog systems with manufacturing imperfections (CV of 23.5% and 14.4% for dendritic branch gains and leaks respectively), this network is able to produce comparable results with fewer synaptic resources. The chip fabricated in [Formula: see text]m complementary metal oxide semiconductor has eight dendrites per cell and uses two opposing cells per class to cancel common-mode inputs. The chip can operate down to a [Formula: see text] V and dissipates 19 nW of static power per neuronal cell and [Formula: see text] 125 pJ/spike. For two-class classification problems of high-dimensional rate encoded binary patterns, the hardware achieves comparable performance as software implementation of the same with only about a 0.5% reduction in accuracy. On two UCI data sets, the IC integrated circuit has classification accuracy comparable to standard machine learners like support vector machines and extreme learning machines while using two to five times binary synapses. We also show that the system can operate on mean rate encoded spike patterns, as well as short bursts of spikes. To the best of our knowledge, this is the first attempt in hardware to perform classification exploiting dendritic properties and binary synapses.

Quantum pattern recognition with multi-neuron interactions

Science.gov (United States)

Fard, E. Rezaei; Aghayar, K.; Amniat-Talab, M.

2018-03-01

We present a quantum neural network with multi-neuron interactions for pattern recognition tasks by a combination of extended classic Hopfield network and adiabatic quantum computation. This scheme can be used as an associative memory to retrieve partial patterns with any number of unknown bits. Also, we propose a preprocessing approach to classifying the pattern space S to suppress spurious patterns. The results of pattern clustering show that for pattern association, the number of weights (η ) should equal the numbers of unknown bits in the input pattern ( d). It is also remarkable that associative memory function depends on the location of unknown bits apart from the d and load parameter α.

Comparison of the Classifier Oriented Gait Score and the Gait Profile Score based on imitated gait impairments.

Science.gov (United States)

Christian, Josef; Kröll, Josef; Schwameder, Hermann

2017-06-01

Common summary measures of gait quality such as the Gait Profile Score (GPS) are based on the principle of measuring a distance from the mean pattern of a healthy reference group in a gait pattern vector space. The recently introduced Classifier Oriented Gait Score (COGS) is a pathology specific score that measures this distance in a unique direction, which is indicated by a linear classifier. This approach has potentially improved the discriminatory power to detect subtle changes in gait patterns but does not incorporate a profile of interpretable sub-scores like the GPS. The main aims of this study were to extend the COGS by decomposing it into interpretable sub-scores as realized in the GPS and to compare the discriminative power of the GPS and COGS. Two types of gait impairments were imitated to enable a high level of control of the gait patterns. Imitated impairments were realized by restricting knee extension and inducing leg length discrepancy. The results showed increased discriminatory power of the COGS for differentiating diverse levels of impairment. Comparison of the GPS and COGS sub-scores and their ability to indicate changes in specific variables supports the validity of both scores. The COGS is an overall measure of gait quality with increased power to detect subtle changes in gait patterns and might be well suited for tracing the effect of a therapeutic treatment over time. The newly introduced sub-scores improved the interpretability of the COGS, which is helpful for practical applications. Copyright © 2017 Elsevier B.V. All rights reserved.

Developing a complex independent component analysis technique to extract non-stationary patterns from geophysical time-series

Science.gov (United States)

Forootan, Ehsan; Kusche, Jürgen

2016-04-01

Geodetic/geophysical observations, such as the time series of global terrestrial water storage change or sea level and temperature change, represent samples of physical processes and therefore contain information about complex physical interactionswith many inherent time scales. Extracting relevant information from these samples, for example quantifying the seasonality of a physical process or its variability due to large-scale ocean-atmosphere interactions, is not possible by rendering simple time series approaches. In the last decades, decomposition techniques have found increasing interest for extracting patterns from geophysical observations. Traditionally, principal component analysis (PCA) and more recently independent component analysis (ICA) are common techniques to extract statistical orthogonal (uncorrelated) and independent modes that represent the maximum variance of observations, respectively. PCA and ICA can be classified as stationary signal decomposition techniques since they are based on decomposing the auto-covariance matrix or diagonalizing higher (than two)-order statistical tensors from centered time series. However, the stationary assumption is obviously not justifiable for many geophysical and climate variables even after removing cyclic components e.g., the seasonal cycles. In this paper, we present a new decomposition method, the complex independent component analysis (CICA, Forootan, PhD-2014), which can be applied to extract to non-stationary (changing in space and time) patterns from geophysical time series. Here, CICA is derived as an extension of real-valued ICA (Forootan and Kusche, JoG-2012), where we (i) define a new complex data set using a Hilbert transformation. The complex time series contain the observed values in their real part, and the temporal rate of variability in their imaginary part. (ii) An ICA algorithm based on diagonalization of fourth-order cumulants is then applied to decompose the new complex data set in (i

Identifying aggressive prostate cancer foci using a DNA methylation classifier.

Science.gov (United States)

Mundbjerg, Kamilla; Chopra, Sameer; Alemozaffar, Mehrdad; Duymich, Christopher; Lakshminarasimhan, Ranjani; Nichols, Peter W; Aron, Manju; Siegmund, Kimberly D; Ukimura, Osamu; Aron, Monish; Stern, Mariana; Gill, Parkash; Carpten, John D; Ørntoft, Torben F; Sørensen, Karina D; Weisenberger, Daniel J; Jones, Peter A; Duddalwar, Vinay; Gill, Inderbir; Liang, Gangning

2017-01-12

Slow-growing prostate cancer (PC) can be aggressive in a subset of cases. Therefore, prognostic tools to guide clinical decision-making and avoid overtreatment of indolent PC and undertreatment of aggressive disease are urgently needed. PC has a propensity to be multifocal with several different cancerous foci per gland. Here, we have taken advantage of the multifocal propensity of PC and categorized aggressiveness of individual PC foci based on DNA methylation patterns in primary PC foci and matched lymph node metastases. In a set of 14 patients, we demonstrate that over half of the cases have multiple epigenetically distinct subclones and determine the primary subclone from which the metastatic lesion(s) originated. Furthermore, we develop an aggressiveness classifier consisting of 25 DNA methylation probes to determine aggressive and non-aggressive subclones. Upon validation of the classifier in an independent cohort, the predicted aggressive tumors are significantly associated with the presence of lymph node metastases and invasive tumor stages. Overall, this study provides molecular-based support for determining PC aggressiveness with the potential to impact clinical decision-making, such as targeted biopsy approaches for early diagnosis and active surveillance, in addition to focal therapy.

Relation between breast parenchymal pattern and breast cancer

International Nuclear Information System (INIS)

Kim, Kyeung Hee; Lee, Sung Yong; Bahk, Yong Whee

1985-01-01

Although the usefulness of mammography as a screening test for breast cancer is still in dispute, its use to patients over 50 years of age is valid. Since Wolfe first classified the breast parenchymal patterns of mammography into 4 patterns, many authors have adopted the criteria in studying the changes of the parenchymal patterns for certain ages and the risks for breast cancer of certain parenchymal patterns. Authors reviewed 49 cases of breast masses which diagnosed by mammography and by operation during the period from January 1978 to July 1983 at St. Mary Hospital, Catholic Medical College. The parenchymal tissue patterns were classified according to Wolfe into N1, P1, P2 and DY, Risk groups were classified into low risk group (N1, P1) and high group (P2, DY). On the basis of these criteria, benign and malignant disease were analyzed against the breast parenchymal patterns. The results and conclusions were as follows: 1. Age ranged from 16 years to 67 years with the most prevalent age being 4th and 5th decades. 2. Diagnoses were: fibroadenoma 17 cases, fibrous dysplasia 16 cases, ductal papilloma 3 cases, and cancer 13 cases. 3. Categorization of those 26 benign disease according to the Wolfe's criteria was: N1 6 cases, P1 10 cases, P2 9 cases and DY 11 cases. On the other hand, categorization of 13 cases of cancer was: N1 5 caes, P1 3 cases, P2 3 cases, and DY 2 cases. 4. Of 13 cases of cancer, 8 fell in the low risk group and remainder in the high risk group. There were no significant correlation between the parenchymal patterns and the incidence of breast cancer

Pattern recognition in menstrual bleeding diaries by statistical cluster analysis

Directory of Open Access Journals (Sweden)

Wessel Jens

2009-07-01

Full Text Available Abstract Background The aim of this paper is to empirically identify a treatment-independent statistical method to describe clinically relevant bleeding patterns by using bleeding diaries of clinical studies on various sex hormone containing drugs. Methods We used the four cluster analysis methods single, average and complete linkage as well as the method of Ward for the pattern recognition in menstrual bleeding diaries. The optimal number of clusters was determined using the semi-partial R2, the cubic cluster criterion, the pseudo-F- and the pseudo-t2-statistic. Finally, the interpretability of the results from a gynecological point of view was assessed. Results The method of Ward yielded distinct clusters of the bleeding diaries. The other methods successively chained the observations into one cluster. The optimal number of distinctive bleeding patterns was six. We found two desirable and four undesirable bleeding patterns. Cyclic and non cyclic bleeding patterns were well separated. Conclusion Using this cluster analysis with the method of Ward medications and devices having an impact on bleeding can be easily compared and categorized.

36 CFR 1256.46 - National security-classified information.

Science.gov (United States)

2010-07-01

... 36 Parks, Forests, and Public Property 3 2010-07-01 2010-07-01 false National security-classified... Restrictions § 1256.46 National security-classified information. In accordance with 5 U.S.C. 552(b)(1), NARA... properly classified under the provisions of the pertinent Executive Order on Classified National Security...

Analysis of Usage Patterns in Large Multimedia Websites

Science.gov (United States)

Singh, Rahul; Bhattarai, Bibek

User behavior in a website is a critical indicator of the web site's usability and success. Therefore an understanding of usage patterns is essential to website design optimization. In this context, large multimedia websites pose a significant challenge for comprehension of the complex and diverse user behaviors they sustain. This is due to the complexity of analyzing and understanding user-data interactions in media-rich contexts. In this chapter we present a novel multi-perspective approach for usability analysis of large media rich websites. Our research combines multimedia web content analysis with elements of web-log analysis and visualization/visual mining of web usage metadata. Multimedia content analysis allows direct estimation of the information-cues presented to a user by the web content. Analysis of web logs and usage-metadata, such as location, type, and frequency of interactions provides a complimentary perspective on the site's usage. The entire set of information is leveraged through powerful visualization and interactive querying techniques to provide analysis of usage patterns, measure of design quality, as well as the ability to rapidly identify problems in the web-site design. Experiments on media rich sites including the SkyServer - a large multimedia web-based astronomy information repository demonstrate the efficacy and promise of the proposed approach.

Class-specific Error Bounds for Ensemble Classifiers

Energy Technology Data Exchange (ETDEWEB)

Prenger, R; Lemmond, T; Varshney, K; Chen, B; Hanley, W

2009-10-06

The generalization error, or probability of misclassification, of ensemble classifiers has been shown to be bounded above by a function of the mean correlation between the constituent (i.e., base) classifiers and their average strength. This bound suggests that increasing the strength and/or decreasing the correlation of an ensemble's base classifiers may yield improved performance under the assumption of equal error costs. However, this and other existing bounds do not directly address application spaces in which error costs are inherently unequal. For applications involving binary classification, Receiver Operating Characteristic (ROC) curves, performance curves that explicitly trade off false alarms and missed detections, are often utilized to support decision making. To address performance optimization in this context, we have developed a lower bound for the entire ROC curve that can be expressed in terms of the class-specific strength and correlation of the base classifiers. We present empirical analyses demonstrating the efficacy of these bounds in predicting relative classifier performance. In addition, we specify performance regions of the ROC curve that are naturally delineated by the class-specific strengths of the base classifiers and show that each of these regions can be associated with a unique set of guidelines for performance optimization of binary classifiers within unequal error cost regimes.

Data and statistical methods for analysis of trends and patterns

International Nuclear Information System (INIS)

Atwood, C.L.; Gentillon, C.D.; Wilson, G.E.

1992-11-01

This report summarizes topics considered at a working meeting on data and statistical methods for analysis of trends and patterns in US commercial nuclear power plants. This meeting was sponsored by the Office of Analysis and Evaluation of Operational Data (AEOD) of the Nuclear Regulatory Commission (NRC). Three data sets are briefly described: Nuclear Plant Reliability Data System (NPRDS), Licensee Event Report (LER) data, and Performance Indicator data. Two types of study are emphasized: screening studies, to see if any trends or patterns appear to be present; and detailed studies, which are more concerned with checking the analysis assumptions, modeling any patterns that are present, and searching for causes. A prescription is given for a screening study, and ideas are suggested for a detailed study, when the data take of any of three forms: counts of events per time, counts of events per demand, and non-event data

Deconvolution When Classifying Noisy Data Involving Transformations

KAUST Repository

Carroll, Raymond

2012-09-01

In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

Deconvolution When Classifying Noisy Data Involving Transformations.

Science.gov (United States)

Carroll, Raymond; Delaigle, Aurore; Hall, Peter

2012-09-01

In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

Just-in-time classifiers for recurrent concepts.

Science.gov (United States)

Alippi, Cesare; Boracchi, Giacomo; Roveri, Manuel

2013-04-01

Just-in-time (JIT) classifiers operate in evolving environments by classifying instances and reacting to concept drift. In stationary conditions, a JIT classifier improves its accuracy over time by exploiting additional supervised information coming from the field. In nonstationary conditions, however, the classifier reacts as soon as concept drift is detected; the current classification setup is discarded and a suitable one activated to keep the accuracy high. We present a novel generation of JIT classifiers able to deal with recurrent concept drift by means of a practical formalization of the concept representation and the definition of a set of operators working on such representations. The concept-drift detection activity, which is crucial in promptly reacting to changes exactly when needed, is advanced by considering change-detection tests monitoring both inputs and classes distributions.

Deconvolution When Classifying Noisy Data Involving Transformations

KAUST Repository

Carroll, Raymond; Delaigle, Aurore; Hall, Peter

2012-01-01

In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

A Comparison of Physiological Signal Analysis Techniques and Classifiers for Automatic Emotional Evaluation of Audiovisual Contents.

Science.gov (United States)

Colomer Granero, Adrián; Fuentes-Hurtado, Félix; Naranjo Ornedo, Valery; Guixeres Provinciale, Jaime; Ausín, Jose M; Alcañiz Raya, Mariano

2016-01-01

This work focuses on finding the most discriminatory or representative features that allow to classify commercials according to negative, neutral and positive effectiveness based on the Ace Score index. For this purpose, an experiment involving forty-seven participants was carried out. In this experiment electroencephalography (EEG), electrocardiography (ECG), Galvanic Skin Response (GSR) and respiration data were acquired while subjects were watching a 30-min audiovisual content. This content was composed by a submarine documentary and nine commercials (one of them the ad under evaluation). After the signal pre-processing, four sets of features were extracted from the physiological signals using different state-of-the-art metrics. These features computed in time and frequency domains are the inputs to several basic and advanced classifiers. An average of 89.76% of the instances was correctly classified according to the Ace Score index. The best results were obtained by a classifier consisting of a combination between AdaBoost and Random Forest with automatic selection of features. The selected features were those extracted from GSR and HRV signals. These results are promising in the audiovisual content evaluation field by means of physiological signal processing.

Dietary pattern and asthma: a systematic review and meta-analysis

Directory of Open Access Journals (Sweden)

Lv N

2014-08-01

Full Text Available Nan Lv,1 Lan Xiao,1 Jun Ma1,2 1Palo Alto Medical Foundation Research Institute, 2Department of Medicine, Stanford University School of Medicine, Stanford, CA, USA Background: The literature on the relationship between diet and asthma has largely focused on individual nutrients, with conflicting results. People consume a combination of foods from various groups that form a dietary pattern. Studying the role of dietary patterns in asthma is an emerging area of research. The purpose of this study was to systematically review dietary patterns and asthma outcomes in adults and children, to review maternal diet and child asthma, and to conduct a meta-analysis on the association between asthma prevalence and dietary patterns in adults. Methods: We searched Medline, Scopus, and ISI Web of Knowledge up to January 2014. Two researchers independently reviewed studies meeting the inclusion criteria using the American Dietetic Association quality criteria. A linear mixed model was used to derive the pooled effect size (95% confidence interval for each of three dietary pattern categories (healthy, unhealthy, and neutral. Results: Thirty-one studies were identified (16 cross-sectional, one case-control, 13 cohort, and one randomized controlled trial, including 12 in adults, 13 in children, five in pregnant woman–child pairs, and one in both children and pregnant woman–child pairs. Six of the 12 adult studies reported significant associations between dietary patterns and asthma outcomes (eg, ever asthma and forced expiratory volume in one second. Seven of ten studies examining the Mediterranean diet showed protective effects on child asthma and/or wheeze. Four of the six studies in mother-child pairs showed that maternal dietary patterns during pregnancy were not associated with child asthma or wheeze. The meta-analysis including six adult studies, the primary outcome of which was the prevalence of current or ever asthma, showed no association with healthy

An ontology-based intrusion patterns classification system | Shonubi ...

African Journals Online (AJOL)

Studies have shown that computer intrusions have been on the increase in recent times. Many techniques and patterns are being used by intruders to gain access to data on host computer networks. In this work, intrusion patterns were identified and classified and inherent knowledge were represented using an ontology of ...

Human Walking Pattern Recognition Based on KPCA and SVM with Ground Reflex Pressure Signal

Directory of Open Access Journals (Sweden)

Zhaoqin Peng

2013-01-01

Full Text Available Algorithms based on the ground reflex pressure (GRF signal obtained from a pair of sensing shoes for human walking pattern recognition were investigated. The dimensionality reduction algorithms based on principal component analysis (PCA and kernel principal component analysis (KPCA for walking pattern data compression were studied in order to obtain higher recognition speed. Classifiers based on support vector machine (SVM, SVM-PCA, and SVM-KPCA were designed, and the classification performances of these three kinds of algorithms were compared using data collected from a person who was wearing the sensing shoes. Experimental results showed that the algorithm fusing SVM and KPCA had better recognition performance than the other two methods. Experimental outcomes also confirmed that the sensing shoes developed in this paper can be employed for automatically recognizing human walking pattern in unlimited environments which demonstrated the potential application in the control of exoskeleton robots.

SELDI-TOF-based serum proteomic pattern diagnostics for early detection of cancer.

Science.gov (United States)

Petricoin, Emanuel F; Liotta, Lance A

2004-02-01

Proteomics is more than just generating lists of proteins that increase or decrease in expression as a cause or consequence of pathology. The goal should be to characterize the information flow through the intercellular protein circuitry that communicates with the extracellular microenvironment and then ultimately to the serum/plasma macroenvironment. The nature of this information can be a cause, or a consequence, of disease and toxicity-based processes. Serum proteomic pattern diagnostics is a new type of proteomic platform in which patterns of proteomic signatures from high dimensional mass spectrometry data are used as a diagnostic classifier. This approach has recently shown tremendous promise in the detection of early-stage cancers. The biomarkers found by SELDI-TOF-based pattern recognition analysis are mostly low molecular weight fragments produced at the specific tumor microenvironment.

How to Diagnose and Classify Tattoo Complications in the Clinic: A System of Distinctive Patterns.

Science.gov (United States)

Serup, Jørgen

2017-01-01

Tattoo complications represent a broad spectrum of clinical entities and disease mechanisms. Infections are known, but chronic inflammatory reactions have hitherto been inconsistently reported and given many interpretations and terms. A clinical classification system of distinct patterns with emphasis on inflammatory tattoo reactions is introduced. Allergic reactions prevalent in red tattoos and often associated with azo pigments are manifested as the 'plaque elevation', 'excessive hyperkeratosis', and 'ulceronecrotic' patterns. The allergen is a hapten. Nonallergic reactions prevalent in black tattoos and associated with carbon black are manifested as the 'papulonodular' pattern. Carbon black nanoparticles agglomerate in the dermis over time forming foreign bodies that elicit reactions. Many black tattoos even develop sarcoid granuloma, and the 'papulonodular' pattern is strongly associated with sarcoidosis affecting other organs. Tattoo complications include a large group of less frequent but nevertheless specific entities, i.e. irritant and toxic local events, photosensitivity, urticaria, eczematous rash due to soluble allergen, neurosensitivity and pain syndrome, lymphopathies, pigment diffusion or fan, scars, and other sequels of tattooing or tattoo removal. Keratoacanthoma occurs in tattoos. Carcinoma and melanoma are rare and occur by coincidence only. Different tattoo complications require different therapeutic approaches, and precise diagnosis is thus important as a key to therapy. The proposed new classification with characteristic patterns relies on simple tools, namely patient history, objective findings, and supplementary punch biopsy. By virtue of simplicity and broad access, these methods make the proposed classification widely applicable in clinics and hospitals. The system is reported to the 11th revision of the WHO diagnosis classification used as international standard. © 2017 S. Karger AG, Basel.

Analysis of synonymous codon usage patterns in the genus Rhizobium.

Science.gov (United States)

Wang, Xinxin; Wu, Liang; Zhou, Ping; Zhu, Shengfeng; An, Wei; Chen, Yu; Zhao, Lin

2013-11-01

The codon usage patterns of rhizobia have received increasing attention. However, little information is available regarding the conserved features of the codon usage patterns in a typical rhizobial genus. The codon usage patterns of six completely sequenced strains belonging to the genus Rhizobium were analysed as model rhizobia in the present study. The relative neutrality plot showed that selection pressure played a role in codon usage in the genus Rhizobium. Spearman's rank correlation analysis combined with correspondence analysis (COA) showed that the codon adaptation index and the effective number of codons (ENC) had strong correlation with the first axis of the COA, which indicated the important role of gene expression level and the ENC in the codon usage patterns in this genus. The relative synonymous codon usage of Cys codons had the strongest correlation with the second axis of the COA. Accordingly, the usage of Cys codons was another important factor that shaped the codon usage patterns in Rhizobium genomes and was a conserved feature of the genus. Moreover, the comparison of codon usage between highly and lowly expressed genes showed that 20 unique preferred codons were shared among Rhizobium genomes, revealing another conserved feature of the genus. This is the first report of the codon usage patterns in the genus Rhizobium.

Comparing classifiers for pronunciation error detection

NARCIS (Netherlands)

Strik, H.; Truong, K.; Wet, F. de; Cucchiarini, C.

2007-01-01

Providing feedback on pronunciation errors in computer assisted language learning systems requires that pronunciation errors be detected automatically. In the present study we compare four types of classifiers that can be used for this purpose: two acoustic-phonetic classifiers (one of which employs

Automated classification of immunostaining patterns in breast tissue from the human protein atlas.

Science.gov (United States)

Swamidoss, Issac Niwas; Kårsnäs, Andreas; Uhlmann, Virginie; Ponnusamy, Palanisamy; Kampf, Caroline; Simonsson, Martin; Wählby, Carolina; Strand, Robin

2013-01-01

The Human Protein Atlas (HPA) is an effort to map the location of all human proteins (http://www.proteinatlas.org/). It contains a large number of histological images of sections from human tissue. Tissue micro arrays (TMA) are imaged by a slide scanning microscope, and each image represents a thin slice of a tissue core with a dark brown antibody specific stain and a blue counter stain. When generating antibodies for protein profiling of the human proteome, an important step in the quality control is to compare staining patterns of different antibodies directed towards the same protein. This comparison is an ultimate control that the antibody recognizes the right protein. In this paper, we propose and evaluate different approaches for classifying sub-cellular antibody staining patterns in breast tissue samples. The proposed methods include the computation of various features including gray level co-occurrence matrix (GLCM) features, complex wavelet co-occurrence matrix (CWCM) features, and weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHARM)-inspired features. The extracted features are used into two different multivariate classifiers (support vector machine (SVM) and linear discriminant analysis (LDA) classifier). Before extracting features, we use color deconvolution to separate different tissue components, such as the brownly stained positive regions and the blue cellular regions, in the immuno-stained TMA images of breast tissue. We present classification results based on combinations of feature measurements. The proposed complex wavelet features and the WND-CHARM features have accuracy similar to that of a human expert. Both human experts and the proposed automated methods have difficulties discriminating between nuclear and cytoplasmic staining patterns. This is to a large extent due to mixed staining of nucleus and cytoplasm. Methods for quantification of staining patterns in histopathology have many

Automated classification of immunostaining patterns in breast tissue from the human protein Atlas

Directory of Open Access Journals (Sweden)

Issac Niwas Swamidoss

2013-01-01

Full Text Available Background: The Human Protein Atlas (HPA is an effort to map the location of all human proteins (http://www.proteinatlas.org/. It contains a large number of histological images of sections from human tissue. Tissue micro arrays (TMA are imaged by a slide scanning microscope, and each image represents a thin slice of a tissue core with a dark brown antibody specific stain and a blue counter stain. When generating antibodies for protein profiling of the human proteome, an important step in the quality control is to compare staining patterns of different antibodies directed towards the same protein. This comparison is an ultimate control that the antibody recognizes the right protein. In this paper, we propose and evaluate different approaches for classifying sub-cellular antibody staining patterns in breast tissue samples. Materials and Methods: The proposed methods include the computation of various features including gray level co-occurrence matrix (GLCM features, complex wavelet co-occurrence matrix (CWCM features, and weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHARM-inspired features. The extracted features are used into two different multivariate classifiers (support vector machine (SVM and linear discriminant analysis (LDA classifier. Before extracting features, we use color deconvolution to separate different tissue components, such as the brownly stained positive regions and the blue cellular regions, in the immuno-stained TMA images of breast tissue. Results: We present classification results based on combinations of feature measurements. The proposed complex wavelet features and the WND-CHARM features have accuracy similar to that of a human expert. Conclusions: Both human experts and the proposed automated methods have difficulties discriminating between nuclear and cytoplasmic staining patterns. This is to a large extent due to mixed staining of nucleus and cytoplasm. Methods for

Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal.

Science.gov (United States)

Hosseinifard, Behshad; Moradi, Mohammad Hassan; Rostami, Reza

2013-03-01

Diagnosing depression in the early curable stages is very important and may even save the life of a patient. In this paper, we study nonlinear analysis of EEG signal for discriminating depression patients and normal controls. Forty-five unmedicated depressed patients and 45 normal subjects were participated in this study. Power of four EEG bands and four nonlinear features including detrended fluctuation analysis (DFA), higuchi fractal, correlation dimension and lyapunov exponent were extracted from EEG signal. For discriminating the two groups, k-nearest neighbor, linear discriminant analysis and logistic regression as the classifiers are then used. Highest classification accuracy of 83.3% is obtained by correlation dimension and LR classifier among other nonlinear features. For further improvement, all nonlinear features are combined and applied to classifiers. A classification accuracy of 90% is achieved by all nonlinear features and LR classifier. In all experiments, genetic algorithm is employed to select the most important features. The proposed technique is compared and contrasted with the other reported methods and it is demonstrated that by combining nonlinear features, the performance is enhanced. This study shows that nonlinear analysis of EEG can be a useful method for discriminating depressed patients and normal subjects. It is suggested that this analysis may be a complementary tool to help psychiatrists for diagnosing depressed patients. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

Evaluation of Classifier Performance for Multiclass Phenotype Discrimination in Untargeted Metabolomics.

Science.gov (United States)

Trainor, Patrick J; DeFilippis, Andrew P; Rai, Shesh N

2017-06-21

Statistical classification is a critical component of utilizing metabolomics data for examining the molecular determinants of phenotypes. Despite this, a comprehensive and rigorous evaluation of the accuracy of classification techniques for phenotype discrimination given metabolomics data has not been conducted. We conducted such an evaluation using both simulated and real metabolomics datasets, comparing Partial Least Squares-Discriminant Analysis (PLS-DA), Sparse PLS-DA, Random Forests, Support Vector Machines (SVM), Artificial Neural Network, k -Nearest Neighbors ( k -NN), and Naïve Bayes classification techniques for discrimination. We evaluated the techniques on simulated data generated to mimic global untargeted metabolomics data by incorporating realistic block-wise correlation and partial correlation structures for mimicking the correlations and metabolite clustering generated by biological processes. Over the simulation studies, covariance structures, means, and effect sizes were stochastically varied to provide consistent estimates of classifier performance over a wide range of possible scenarios. The effects of the presence of non-normal error distributions, the introduction of biological and technical outliers, unbalanced phenotype allocation, missing values due to abundances below a limit of detection, and the effect of prior-significance filtering (dimension reduction) were evaluated via simulation. In each simulation, classifier parameters, such as the number of hidden nodes in a Neural Network, were optimized by cross-validation to minimize the probability of detecting spurious results due to poorly tuned classifiers. Classifier performance was then evaluated using real metabolomics datasets of varying sample medium, sample size, and experimental design. We report that in the most realistic simulation studies that incorporated non-normal error distributions, unbalanced phenotype allocation, outliers, missing values, and dimension reduction

Using point-set compression to classify folk songs

DEFF Research Database (Denmark)

Meredith, David

2014-01-01

-neighbour algorithm and leave-one-out cross-validation to classify the 360 melodies into tune families. The classifications produced by the algorithms were compared with a ground-truth classification prepared by expert musicologists. Twelve of the thirteen compressors used in the experiment were based...... compared. The highest classification success rate of 77–84% was achieved by COSIATEC, followed by 60–64% for Forth’s algorithm and then 52–58% for SIATECCompress. When the NCDs were calculated using bzip2, the success rate was only 12.5%. The results demonstrate that the effectiveness of NCD for measuring...... similarity between folk-songs for classification purposes is highly dependent upon the actual compressor chosen. Furthermore, it seems that compressors based on finding maximal repeated patterns in point-set representations of music show more promise for NCD-based music classification than general...

Hierarchical mixtures of naive Bayes classifiers

NARCIS (Netherlands)

Wiering, M.A.

2002-01-01

Naive Bayes classifiers tend to perform very well on a large number of problem domains, although their representation power is quite limited compared to more sophisticated machine learning algorithms. In this pa- per we study combining multiple naive Bayes classifiers by using the hierar- chical

A Novel Cascade Classifier for Automatic Microcalcification Detection.

Directory of Open Access Journals (Sweden)

Seung Yeon Shin

Full Text Available In this paper, we present a novel cascaded classification framework for automatic detection of individual and clusters of microcalcifications (μC. Our framework comprises three classification stages: i a random forest (RF classifier for simple features capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated; ii a more complex discriminative restricted Boltzmann machine (DRBM classifier for μC candidates determined in the RF stage, which automatically learns the detailed morphology of μC appearances for improved discriminative power; and iii a detector to detect clusters of μCs from the individual μC detection results, using two different criteria. From the two-stage RF-DRBM classifier, we are able to distinguish μCs using explicitly computed features, as well as learn implicit features that are able to further discriminate between confusing cases. Experimental evaluation is conducted on the original Mammographic Image Analysis Society (MIAS and mini-MIAS databases, as well as our own Seoul National University Bundang Hospital digital mammographic database. It is shown that the proposed method outperforms comparable methods in terms of receiver operating characteristic (ROC and precision-recall curves for detection of individual μCs and free-response receiver operating characteristic (FROC curve for detection of clustered μCs.

A Supervised Multiclass Classifier for an Autocoding System

Directory of Open Access Journals (Sweden)

Yukako Toko

2017-11-01

Full Text Available Classification is often required in various contexts, including in the field of official statistics. In the previous study, we have developed a multiclass classifier that can classify short text descriptions with high accuracy. The algorithm borrows the concept of the naïve Bayes classifier and is so simple that its structure is easily understandable. The proposed classifier has the following two advantages. First, the processing times for both learning and classifying are extremely practical. Second, the proposed classifier yields high-accuracy results for a large portion of a dataset. We have previously developed an autocoding system for the Family Income and Expenditure Survey in Japan that has a better performing classifier. While the original system was developed in Perl in order to improve the efficiency of the coding process of short Japanese texts, the proposed system is implemented in the R programming language in order to explore versatility and is modified to make the system easily applicable to English text descriptions, in consideration of the increasing number of R users in the field of official statistics. We are planning to publish the proposed classifier as an R-package. The proposed classifier would be generally applicable to other classification tasks including coding activities in the field of official statistics, and it would contribute greatly to improving their efficiency.

Analysis of plant LTR-retrotransposons at the fine-scale family level reveals individual molecular patterns

Directory of Open Access Journals (Sweden)

Domingues Douglas S

2012-04-01

Full Text Available Abstract Background Sugarcane is an important crop worldwide for sugar production and increasingly, as a renewable energy source. Modern cultivars have polyploid, large complex genomes, with highly unequal contributions from ancestral genomes. Long Terminal Repeat retrotransposons (LTR-RTs are the single largest components of most plant genomes and can substantially impact the genome in many ways. It is therefore crucial to understand their contribution to the genome and transcriptome, however a detailed study of LTR-RTs in sugarcane has not been previously carried out. Results Sixty complete LTR-RT elements were classified into 35 families within four Copia and three Gypsy lineages. Structurally, within lineages elements were similar, between lineages there were large size differences. FISH analysis resulted in the expected pattern of Gypsy/heterochromatin, Copia/euchromatin, but in two lineages there was localized clustering on some chromosomes. Analysis of related ESTs and RT-PCR showed transcriptional variation between tissues and families. Four distinct patterns were observed in sRNA mapping, the most unusual of which was that of Ale1, with very large numbers of 24nt sRNAs in the coding region. The results presented support the conclusion that distinct small RNA-regulated pathways in sugarcane target the lineages of LTR-RT elements. Conclusions Individual LTR-RT sugarcane families have distinct structures, and transcriptional and regulatory signatures. Our results indicate that in sugarcane individual LTR-RT families have distinct behaviors and can potentially impact the genome in diverse ways. For instance, these transposable elements may affect nearby genes by generating a diverse set of small RNA's that trigger gene silencing mechanisms. There is also some evidence that ancestral genomes contribute significantly different element numbers from particular LTR-RT lineages to the modern sugarcane cultivar genome.

Immunohistochemical analysis of breast tissue microarray images using contextual classifiers

Directory of Open Access Journals (Sweden)

Stephen J McKenna

2013-01-01

Full Text Available Background: Tissue microarrays (TMAs are an important tool in translational research for examining multiple cancers for molecular and protein markers. Automatic immunohistochemical (IHC scoring of breast TMA images remains a challenging problem. Methods: A two-stage approach that involves localization of regions of invasive and in-situ carcinoma followed by ordinal IHC scoring of nuclei in these regions is proposed. The localization stage classifies locations on a grid as tumor or non-tumor based on local image features. These classifications are then refined using an auto-context algorithm called spin-context. Spin-context uses a series of classifiers to integrate image feature information with spatial context information in the form of estimated class probabilities. This is achieved in a rotationally-invariant manner. The second stage estimates ordinal IHC scores in terms of the strength of staining and the proportion of nuclei stained. These estimates take the form of posterior probabilities, enabling images with uncertain scores to be referred for pathologist review. Results: The method was validated against manual pathologist scoring on two nuclear markers, progesterone receptor (PR and estrogen receptor (ER. Errors for PR data were consistently lower than those achieved with ER data. Scoring was in terms of estimated proportion of cells that were positively stained (scored on an ordinal scale of 0-6 and perceived strength of staining (scored on an ordinal scale of 0-3. Average absolute differences between predicted scores and pathologist-assigned scores were 0.74 for proportion of cells and 0.35 for strength of staining (PR. Conclusions: The use of context information via spin-context improved the precision and recall of tumor localization. The combination of the spin-context localization method with the automated scoring method resulted in reduced IHC scoring errors.

Development and analysis of a low-cost screening tool to identify and classify hearing loss in children: a proposal for developing countries

Directory of Open Access Journals (Sweden)

Alessandra Giannella Samelli

2011-01-01

Full Text Available OBJECTIVE: A lack of attention has been given to hearing health in primary care in developing countries. A strategy involving low-cost screening tools may fill the current gap in hearing health care provided to children. Therefore, it is necessary to establish and adopt lower-cost procedures that are accessible to underserved areas that lack other physical or human resources that would enable the identification of groups at risk for hearing loss. The aim of this study was to develop and analyze the efficacy of a low-cost screening tool to identify and classify hearing loss in children. METHODS: A total of 214 2-to-10 year-old children participated in this study. The study was conducted by providing a questionnaire to the parents and comparing the answers with the results of a complete audiological assessment. Receiver operating characteristic (ROC curves were constructed, and discriminant analysis techniques were used to classify each child based on the total score. RESULTS: We found conductive hearing loss in 39.3% of children, sensorineural hearing loss in 7.4% and normal hearing in 53.3%. The discriminant analysis technique provided the following classification rule for the total score on the questionnaire: 0 to 4 points - normal hearing; 5 to 7 points - conductive hearing loss; over 7 points - sensorineural hearing loss. CONCLUSION: Our results suggest that the questionnaire could be used as a screening tool to classify children with normal hearing or hearing loss and according to the type of hearing loss based on the total questionnaire score

A Western Dietary Pattern Increases Prostate Cancer Risk: A Systematic Review and Meta-Analysis.

Science.gov (United States)

Fabiani, Roberto; Minelli, Liliana; Bertarelli, Gaia; Bacci, Silvia

2016-10-12

Dietary patterns were recently applied to examine the relationship between eating habits and prostate cancer (PC) risk. While the associations between PC risk with the glycemic index and Mediterranean score have been reviewed, no meta-analysis is currently available on dietary patterns defined by "a posteriori" methods. A literature search was carried out (PubMed, Web of Science) to identify studies reporting the relationship between dietary patterns and PC risk. Relevant dietary patterns were selected and the risks estimated were calculated by a random-effect model. Multivariable-adjusted odds ratios (ORs), for a first-percentile increase in dietary pattern score, were combined by a dose-response meta-analysis. Twelve observational studies were included in the meta-analysis which identified a "Healthy pattern" and a "Western pattern". The Healthy pattern was not related to PC risk (OR = 0.96; 95% confidence interval (CI): 0.88-1.04) while the Western pattern significantly increased it (OR = 1.34; 95% CI: 1.08-1.65). In addition, the "Carbohydrate pattern", which was analyzed in four articles, was positively associated with a higher PC risk (OR = 1.64; 95% CI: 1.35-2.00). A significant linear trend between the Western ( p = 0.011) pattern, the Carbohydrate ( p = 0.005) pattern, and the increment of PC risk was observed. The small number of studies included in the meta-analysis suggests that further investigation is necessary to support these findings.

Comparative analysis of taxonomic, functional, and metabolic patterns of microbiomes from 14 full-scale biogas reactors by metagenomic sequencing and radioisotopic analysis.

Science.gov (United States)

Luo, Gang; Fotidis, Ioannis A; Angelidaki, Irini

2016-01-01

Biogas production is a very complex process due to the high complexity in diversity and interactions of the microorganisms mediating it, and only limited and diffuse knowledge exists about the variation of taxonomic and functional patterns of microbiomes across different biogas reactors, and their relationships with the metabolic patterns. The present study used metagenomic sequencing and radioisotopic analysis to assess the taxonomic, functional, and metabolic patterns of microbiomes from 14 full-scale biogas reactors operated under various conditions treating either sludge or manure. The results from metagenomic analysis showed that the dominant methanogenic pathway revealed by radioisotopic analysis was not always correlated with the taxonomic and functional compositions. It was found by radioisotopic experiments that the aceticlastic methanogenic pathway was dominant, while metagenomics analysis showed higher relative abundance of hydrogenotrophic methanogens. Principal coordinates analysis showed the sludge-based samples were clearly distinct from the manure-based samples for both taxonomic and functional patterns, and canonical correspondence analysis showed that the both temperature and free ammonia were crucial environmental variables shaping the taxonomic and functional patterns. The study further the overall patterns of functional genes were strongly correlated with overall patterns of taxonomic composition across different biogas reactors. The discrepancy between the metabolic patterns determined by metagenomic analysis and metabolic pathways determined by radioisotopic analysis was found. Besides, a clear correlation between taxonomic and functional patterns was demonstrated for biogas reactors, and also the environmental factors that shaping both taxonomic and functional genes patterns were identified.

A Learning Outcome-Oriented Approach towards Classifying Pervasive Games for Learning Using Game Design Patterns and Contextual Information

Science.gov (United States)

Schmitz, Birgit; Klemke, Roland; Specht, Marcus

2013-01-01

Mobile and in particular pervasive games are a strong component of future scenarios for teaching and learning. Based on results from a previous review of practical papers, this work explores the educational potential of pervasive games for learning by analysing underlying game mechanisms. In order to determine and classify cognitive and affective…

Logarithmic learning for generalized classifier neural network.

Science.gov (United States)

Ozyildirim, Buse Melis; Avci, Mutlu

2014-12-01

Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning approach is proposed. The proposed method uses logarithmic cost function instead of squared error. Minimization of this cost function reduces the number of iterations used for reaching the minima. The proposed method is tested on 15 different data sets and performance of logarithmic learning generalized classifier neural network is compared with that of standard one. Thanks to operation range of radial basis function included by generalized classifier neural network, proposed logarithmic approach and its derivative has continuous values. This makes it possible to adopt the advantage of logarithmic fast convergence by the proposed learning method. Due to fast convergence ability of logarithmic cost function, training time is maximally decreased to 99.2%. In addition to decrease in training time, classification performance may also be improved till 60%. According to the test results, while the proposed method provides a solution for time requirement problem of generalized classifier neural network, it may also improve the classification accuracy. The proposed method can be considered as an efficient way for reducing the time requirement problem of generalized classifier neural network. Copyright © 2014 Elsevier Ltd. All rights reserved.

Driving Style Analysis Using Primitive Driving Patterns With Bayesian Nonparametric Approaches

OpenAIRE

Wang, Wenshuo; Xi, Junqiang; Zhao, Ding

2017-01-01

Analysis and recognition of driving styles are profoundly important to intelligent transportation and vehicle calibration. This paper presents a novel driving style analysis framework using the primitive driving patterns learned from naturalistic driving data. In order to achieve this, first, a Bayesian nonparametric learning method based on a hidden semi-Markov model (HSMM) is introduced to extract primitive driving patterns from time series driving data without prior knowledge of the number...

Using Conditional Analysis to Investigate Spatial and Temporal patterns in Upland Rainfall

Science.gov (United States)

Sakamoto Ferranti, Emma Jayne; Whyatt, James Duncan; Timmis, Roger James

2010-05-01

The seasonality and characteristics of rainfall in the UK are altering under a changing climate. Summer rainfall is generally decreasing whereas winter rainfall is increasing, particularly in northern and western areas (Maraun et al., 2008) and recent research suggests these rainfall increases are amplified in upland areas (Burt and Ferranti, 2010). Conditional analysis has been used to investigate these rainfall patterns in Cumbria, an upland area in northwest England. Cumbria was selected as an example of a topographically diverse mid-latitude region that has a predominately maritime and westerly-defined climate. Moreover it has a dense network of more than 400 rain gauges that have operated for periods between 1900 and present day. Cumbria has experienced unprecedented flooding in the past decade and understanding the spatial and temporal changes in this and other upland regions is important for water resource and ecosystem management. The conditional analysis method examines the spatial and temporal variations in rainfall under different synoptic conditions and in different geographic sub-regions (Ferranti et al., 2009). A daily synoptic typing scheme, the Lamb Weather Catalogue, was applied to classify rainfall into different weather types, for example: south-westerly, westerly, easterly or cyclonic. Topographic descriptors developed using GIS were used to classify rain gauges into 6 directionally-dependant geographic sub-regions: coastal, windward-lowland, windward-upland, leeward-upland, leeward-lowland, secondary upland. Combining these classification methods enabled seasonal rainfall climatologies to be produced for specific weather types and sub-regions. Winter rainfall climatologies were constructed for all 6 sub-regions for 3 weather types - south-westerly (SW), westerly (W), and cyclonic (C); these weather types contribute more than 50% of total winter rainfall. The frequency of wet-days (>0.3mm), the total winter rainfall and the average wet day

Analysis of metabolomic patterns in thoroughbreds before and after exercise

Directory of Open Access Journals (Sweden)

Hyun-Jun Jang

2017-11-01

Full Text Available Objective Evaluation of exercise effects in racehorses is important in horseracing industry and animal health care. In this study, we compared metabolic patterns between before and after exercise to screen metabolic biomarkers for exercise effects in thoroughbreds. Methods The concentration of metabolites in muscle, plasma, and urine was measured by 1H nuclear magnetic resonance (NMR spectroscopy analysis and the relative metabolite levels in the three samples were compared between before and after exercise. Subsequently, multivariate data analysis based on the metabolic profiles was performed using orthogonal partial least square discriminant analysis (OPLS-DA and variable important plots and t-test was used for basic statistical analysis. Results From 1H NMR spectroscopy analysis, 35, 25, and 34 metabolites were detected in the muscle, plasma, and urine. Aspartate, betaine, choline, cysteine, ethanol, and threonine were increased over 2-fold in the muscle; propionate and trimethylamine were increased over 2-fold in the plasma; and alanine, glycerol, inosine, lactate, and pyruvate were increased over 2-fold whereas acetoacetate, arginine, citrulline, creatine, glutamine, glutarate, hippurate, lysine, methionine, phenylacetylglycine, taurine, trigonelline, trimethylamine, and trimethylamine N-oxide were decreased below 0.5-fold in the urine. The OPLS-DA showed clear separation of the metabolic patterns before and after exercise in the muscle, plasma, and urine. Statistical analysis showed that after exercise, acetoacetate, arginine, glutamine, hippurate, phenylacetylglycine trimethylamine, trimethylamine N-oxide, and trigonelline were significantly decreased and alanine, glycerol, inosine, lactate, and pyruvate were significantly increased in the urine (p<0.05. Conclusion In conclusion, we analyzed integrated metabolic patterns in the muscle, plasma, and urine before and after exercise in racehorses. We found changed patterns of metabolites in

DECISION TREE CLASSIFIERS FOR STAR/GALAXY SEPARATION

International Nuclear Information System (INIS)

Vasconcellos, E. C.; Ruiz, R. S. R.; De Carvalho, R. R.; Capelato, H. V.; Gal, R. R.; LaBarbera, F. L.; Frago Campos Velho, H.; Trevisan, M.

2011-01-01

We study the star/galaxy classification efficiency of 13 different decision tree algorithms applied to photometric objects in the Sloan Digital Sky Survey Data Release Seven (SDSS-DR7). Each algorithm is defined by a set of parameters which, when varied, produce different final classification trees. We extensively explore the parameter space of each algorithm, using the set of 884,126 SDSS objects with spectroscopic data as the training set. The efficiency of star-galaxy separation is measured using the completeness function. We find that the Functional Tree algorithm (FT) yields the best results as measured by the mean completeness in two magnitude intervals: 14 ≤ r ≤ 21 (85.2%) and r ≥ 19 (82.1%). We compare the performance of the tree generated with the optimal FT configuration to the classifications provided by the SDSS parametric classifier, 2DPHOT, and Ball et al. We find that our FT classifier is comparable to or better in completeness over the full magnitude range 15 ≤ r ≤ 21, with much lower contamination than all but the Ball et al. classifier. At the faintest magnitudes (r > 19), our classifier is the only one that maintains high completeness (>80%) while simultaneously achieving low contamination (∼2.5%). We also examine the SDSS parametric classifier (psfMag - modelMag) to see if the dividing line between stars and galaxies can be adjusted to improve the classifier. We find that currently stars in close pairs are often misclassified as galaxies, and suggest a new cut to improve the classifier. Finally, we apply our FT classifier to separate stars from galaxies in the full set of 69,545,326 SDSS photometric objects in the magnitude range 14 ≤ r ≤ 21.

Evaluation of mammographic density patterns: reproducibility and concordance among scales

Directory of Open Access Journals (Sweden)

Garrido-Estepa Macarena

2010-09-01

Full Text Available Abstract Background Increased mammographic breast density is a moderate risk factor for breast cancer. Different scales have been proposed for classifying mammographic density. This study sought to assess intra-rater agreement for the most widely used scales (Wolfe, Tabár, BI-RADS and Boyd and compare them in terms of classifying mammograms as high- or low-density. Methods The study covered 3572 mammograms drawn from women included in the DDM-Spain study, carried-out in seven Spanish Autonomous Regions. Each mammogram was read by an expert radiologist and classified using the Wolfe, Tabár, BI-RADS and Boyd scales. In addition, 375 mammograms randomly selected were read a second time to estimate intra-rater agreement for each scale using the kappa statistic. Owing to the ordinal nature of the scales, weighted kappa was computed. The entire set of mammograms (3572 was used to calculate agreement among the different scales in classifying high/low-density patterns, with the kappa statistic being computed on a pair-wise basis. High density was defined as follows: percentage of dense tissue greater than 50% for the Boyd, "heterogeneously dense and extremely dense" categories for the BI-RADS, categories P2 and DY for the Wolfe, and categories IV and V for the Tabár scales. Results There was good agreement between the first and second reading, with weighted kappa values of 0.84 for Wolfe, 0.71 for Tabár, 0.90 for BI-RADS, and 0.92 for Boyd scale. Furthermore, there was substantial agreement among the different scales in classifying high- versus low-density patterns. Agreement was almost perfect between the quantitative scales, Boyd and BI-RADS, and good for those based on the observed pattern, i.e., Tabár and Wolfe (kappa 0.81. Agreement was lower when comparing a pattern-based (Wolfe or Tabár versus a quantitative-based (BI-RADS or Boyd scale. Moreover, the Wolfe and Tabár scales classified more mammograms in the high-risk group, 46.61 and 37

Qualitative Analysis of Primary Fingerprint Pattern in Different Blood Group and Gender in Nepalese

Directory of Open Access Journals (Sweden)

Sudikshya KC

2018-01-01

Full Text Available Dermatoglyphics, the study of epidermal ridges on palm, sole, and digits, is considered as most effective and reliable evidence of identification. The fingerprints were studied in 300 Nepalese of known blood groups of different ages and classified into primary patterns and then analyzed statistically. In both sexes, incidence of loops was highest in ABO blood group and Rh +ve blood types, followed by whorls and arches, while the incidence of whorls was highest followed by loops and arches in Rh −ve blood types. Loops were higher in all blood groups except “A –ve” and “B –ve” where whorls were predominant. The fingerprint pattern in Rh blood types of blood group “A” was statistically significant while in others it was insignificant. In middle and little finger, loops were higher whereas in ring finger whorls were higher in all blood groups. Whorls were higher in thumb and index finger except in blood group “O” where loops were predominant. This study concludes that distribution of primary pattern of fingerprint is not related to gender and blood group but is related to individual digits.

Identification of flooded area from satellite images using Hybrid Kohonen Fuzzy C-Means sigma classifier

Directory of Open Access Journals (Sweden)

Krishna Kant Singh

2017-06-01

Full Text Available A novel neuro fuzzy classifier Hybrid Kohonen Fuzzy C-Means-σ (HKFCM-σ is proposed in this paper. The proposed classifier is a hybridization of Kohonen Clustering Network (KCN with FCM-σ clustering algorithm. The network architecture of HKFCM-σ is similar to simple KCN network having only two layers, i.e., input and output layer. However, the selection of winner neuron is done based on FCM-σ algorithm. Thus, embedding the features of both, a neural network and a fuzzy clustering algorithm in the classifier. This hybridization results in a more efficient, less complex and faster classifier for classifying satellite images. HKFCM-σ is used to identify the flooding that occurred in Kashmir area in September 2014. The HKFCM-σ classifier is applied on pre and post flooding Landsat 8 OLI images of Kashmir to detect the areas that were flooded due to the heavy rainfalls of September, 2014. The classifier is trained using the mean values of the various spectral indices like NDVI, NDWI, NDBI and first component of Principal Component Analysis. The error matrix was computed to test the performance of the method. The method yields high producer’s accuracy, consumer’s accuracy and kappa coefficient value indicating that the proposed classifier is highly effective and efficient.

Laban Movement Analysis towards Behavior Patterns

Science.gov (United States)

Santos, Luís; Dias, Jorge

This work presents a study about the use of Laban Movement Analysis (LMA) as a robust tool to describe human basic behavior patterns, to be applied in human-machine interaction. LMA is a language used to describe and annotate dancing movements and is divided in components [1]: Body, Space, Shape and Effort. Despite its general framework is widely used in physical and mental therapy [2], it has found little application in the engineering domain. Rett J. [3] proposed to implement LMA using Bayesian Networks. However LMA component models have not yet been fully implemented. A study on how to approach behavior using LMA is presented. Behavior is a complex feature and movement chain, but we believe that most basic behavior primitives can be discretized in simple features. Correctly identifying Laban parameters and the movements the authors feel that good patterns can be found within a specific set of basic behavior semantics.

Word2Vec inversion and traditional text classifiers for phenotyping lupus.

Science.gov (United States)

Turner, Clayton A; Jacobs, Alexander D; Marques, Cassios K; Oates, James C; Kamen, Diane L; Anderson, Paul E; Obeid, Jihad S

2017-08-22

Identifying patients with certain clinical criteria based on manual chart review of doctors' notes is a daunting task given the massive amounts of text notes in the electronic health records (EHR). This task can be automated using text classifiers based on Natural Language Processing (NLP) techniques along with pattern recognition machine learning (ML) algorithms. The aim of this research is to evaluate the performance of traditional classifiers for identifying patients with Systemic Lupus Erythematosus (SLE) in comparison with a newer Bayesian word vector method. We obtained clinical notes for patients with SLE diagnosis along with controls from the Rheumatology Clinic (662 total patients). Sparse bag-of-words (BOWs) and Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs) matrices were produced using NLP pipelines. These matrices were subjected to several different NLP classifiers: neural networks, random forests, naïve Bayes, support vector machines, and Word2Vec inversion, a Bayesian inversion method. Performance was measured by calculating accuracy and area under the Receiver Operating Characteristic (ROC) curve (AUC) of a cross-validated (CV) set and a separate testing set. We calculated the accuracy of the ICD-9 billing codes as a baseline to be 90.00% with an AUC of 0.900, the shallow neural network with CUIs to be 92.10% with an AUC of 0.970, the random forest with BOWs to be 95.25% with an AUC of 0.994, the random forest with CUIs to be 95.00% with an AUC of 0.979, and the Word2Vec inversion to be 90.03% with an AUC of 0.905. Our results suggest that a shallow neural network with CUIs and random forests with both CUIs and BOWs are the best classifiers for this lupus phenotyping task. The Word2Vec inversion method failed to significantly beat the ICD-9 code classification, but yielded promising results. This method does not require explicit features and is more adaptable to non-binary classification tasks. The Word2Vec inversion is

Cluster analysis

CERN Document Server

Everitt, Brian S; Leese, Morven; Stahl, Daniel

2011-01-01

Cluster analysis comprises a range of methods for classifying multivariate data into subgroups. By organizing multivariate data into such subgroups, clustering can help reveal the characteristics of any structure or patterns present. These techniques have proven useful in a wide range of areas such as medicine, psychology, market research and bioinformatics.This fifth edition of the highly successful Cluster Analysis includes coverage of the latest developments in the field and a new chapter dealing with finite mixture models for structured data.Real life examples are used throughout to demons

32 CFR 2400.28 - Dissemination of classified information.

Science.gov (United States)

2010-07-01

... 32 National Defense 6 2010-07-01 2010-07-01 false Dissemination of classified information. 2400.28... SECURITY PROGRAM Safeguarding § 2400.28 Dissemination of classified information. Heads of OSTP offices... originating official may prescribe specific restrictions on dissemination of classified information when...

Parent Involvement and Science Achievement: A Cross-Classified Multilevel Latent Growth Curve Analysis

Science.gov (United States)

Johnson, Ursula Y.; Hull, Darrell M.

2014-01-01

The authors examined science achievement growth at Grades 3, 5, and 8 and parent school involvement at the same time points using the Early Childhood Longitudinal Study-Kindergarten Class of 1998-1999. Data were analyzed using cross-classified multilevel latent growth curve modeling with time invariant and varying covariates. School-based…

An analysis of error patterns in children's backward digit recall in noise

Science.gov (United States)

Osman, Homira; Sullivan, Jessica R.

2015-01-01

The purpose of the study was to determine whether perceptual masking or cognitive processing accounts for a decline in working memory performance in the presence of competing speech. The types and patterns of errors made on the backward digit span in quiet and multitalker babble at -5 dB signal-to-noise ratio (SNR) were analyzed. The errors were classified into two categories: item (if digits that were not presented in a list were repeated) and order (if correct digits were repeated but in an incorrect order). Fifty five children with normal hearing were included. All the children were aged between 7 years and 10 years. Repeated measures of analysis of variance (RM-ANOVA) revealed the main effects for error type and digit span length. In terms of listening condition interaction it was found that the order errors occurred more frequently than item errors in the degraded listening condition compared to quiet. In addition, children had more difficulty recalling the correct order of intermediate items, supporting strong primacy and recency effects. Decline in children's working memory performance was not primarily related to perceptual difficulties alone. The majority of errors was related to the maintenance of sequential order information, which suggests that reduced performance in competing speech may result from increased cognitive processing demands in noise. PMID:26168949

[Scale effect of Nanjing urban green infrastructure network pattern and connectivity analysis.

Science.gov (United States)

Yu, Ya Ping; Yin, Hai Wei; Kong, Fan Hua; Wang, Jing Jing; Xu, Wen Bin

2016-07-01

Based on ArcGIS, Erdas, GuidosToolbox, Conefor and other software platforms, using morphological spatial pattern analysis (MSPA) and landscape connectivity analysis methods, this paper quantitatively analysed the scale effect, edge effect and distance effect of the Nanjing urban green infrastructure network pattern in 2013 by setting different pixel sizes (P) and edge widths in MSPA analysis, and setting different dispersal distance thresholds in landscape connectivity analysis. The results showed that the type of landscape acquired based on the MSPA had a clear scale effect and edge effect, and scale effects only slightly affected landscape types, whereas edge effects were more obvious. Different dispersal distances had a great impact on the landscape connectivity, 2 km or 2.5 km dispersal distance was a critical threshold for Nanjing. When selecting the pixel size 30 m of the input data and the edge wide 30 m used in the morphological model, we could get more detailed landscape information of Nanjing UGI network. Based on MSPA and landscape connectivity, analysis of the scale effect, edge effect, and distance effect on the landscape types of the urban green infrastructure (UGI) network was helpful for selecting the appropriate size, edge width, and dispersal distance when developing these networks, and for better understanding the spatial pattern of UGI networks and the effects of scale and distance on the ecology of a UGI network. This would facilitate a more scientifically valid set of design parameters for UGI network spatiotemporal pattern analysis. The results of this study provided an important reference for Nanjing UGI networks and a basis for the analysis of the spatial and temporal patterns of medium-scale UGI landscape networks in other regions.

An Analysis of Interaction Patterns in the Focus Group Interview

Directory of Open Access Journals (Sweden)

Gavora Peter

2015-12-01

Full Text Available This paper is based on the analysis of a focus group interview of a moderator and a group of undergraduate students on the topic of self-regulation of learning. The purpose of the investigation was to identify interaction patterns that appeared in the talk of participants and the moderator. In the stream of communication two rudimentary interaction patterns were recognized. The first pattern was named the Catalogue. It consists of a sequence of turns of participants who respond to a request of the moderator and who provide their answers, one by one, without reacting on the content of the previous partner(s talk. The other interaction pattern was called the Domino. In this pattern participants respond to each other. The Catalogue pattern prevailed in the interview. Alongside with identification of patterns of interaction the study demonstrated the functions of the common ground and its accomplishment in the talk of the moderator and participants.

Artificial immune pattern recognition for damage detection in structural health monitoring sensor networks

Science.gov (United States)

Chen, Bo; Zang, Chuanzhi

2009-03-01

This paper presents an artificial immune pattern recognition (AIPR) approach for the damage detection and classification in structures. An AIPR-based Structure Damage Classifier (AIPR-SDC) has been developed by mimicking immune recognition and learning mechanisms. The structure damage patterns are represented by feature vectors that are extracted from the structure's dynamic response measurements. The training process is designed based on the clonal selection principle in the immune system. The selective and adaptive features of the clonal selection algorithm allow the classifier to generate recognition feature vectors that are able to match the training data. In addition, the immune learning algorithm can learn and remember various data patterns by generating a set of memory cells that contains representative feature vectors for each class (pattern). The performance of the presented structure damage classifier has been validated using a benchmark structure proposed by the IASC-ASCE (International Association for Structural Control - American Society of Civil Engineers) Structural Health Monitoring Task Group. The validation results show a better classification success rate comparing to some of other classification algorithms.

Longitudinal Patterns of Glycemic Control and Blood Pressure in Pregnant Women with Type 1 Diabetes Mellitus: Phenotypes from Functional Data Analysis.

Science.gov (United States)

Szczesniak, Rhonda D; Li, Dan; Duan, Leo L; Altaye, Mekibib; Miodovnik, Menachem; Khoury, Jane C

2016-11-01

Objective  To identify phenotypes of type 1 diabetes control and associations with maternal/neonatal characteristics based on blood pressure (BP), glucose, and insulin curves during gestation, using a novel functional data analysis approach that accounts for sparse longitudinal patterns of medical monitoring during pregnancy. Methods  We performed a retrospective longitudinal cohort study of women with type 1 diabetes whose BP, glucose, and insulin requirements were monitored throughout gestation as part of a program-project grant. Scores from sparse functional principal component analysis (fPCA) were used to classify gestational profiles according to the degree of control for each monitored measure. Phenotypes created using fPCA were compared with respect to maternal and neonatal characteristics and outcome. Results  Most of the gestational profile variation in the monitored measures was explained by the first principal component (82-94%). Profiles clustered into three subgroups of high, moderate, or low heterogeneity, relative to the overall mean response. Phenotypes were associated with baseline characteristics, longitudinal changes in glycohemoglobin A1 and weight, and to pregnancy-related outcomes. Conclusion  Three distinct longitudinal patterns of glucose, insulin, and BP control were found. By identifying these phenotypes, interventions can be targeted for subgroups at highest risk for compromised outcome, to optimize diabetes management during pregnancy. Thieme Medical Publishers 333 Seventh Avenue, New York, NY 10001, USA.

Long-term patterns of dental attendance and caries experience among British adults: a retrospective analysis.

Science.gov (United States)

Aldossary, Arwa; Harrison, Victoria E; Bernabé, Eduardo

2015-02-01

There is inconclusive evidence on the value of regular dental attendance. This study explored the relationship between long-term patterns of dental attendance and caries experience. We used retrospective data from 3,235 adults, ≥ 16 yrs of age, who participated in the Adult Dental Health Survey in the UK. Participants were classified into four groups (always, current, former, and never regular-attenders) based on their responses to three questions on lifetime dental-attendance patterns. The association between dental-attendance patterns and caries experience, as measured using the decayed, missing, or filled teeth (DMFT) index, was tested in negative binomial regression models, adjusting for demographic (sex, age, and country of residence) and socio-economic (educational attainment, household income, and social class) factors. A consistent pattern of association between long-term dental attendance and caries experience was found in adjusted models. Former and never regular-attenders had a significantly higher DMFT score and numbers of decayed and missing teeth, but fewer filled teeth, than always regular-attenders. No differences in DMFT or its components were found between current and always regular-attenders. The findings of this study show that adults with different lifetime trajectories of dental attendance had different dental statuses. © 2014 Eur J Oral Sci.

Comprehensive benchmarking and ensemble approaches for metagenomic classifiers.

Science.gov (United States)

McIntyre, Alexa B R; Ounit, Rachid; Afshinnekoo, Ebrahim; Prill, Robert J; Hénaff, Elizabeth; Alexander, Noah; Minot, Samuel S; Danko, David; Foox, Jonathan; Ahsanuddin, Sofia; Tighe, Scott; Hasan, Nur A; Subramanian, Poorani; Moffat, Kelly; Levy, Shawn; Lonardi, Stefano; Greenfield, Nick; Colwell, Rita R; Rosen, Gail L; Mason, Christopher E

2017-09-21

One of the main challenges in metagenomics is the identification of microorganisms in clinical and environmental samples. While an extensive and heterogeneous set of computational tools is available to classify microorganisms using whole-genome shotgun sequencing data, comprehensive comparisons of these methods are limited. In this study, we use the largest-to-date set of laboratory-generated and simulated controls across 846 species to evaluate the performance of 11 metagenomic classifiers. Tools were characterized on the basis of their ability to identify taxa at the genus, species, and strain levels, quantify relative abundances of taxa, and classify individual reads to the species level. Strikingly, the number of species identified by the 11 tools can differ by over three orders of magnitude on the same datasets. Various strategies can ameliorate taxonomic misclassification, including abundance filtering, ensemble approaches, and tool intersection. Nevertheless, these strategies were often insufficient to completely eliminate false positives from environmental samples, which are especially important where they concern medically relevant species. Overall, pairing tools with different classification strategies (k-mer, alignment, marker) can combine their respective advantages. This study provides positive and negative controls, titrated standards, and a guide for selecting tools for metagenomic analyses by comparing ranges of precision, accuracy, and recall. We show that proper experimental design and analysis parameters can reduce false positives, provide greater resolution of species in complex metagenomic samples, and improve the interpretation of results.

Switching field distribution and magnetization reversal process of FePt dot patterns

Energy Technology Data Exchange (ETDEWEB)

Ishio, S., E-mail: ishio@gipc.akita-u.ac.jp [Department of Materials Science and Engineering, Akita University, Akita 010-8502 (Japan); Takahashi, S.; Hasegawa, T.; Arakawa, A.; Sasaki, H. [Department of Materials Science and Engineering, Akita University, Akita 010-8502 (Japan); Yan, Z.; Liu, X. [Venture Business Laboratory, Akita University, Tegata Gakuen-machi, Akita 010-8502 (Japan); Kondo, Y.; Yamane, H.; Ariake, J. [Akita Prefectural R and D Center, 4-21 Sanuki, Akita 010-1623 (Japan); Suzuki, M.; Kawamura, N.; Mizumaki, M. [Japan Synchrotron Radiation Research Institute, 1-1-1, Kouto, Sayo-cho, Sayo-gun, Hyogo 679-5198 (Japan)

2014-06-01

The fabrication of FePt nanodots with a high structural quality and the control of their switching fields are key issues in realizing high density bit pattern recording. We have prepared FePt dot patterns for dots with 15–300 nm diameters by electron beam lithography and re-annealing, and studied the relation between magnetization reversal process and structure of FePt nanodots. The switching field (H{sub sw}) of dot patterns re-annealed at 710 °C for 240 min showed a bimodal distribution, where a higher peak was found at 5–6 T, and a lower peak was found at ∼2 T. It was revealed by cross-sectional TEM analysis that the structure of dots in the pattern can be classified into two groups. One group has a high degree of order with well-defined [0 0 1] crystalline growth, and the other group includes structurally-disturbed dots like [1 1 1] growth and twin crystals. This structural inhomogeneity causes the magnetic switching field distribution observed. - Highlights: • FePt dot patterns with 15–100 nm dot diameters were prepared by EB lithography. • Maximum coercivity of 30 kOe was found in the dot pattern with 30 nm in diameter. • Magnetization reversal was studied on the base of TEM analysis and LLG simulation.

[Applications of 2D and 3D landscape pattern indices in landscape pattern analysis of mountainous area at county level].

Science.gov (United States)

Lu, Chao; Qi, Wei; Li, Le; Sun, Yao; Qin, Tian-Tian; Wang, Na-Na

2012-05-01

Landscape pattern indices are the commonly used tools for the quantitative analysis of landscape pattern. However, the traditional 2D landscape pattern indices neglect the effects of terrain on landscape, existing definite limitations in quantitatively describing the landscape patterns in mountains areas. Taking the Qixia City, a typical mountainous and hilly region in Shandong Province of East China, as a case, this paper compared the differences between 2D and 3D landscape pattern indices in quantitatively describing the landscape patterns and their dynamic changes in mountainous areas. On the basis of terrain structure analysis, a set of landscape pattern indices were selected, including area and density (class area and mean patch size), edge and shape (edge density, landscape shape index, and fractal dimension of mean patch), diversity (Shannon's diversity index and evenness index) , and gathering and spread (contagion index). There existed obvious differences between the 3D class area, mean patch area, and edge density and the corresponding 2D indices, but no significant differences between the 3D landscape shape index, fractal dimension of mean patch, and Shannon' s diversity index and evenness index and the corresponding 2D indices. The 3D contagion index and 2D contagion index had no difference. Because the 3D landscape pattern indices were calculated by using patch surface area and surface perimeter whereas the 2D landscape pattern indices were calculated by adopting patch projective area and projective perimeter, the 3D landscape pattern indices could be relative accurate and efficient in describing the landscape area, density and borderline, in mountainous areas. However, there were no distinct differences in describing landscape shape, diversity, and gathering and spread between the 3D and 2D landscape pattern indices. Generally, by introducing 3D landscape pattern indices to topographic pattern, the description of landscape pattern and its dynamic

Mercury⊕: An evidential reasoning image classifier

Science.gov (United States)

Peddle, Derek R.

1995-12-01

MERCURY⊕ is a multisource evidential reasoning classification software system based on the Dempster-Shafer theory of evidence. The design and implementation of this software package is described for improving the classification and analysis of multisource digital image data necessary for addressing advanced environmental and geoscience applications. In the remote-sensing context, the approach provides a more appropriate framework for classifying modern, multisource, and ancillary data sets which may contain a large number of disparate variables with different statistical properties, scales of measurement, and levels of error which cannot be handled using conventional Bayesian approaches. The software uses a nonparametric, supervised approach to classification, and provides a more objective and flexible interface to the evidential reasoning framework using a frequency-based method for computing support values from training data. The MERCURY⊕ software package has been implemented efficiently in the C programming language, with extensive use made of dynamic memory allocation procedures and compound linked list and hash-table data structures to optimize the storage and retrieval of evidence in a Knowledge Look-up Table. The software is complete with a full user interface and runs under Unix, Ultrix, VAX/VMS, MS-DOS, and Apple Macintosh operating system. An example of classifying alpine land cover and permafrost active layer depth in northern Canada is presented to illustrate the use and application of these ideas.

Application of pattern recognition techniques to crime analysis

Energy Technology Data Exchange (ETDEWEB)

Bender, C.F.; Cox, L.A. Jr.; Chappell, G.A.

1976-08-15

The initial goal was to evaluate the capabilities of current pattern recognition techniques when applied to existing computerized crime data. Performance was to be evaluated both in terms of the system's capability to predict crimes and to optimize police manpower allocation. A relation was sought to predict the crime's susceptibility to solution, based on knowledge of the crime type, location, time, etc. The preliminary results of this work are discussed. They indicate that automatic crime analysis involving pattern recognition techniques is feasible, and that efforts to determine optimum variables and techniques are warranted. 47 figures (RWR)

Describing Old Czech Declension Patterns for Automatic Text Analysis

Czech Academy of Sciences Publication Activity Database

Jínová, P.; Lehečka, Boris; Oliva jr., Karel

-, č. 13 (2014), s. 7-17 ISSN 1579-8372 Institutional support: RVO:68378092 Keywords : Old Czech morphology * declension patterns * automatic text analysis * i-stems * ja-stems Subject RIV: AI - Linguistics

Distorted Pattern Recognition and Analysis with the Help of IEf Graph Representation

Directory of Open Access Journals (Sweden)

Adam Sedziwy

2002-01-01

Full Text Available An algorithm for distorted pattern recognition is presented. lt's generalization of M Flasinski results (Pattern Recognition, 27, 1-16, 1992. A new formalism allows to make both qualitative and quantitive distortion analysis. It also enlarges parser flexibility by extending the set of patterns which may be recognized.

Assessment of fractures classified as non-mineralised in the Sicada database

Energy Technology Data Exchange (ETDEWEB)

Claesson Liljedahl, Lillemor; Munier, Raymond (Swedish Nuclear Fuel and Waste Management Co., Stockholm (Sweden)); Sandstroem, Bjoern (WSP Sverige AB, Goeteborg (Sweden)); Drake, Henrik (Isochron GeoConsulting, Varberg (Sweden)); Tullborg, Eva-Lena (Terralogica AB, Graabo (Sweden))

2011-03-15

The general objective of this report was to describe the results of the investigation of fractures classified as non-mineralised in Sicada. Such fractures exist at Forsmark and at Laxemar. The main aims of the investigation of these fractures were to: - Quantify the number of non-mineralised fractures (i.e. fractures lacking mineral coating) in Sicada (table: p{_}fract{_}core{_}eshi). - Closely examine a selection of fractures recorded as non-mineralised in Sicada. - Outline possible reasons for the existence of non-mineralised fractures. The work has involved extraction of fracture data from Sicada and subsequent statistical analysis. Since several thousand fractures are classified as non-mineralised in Sicada, it was not a practical possibility to include all these in this study, we examined one fracture sub-set from each site. We investigated a sample of 204 of these fractures in detail (see Sections 1.1 and 2.4). Rock mechanical differences between Forsmark and Laxemar and kinematic analysis of fracture surfaces is not discussed in this report

3D Bayesian contextual classifiers

DEFF Research Database (Denmark)

Larsen, Rasmus

2000-01-01

We extend a series of multivariate Bayesian 2-D contextual classifiers to 3-D by specifying a simultaneous Gaussian distribution for the feature vectors as well as a prior distribution of the class variables of a pixel and its 6 nearest 3-D neighbours.......We extend a series of multivariate Bayesian 2-D contextual classifiers to 3-D by specifying a simultaneous Gaussian distribution for the feature vectors as well as a prior distribution of the class variables of a pixel and its 6 nearest 3-D neighbours....

Clean-up progress at the SNL/NM Classified Waste Landfill

International Nuclear Information System (INIS)

Slavin, P.J.; Galloway, R.B.

1999-01-01

The Sandia National Laboratories/New Mexico (SNL/NM)Environmental Restoration Project is currently excavating the Classified Waste Landfill in Technical Area II, a disposal area for weapon components for approximately 40 years until it closed in 1987. Many different types of classified parts were disposed in unlined trenches and pits throughout the course of the landfill's history. A percentage of the parts contain explosives and/or radioactive components or contamination. The excavation has progressed backward chronologically from the last trenches filled through to the earlier pits. Excavation commenced in March 1998, and approximately 75 percent of the site (as defined by geophysical anomalies) has been completed as of November 1999. The material excavated consists primarily of classified weapon assemblies and related components, so disposition must include demilitarization and sanitization. This has resulted in substantial waste minimization and cost avoidance for the project as upwards of 90 percent of the classified materials are being demilitarized and recycled. The project is using field screening and lab analysis in conjunction with preliminary and in-process risk assessments to characterize soil and make waste determinations in a timely a fashion as possible. Challenges in waste management have prompted the adoption of innovative solutions. The hand-picked crew (both management and field staff) and the ability to quickly adapt to changing conditions has ensured the success of the project. The current schedule is to complete excavation in July 2000, with follow-on verification sampling, demilitarization, and waste management activities following

Integrative Analysis of DCE-MRI and Gene Expression Profiles in Construction of a Gene Classifier for Assessment of Hypoxia-Related Risk of Chemoradiotherapy Failure in Cervical Cancer

DEFF Research Database (Denmark)

Fjeldbo, Christina S; Julin, Cathinka H; Lando, Malin

2016-01-01

platforms. The prognostic value was independent of existing clinical markers, regardless of clinical endpoints. CONCLUSIONS: A robust DCE-MRI-associated gene classifier has been constructed that may be used to achieve an early indication of patients' risk of hypoxia-related chemoradiotherapy failure.......PURPOSE: A 31-gene expression signature reflected in dynamic contrast enhanced (DCE)-MR images and correlated with hypoxia-related aggressiveness in cervical cancer was identified in previous work. We here aimed to construct a dichotomous classifier with key signature genes and a predefined...... as an indicator of hypoxia. RESULTS: Classifier candidates were constructed by integrative analysis of ABrix and gene expression profiles in the training cohort and evaluated by a leave-one-out cross-validation approach. On the basis of their ability to separate patients correctly according to hypoxia status, a 6...

Similarity-based pattern analysis and recognition

CERN Document Server

Pelillo, Marcello

2013-01-01

This accessible text/reference presents a coherent overview of the emerging field of non-Euclidean similarity learning. The book presents a broad range of perspectives on similarity-based pattern analysis and recognition methods, from purely theoretical challenges to practical, real-world applications. The coverage includes both supervised and unsupervised learning paradigms, as well as generative and discriminative models. Topics and features: explores the origination and causes of non-Euclidean (dis)similarity measures, and how they influence the performance of traditional classification alg

Reactor power distribution pattern judging device

International Nuclear Information System (INIS)

Ikehara, Tadashi.

1992-01-01

The judging device of the present invention comprises a power distribution readout system for intaking a power value from a fuel segment, a neural network having an experience learning function for receiving a power distribution value as an input variant, mapping it into a desirable property and self-organizing the map, and a learning date base storing a plurality of learnt samples. The read power distribution is classified depending on the similarity thereof with any one of representative learnt power distribution, and the corresponding state of the reactor core is outputted as a result of the judgement. When an error is found in the classified judging operation, erroneous cases are additionally learnt by using the experience and learning function, thereby improving the accuracy of the reactor core characteristic estimation operation. Since the device is mainly based on the neural network having a self-learning function and a pattern classification and judging function, a judging device having a human's intuitive pattern recognition performance and a pattern experience and learning performance is obtainable, thereby enabling to judge the state of the reactor core accurately. (N.H.)

Multivariate statistical pattern recognition system for reactor noise analysis

International Nuclear Information System (INIS)

Gonzalez, R.C.; Howington, L.C.; Sides, W.H. Jr.; Kryter, R.C.

1976-01-01

A multivariate statistical pattern recognition system for reactor noise analysis was developed. The basis of the system is a transformation for decoupling correlated variables and algorithms for inferring probability density functions. The system is adaptable to a variety of statistical properties of the data, and it has learning, tracking, and updating capabilities. System design emphasizes control of the false-alarm rate. The ability of the system to learn normal patterns of reactor behavior and to recognize deviations from these patterns was evaluated by experiments at the ORNL High-Flux Isotope Reactor (HFIR). Power perturbations of less than 0.1 percent of the mean value in selected frequency ranges were detected by the system

Multivariate statistical pattern recognition system for reactor noise analysis

International Nuclear Information System (INIS)

Gonzalez, R.C.; Howington, L.C.; Sides, W.H. Jr.; Kryter, R.C.

1975-01-01

A multivariate statistical pattern recognition system for reactor noise analysis was developed. The basis of the system is a transformation for decoupling correlated variables and algorithms for inferring probability density functions. The system is adaptable to a variety of statistical properties of the data, and it has learning, tracking, and updating capabilities. System design emphasizes control of the false-alarm rate. The ability of the system to learn normal patterns of reactor behavior and to recognize deviations from these patterns was evaluated by experiments at the ORNL High-Flux Isotope Reactor (HFIR). Power perturbations of less than 0.1 percent of the mean value in selected frequency ranges were detected by the system. 19 references

A CLASSIFIER SYSTEM USING SMOOTH GRAPH COLORING

Directory of Open Access Journals (Sweden)

JORGE FLORES CRUZ

2017-01-01

Full Text Available Unsupervised classifiers allow clustering methods with less or no human intervention. Therefore it is desirable to group the set of items with less data processing. This paper proposes an unsupervised classifier system using the model of soft graph coloring. This method was tested with some classic instances in the literature and the results obtained were compared with classifications made with human intervention, yielding as good or better results than supervised classifiers, sometimes providing alternative classifications that considers additional information that humans did not considered.

Experience in performing trends and patterns analysis of nuclear power plant operational data

International Nuclear Information System (INIS)

Novak, T.M.; Williams, M.H.; Dennig, R.L.

1990-01-01

The Office for Analysis and Evaluation of Operational Data (AEOD) of the U.S. Nuclear Regulatory Commission (USNRC) has conducted a formal trends and patterns program since 1982. Since that time, the methods and end products of the program have evolved through experience and changes in the environment for trends and patterns analysis, i.e., increasing regulatory emphasis on operations and balance of plant performance, emergence of performance indicators, the availability of personal computer hardware and software to perform analysis, and changes in the information reported to the USNRC. This paper discusses the technical milestones of the AEOD trends and patterns program in terms of: 1) Sources of operational data, e.g., pre- and post- 1984 Licensee Event Reports, NPRDS, 2) Data storage and retrieval, e.g., Sequence Coding and Search System (SCSS), 3) Statistical methods, e.g., contingency table analysis, 4) Types of results. The paper summarizes the major lessons learned in the process of implementing a trends and patterns program and outlines future direction

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

Speaker gender identification based on majority vote classifiers

Science.gov (United States)

Mezghani, Eya; Charfeddine, Maha; Nicolas, Henri; Ben Amar, Chokri

2017-03-01

Speaker gender identification is considered among the most important tools in several multimedia applications namely in automatic speech recognition, interactive voice response systems and audio browsing systems. Gender identification systems performance is closely linked to the selected feature set and the employed classification model. Typical techniques are based on selecting the best performing classification method or searching optimum tuning of one classifier parameters through experimentation. In this paper, we consider a relevant and rich set of features involving pitch, MFCCs as well as other temporal and frequency-domain descriptors. Five classification models including decision tree, discriminant analysis, nave Bayes, support vector machine and k-nearest neighbor was experimented. The three best perming classifiers among the five ones will contribute by majority voting between their scores. Experimentations were performed on three different datasets spoken in three languages: English, German and Arabic in order to validate language independency of the proposed scheme. Results confirm that the presented system has reached a satisfying accuracy rate and promising classification performance thanks to the discriminating abilities and diversity of the used features combined with mid-level statistics.

Universal Keyword Classifier on Public Key Based Encrypted Multikeyword Fuzzy Search in Public Cloud.

Science.gov (United States)

Munisamy, Shyamala Devi; Chokkalingam, Arun

2015-01-01

Cloud computing has pioneered the emerging world by manifesting itself as a service through internet and facilitates third party infrastructure and applications. While customers have no visibility on how their data is stored on service provider's premises, it offers greater benefits in lowering infrastructure costs and delivering more flexibility and simplicity in managing private data. The opportunity to use cloud services on pay-per-use basis provides comfort for private data owners in managing costs and data. With the pervasive usage of internet, the focus has now shifted towards effective data utilization on the cloud without compromising security concerns. In the pursuit of increasing data utilization on public cloud storage, the key is to make effective data access through several fuzzy searching techniques. In this paper, we have discussed the existing fuzzy searching techniques and focused on reducing the searching time on the cloud storage server for effective data utilization. Our proposed Asymmetric Classifier Multikeyword Fuzzy Search method provides classifier search server that creates universal keyword classifier for the multiple keyword request which greatly reduces the searching time by learning the search path pattern for all the keywords in the fuzzy keyword set. The objective of using BTree fuzzy searchable index is to resolve typos and representation inconsistencies and also to facilitate effective data utilization.

Quantitative assessment of breast density from digitized mammograms into Tabar's patterns

International Nuclear Information System (INIS)

Jamal, N; Ng, K-H; Looi, L-M; McLean, D; Zulfiqar, A; Tan, S-P; Liew, W-F; Shantini, A; Ranganathan, S

2006-01-01

We describe a semi-automated technique for the quantitative assessment of breast density from digitized mammograms in comparison with patterns suggested by Tabar. It was developed using the MATLAB-based graphical user interface applications. It is based on an interactive thresholding method, after a short automated method that shows the fibroglandular tissue area, breast area and breast density each time new thresholds are placed on the image. The breast density is taken as a percentage of the fibroglandular tissue to the breast tissue areas. It was tested in four different ways, namely by examining: (i) correlation of the quantitative assessment results with subjective classification, (ii) classification performance using the quantitative assessment technique, (iii) interobserver agreement and (iv) intraobserver agreement. The results of the quantitative assessment correlated well (r 2 = 0.92) with the subjective Tabar patterns classified by the radiologist (correctly classified 83% of digitized mammograms). The average kappa coefficient for the agreement between the readers was 0.63. This indicated moderate agreement between the three observers in classifying breast density using the quantitative assessment technique. The kappa coefficient of 0.75 for intraobserver agreement reflected good agreement between two sets of readings. The technique may be useful as a supplement to the radiologist's assessment in classifying mammograms into Tabar's pattern associated with breast cancer risk

Dietary pattern analysis: a comparison between matched vegetarian and omnivorous subjects.

Science.gov (United States)

Clarys, Peter; Deriemaeker, Peter; Huybrechts, Inge; Hebbelinck, Marcel; Mullie, Patrick

2013-06-13

Dietary pattern analysis, based on the concept that foods eaten together are as important as a reductive methodology characterized by a single food or nutrient analysis, has emerged as an alternative approach to study the relation between nutrition and disease. The aim of the present study was to compare nutritional intake and the results of dietary pattern analysis in properly matched vegetarian and omnivorous subjects. Vegetarians (n = 69) were recruited via purposeful sampling and matched non-vegetarians (n = 69) with same age, gender, health and lifestyle characteristics were searched for via convenience sampling. Two dietary pattern analysis methods, the Healthy Eating Index-2010 (HEI-2010) and the Mediterranean Diet Score (MDS) were calculated and analysed in function of the nutrient intake. Mean total energy intake was comparable between vegetarians and omnivorous subjects (p > 0.05). Macronutrient analysis revealed significant differences between the mean values for vegetarians and omnivorous subjects (absolute and relative protein and total fat intake were significantly lower in vegetarians, while carbohydrate and fibre intakes were significantly higher in vegetarians than in omnivorous subjects). The HEI and MDS were significantly higher for the vegetarians (HEI = 53.8.1 ± 11.2; MDS = 4.3 ± 1.3) compared to the omnivorous subjects (HEI = 46.4 ± 15.3; MDS = 3.8 ± 1.4). Our results indicate a more nutrient dense pattern, closer to the current dietary recommendations for the vegetarians compared to the omnivorous subjects. Both indexing systems were able to discriminate between the vegetarians and the non-vegetarians with higher scores for the vegetarian subjects.

Carbon classified?

DEFF Research Database (Denmark)

Lippert, Ingmar

2012-01-01

. Using an actor- network theory (ANT) framework, the aim is to investigate the actors who bring together the elements needed to classify their carbon emission sources and unpack the heterogeneous relations drawn on. Based on an ethnographic study of corporate agents of ecological modernisation over...... a period of 13 months, this paper provides an exploration of three cases of enacting classification. Drawing on ANT, we problematise the silencing of a range of possible modalities of consumption facts and point to the ontological ethics involved in such performances. In a context of global warming...

Pattern recognition in complex activity travel patterns : comparison of Euclidean distance, signal-processing theoretical, and multidimensional sequence alignment methods

NARCIS (Netherlands)

Joh, C.H.; Arentze, T.A.; Timmermans, H.J.P.

2001-01-01

The application of a multidimensional sequence alignment method for classifying activity travel patterns is reported. The method was developed as an alternative to the existing classification methods suggested in the transportation literature. The relevance of the multidimensional sequence alignment

Analysis of Web Spam for Non-English Content: Toward More Effective Language-Based Classifiers.

Directory of Open Access Journals (Sweden)

Mansour Alsaleh

Full Text Available Web spammers aim to obtain higher ranks for their web pages by including spam contents that deceive search engines in order to include their pages in search results even when they are not related to the search terms. Search engines continue to develop new web spam detection mechanisms, but spammers also aim to improve their tools to evade detection. In this study, we first explore the effect of the page language on spam detection features and we demonstrate how the best set of detection features varies according to the page language. We also study the performance of Google Penguin, a newly developed anti-web spamming technique for their search engine. Using spam pages in Arabic as a case study, we show that unlike similar English pages, Google anti-spamming techniques are ineffective against a high proportion of Arabic spam pages. We then explore multiple detection features for spam pages to identify an appropriate set of features that yields a high detection accuracy compared with the integrated Google Penguin technique. In order to build and evaluate our classifier, as well as to help researchers to conduct consistent measurement studies, we collected and manually labeled a corpus of Arabic web pages, including both benign and spam pages. Furthermore, we developed a browser plug-in that utilizes our classifier to warn users about spam pages after clicking on a URL and by filtering out search engine results. Using Google Penguin as a benchmark, we provide an illustrative example to show that language-based web spam classifiers are more effective for capturing spam contents.

An Analysis of Intrinsic and Extrinsic Hand Muscle EMG for Improved Pattern Recognition Control.

Science.gov (United States)

Adewuyi, Adenike A; Hargrove, Levi J; Kuiken, Todd A

2016-04-01

Pattern recognition control combined with surface electromyography (EMG) from the extrinsic hand muscles has shown great promise for control of multiple prosthetic functions for transradial amputees. There is, however, a need to adapt this control method when implemented for partial-hand amputees, who possess both a functional wrist and information-rich residual intrinsic hand muscles. We demonstrate that combining EMG data from both intrinsic and extrinsic hand muscles to classify hand grasps and finger motions allows up to 19 classes of hand grasps and individual finger motions to be decoded, with an accuracy of 96% for non-amputees and 85% for partial-hand amputees. We evaluated real-time pattern recognition control of three hand motions in seven different wrist positions. We found that a system trained with both intrinsic and extrinsic muscle EMG data, collected while statically and dynamically varying wrist position increased completion rates from 73% to 96% for partial-hand amputees and from 88% to 100% for non-amputees when compared to a system trained with only extrinsic muscle EMG data collected in a neutral wrist position. Our study shows that incorporating intrinsic muscle EMG data and wrist motion can significantly improve the robustness of pattern recognition control for application to partial-hand prosthetic control.

Application of texture analysis method for mammogram density classification

Science.gov (United States)

Nithya, R.; Santhi, B.

2017-07-01

Mammographic density is considered a major risk factor for developing breast cancer. This paper proposes an automated approach to classify breast tissue types in digital mammogram. The main objective of the proposed Computer-Aided Diagnosis (CAD) system is to investigate various feature extraction methods and classifiers to improve the diagnostic accuracy in mammogram density classification. Texture analysis methods are used to extract the features from the mammogram. Texture features are extracted by using histogram, Gray Level Co-Occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Difference Matrix (GLDM), Local Binary Pattern (LBP), Entropy, Discrete Wavelet Transform (DWT), Wavelet Packet Transform (WPT), Gabor transform and trace transform. These extracted features are selected using Analysis of Variance (ANOVA). The features selected by ANOVA are fed into the classifiers to characterize the mammogram into two-class (fatty/dense) and three-class (fatty/glandular/dense) breast density classification. This work has been carried out by using the mini-Mammographic Image Analysis Society (MIAS) database. Five classifiers are employed namely, Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA), Naive Bayes (NB), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). Experimental results show that ANN provides better performance than LDA, NB, KNN and SVM classifiers. The proposed methodology has achieved 97.5% accuracy for three-class and 99.37% for two-class density classification.

Dissemination Patterns and Associated Network Effects of Sentiments in Social Networks

DEFF Research Database (Denmark)

Hillmann, Robert; Trier, Matthias

2012-01-01

. The dissemination patterns analyzed in this study consist of network motifs based on triples of actors and the ties among them. These motifs are associated with common social network effects to derive meaningful insights about dissemination activities. The data basis includes several thousand social networks...... with textual messages classified according to embedded positive and negative sentiments. Based on this data, sub-networks are extracted and analyzed with a dynamic network motif analysis to determine dissemination patterns and associated network effects. Results indicate that the emergence of digital social...... networks exhibits a strong tendency towards reciprocity, followed by the dominance of hierarchy as an intermediate step leading to social clustering with hubs and transitivity effects for both positive and negative sentiments to the same extend. Sentiments embedded in exchanged textual messages do only...

Different knee joint loading patterns in ACL deficient copers and non-copers during walking

DEFF Research Database (Denmark)

Alkjaer, Tine; Henriksen, Marius; Simonsen, Erik B

2011-01-01

Rupture of the anterior cruciate ligament (ACL) causes changes in the walking pattern. ACL deficient subjects classified as copers and non-copers have been observed to adopt different post-injury walking patterns. How these different patterns affect the knee compression and shear forces...

CKD273, a new proteomics classifier assessing CKD and its prognosis.

Directory of Open Access Journals (Sweden)

Ángel Argilés

Full Text Available National Kidney Foundation CKD staging has allowed uniformity in studies on CKD. However, early diagnosis and predicting progression to end stage renal disease are yet to be improved. Seventy six patients with different levels of CKD, including outpatients and dialysed patients were studied for transcriptome, metabolome and proteome description. High resolution urinary proteome analysis was blindly performed in the 53 non-anuric out of the 76 CKD patients. In addition to routine clinical parameters, CKD273, a urinary proteomics-based classifier and its peptides were quantified. The baseline values were analyzed with regard to the clinical parameters and the occurrence of death or renal death during follow-up (3.6 years as the main outcome measurements. None of the patients with CKD2730.55. Unsupervised clustering analysis of the CKD273 peptides separated the patients into two main groups differing in CKD associated parameters. Among the 273 biomarkers, peptides derived from serum proteins were relatively increased in patients with lower glomerular filtration rate, while collagen-derived peptides were relatively decreased (p<0.05; Spearman. CKD273 was different in the groups with different renal function (p<0.003. The CKD273 classifier separated CKD patients according to their renal function and informed on the likelihood of experiencing adverse outcome. Recently defined in a large population, CKD273 is the first proteomic-based classifier successfully tested for prognosis of CKD progression in an independent cohort.

Effective Heart Disease Detection Based on Quantitative Computerized Traditional Chinese Medicine Using Representation Based Classifiers

Directory of Open Access Journals (Sweden)

Ting Shu

2017-01-01

Full Text Available At present, heart disease is the number one cause of death worldwide. Traditionally, heart disease is commonly detected using blood tests, electrocardiogram, cardiac computerized tomography scan, cardiac magnetic resonance imaging, and so on. However, these traditional diagnostic methods are time consuming and/or invasive. In this paper, we propose an effective noninvasive computerized method based on facial images to quantitatively detect heart disease. Specifically, facial key block color features are extracted from facial images and analyzed using the Probabilistic Collaborative Representation Based Classifier. The idea of facial key block color analysis is founded in Traditional Chinese Medicine. A new dataset consisting of 581 heart disease and 581 healthy samples was experimented by the proposed method. In order to optimize the Probabilistic Collaborative Representation Based Classifier, an analysis of its parameters was performed. According to the experimental results, the proposed method obtains the highest accuracy compared with other classifiers and is proven to be effective at heart disease detection.

Classifying Multi-Model Wheat Yield Impact Response Surfaces Showing Sensitivity to Temperature and Precipitation Change

Science.gov (United States)

Fronzek, Stefan; Pirttioja, Nina; Carter, Timothy R.; Bindi, Marco; Hoffmann, Holger; Palosuo, Taru; Ruiz-Ramos, Margarita; Tao, Fulu; Trnka, Miroslav; Acutis, Marco;

Uncovering stable and occasional human mobility patterns: A case study of the Beijing subway

Science.gov (United States)

Yong, Nuo; Ni, Shunjiang; Shen, Shifei; Chen, Peng; Ji, Xuewei

2018-02-01

There have generally been two kinds of approaches to the empirical study of human mobility. At the group level, some valuable information might be submerged in statistical noise, while due to the diversity of individual purpose and preference, there is still no general statistical regularity of human mobility at the individual level. In this paper, we considered group-level human mobility as the combination of several basic patterns and analyzed the collective mobility by category. Utilizing matrix factorization and correlation analysis, we extracted some of the stable/occasional components from the collective human mobility in the Beijing subway and found that the departure and arrival mobility patterns have different characteristics, both in time and space, under various conditions. We classified individual records into different patterns and analyzed the most likely trip distance by category. The proposed method can decompose stable/occasional mobility patterns from the collective mobility and identify passengers belonging to different patterns, helping us to better understand the origin of different mobility patterns and provide guidance for emergency management of large crowds.

Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers

Science.gov (United States)

Mannini, Andrea; Sabatini, Angelo Maria

2010-01-01

The use of on-body wearable sensors is widespread in several academic and industrial domains. Of great interest are their applications in ambulatory monitoring and pervasive computing systems; here, some quantitative analysis of human motion and its automatic classification are the main computational tasks to be pursued. In this paper, we discuss how human physical activity can be classified using on-body accelerometers, with a major emphasis devoted to the computational algorithms employed for this purpose. In particular, we motivate our current interest for classifiers based on Hidden Markov Models (HMMs). An example is illustrated and discussed by analysing a dataset of accelerometer time series. PMID:22205862

Balanced sensitivity functions for tuning multi-dimensional Bayesian network classifiers

NARCIS (Netherlands)

Bolt, J.H.; van der Gaag, L.C.

Multi-dimensional Bayesian network classifiers are Bayesian networks of restricted topological structure, which are tailored to classifying data instances into multiple dimensions. Like more traditional classifiers, multi-dimensional classifiers are typically learned from data and may include

Recognition of pornographic web pages by classifying texts and images.

Science.gov (United States)

Hu, Weiming; Wu, Ou; Chen, Zhouyao; Fu, Zhouyu; Maybank, Steve

2007-06-01

With the rapid development of the World Wide Web, people benefit more and more from the sharing of information. However, Web pages with obscene, harmful, or illegal content can be easily accessed. It is important to recognize such unsuitable, offensive, or pornographic Web pages. In this paper, a novel framework for recognizing pornographic Web pages is described. A C4.5 decision tree is used to divide Web pages, according to content representations, into continuous text pages, discrete text pages, and image pages. These three categories of Web pages are handled, respectively, by a continuous text classifier, a discrete text classifier, and an algorithm that fuses the results from the image classifier and the discrete text classifier. In the continuous text classifier, statistical and semantic features are used to recognize pornographic texts. In the discrete text classifier, the naive Bayes rule is used to calculate the probability that a discrete text is pornographic. In the image classifier, the object's contour-based features are extracted to recognize pornographic images. In the text and image fusion algorithm, the Bayes theory is used to combine the recognition results from images and texts. Experimental results demonstrate that the continuous text classifier outperforms the traditional keyword-statistics-based classifier, the contour-based image classifier outperforms the traditional skin-region-based image classifier, the results obtained by our fusion algorithm outperform those by either of the individual classifiers, and our framework can be adapted to different categories of Web pages.

Numerical analysis of a neural network with hierarchically organized patterns

International Nuclear Information System (INIS)

Bacci, Silvia; Wiecko, Cristina; Parga, Nestor

1988-01-01

A numerical analysis of the retrieval behaviour of an associative memory model where the memorized patterns are stored hierarchically is performed. It is found that the model is able to categorize errors. For a finite number of categories, these are retrieved correctly even when the stored patterns are not. Instead, when they are allowed to increase with the number of neurons, their retrieval quality deteriorates above a critical category capacity. (Author)

Patterns of dental development in Homo, Australopithecus, Pan, and Gorilla.

Science.gov (United States)

Smith, B H

1994-07-01

Smith ([1986] Nature 323:327-330) distinguished patterns of development of teeth of juvenile fossil hominids as being "more like humans" or "more like apes" based on statistical similarity to group standards. Here, this central tendency discrimination (CTD) is tested for its ability to recognize ape and human patterns of dental development in 789 subadult hominoids. Tooth development of a modern human sample (665 black southern Africans) was scored entirely by an outside investigator; pongid and fossil hominid samples (59 Pan, 50 Gorilla, and 14 fossil hominids) were scored by the author. The claim of Lampl et al. ([1993] Am. J. Phys. Anthropol. 90:113-127) that Smith's 1986 method succeeds in only 8% of human cases was not sustained. Figures for overall success of classification (87% humans, 68% apes) mask important effects of teeth sampled and age class. For humans, the power of CTD varied between 53% and 92% depending on the number and kind of teeth available--nearly that of a coin toss when data described only two nearby teeth, but quite successful with more teeth or distant teeth. For apes, only age class affected accuracy: "Infant" apes (M1 development or = root 1/4), however, were correctly discriminated in 87% of cases. Overall, CTD can be considered reliable (accuracy of 92% for humans and 88% for apes) when data contrast development of distant dental fields and subjects are juveniles (not infants). Restricting analysis of fossils to specimens satisfying these criteria, patterns of dental development of gracile australopithecines and Homo habilis remain classified with African apes. Those of Homo erectus and Neanderthals are classified with humans, suggesting that patterns of growth evolved substantially in the Hominidae. To standardize future research, the computer program that operationalizes CTD is now available.

Proposing an adaptive mutation to improve XCSF performance to classify ADHD and BMD patients

Science.gov (United States)

Sadatnezhad, Khadijeh; Boostani, Reza; Ghanizadeh, Ahmad

2010-12-01

There is extensive overlap of clinical symptoms observed among children with bipolar mood disorder (BMD) and those with attention deficit hyperactivity disorder (ADHD). Thus, diagnosis according to clinical symptoms cannot be very accurate. It is therefore desirable to develop quantitative criteria for automatic discrimination between these disorders. This study is aimed at designing an efficient decision maker to accurately classify ADHD and BMD patients by analyzing their electroencephalogram (EEG) signals. In this study, 22 channels of EEGs have been recorded from 21 subjects with ADHD and 22 individuals with BMD. Several informative features, such as fractal dimension, band power and autoregressive coefficients, were extracted from the recorded signals. Considering the multimodal overlapping distribution of the obtained features, linear discriminant analysis (LDA) was used to reduce the input dimension in a more separable space to make it more appropriate for the proposed classifier. A piecewise linear classifier based on the extended classifier system for function approximation (XCSF) was modified by developing an adaptive mutation rate, which was proportional to the genotypic content of best individuals and their fitness in each generation. The proposed operator controlled the trade-off between exploration and exploitation while maintaining the diversity in the classifier's population to avoid premature convergence. To assess the effectiveness of the proposed scheme, the extracted features were applied to support vector machine, LDA, nearest neighbor and XCSF classifiers. To evaluate the method, a noisy environment was simulated with different noise amplitudes. It is shown that the results of the proposed technique are more robust as compared to conventional classifiers. Statistical tests demonstrate that the proposed classifier is a promising method for discriminating between ADHD and BMD patients.

Using Neural Networks to Classify Digitized Images of Galaxies

Science.gov (United States)

Goderya, S. N.; McGuire, P. C.

2000-12-01

Automated classification of Galaxies into Hubble types is of paramount importance to study the large scale structure of the Universe, particularly as survey projects like the Sloan Digital Sky Survey complete their data acquisition of one million galaxies. At present it is not possible to find robust and efficient artificial intelligence based galaxy classifiers. In this study we will summarize progress made in the development of automated galaxy classifiers using neural networks as machine learning tools. We explore the Bayesian linear algorithm, the higher order probabilistic network, the multilayer perceptron neural network and Support Vector Machine Classifier. The performance of any machine classifier is dependant on the quality of the parameters that characterize the different groups of galaxies. Our effort is to develop geometric and invariant moment based parameters as input to the machine classifiers instead of the raw pixel data. Such an approach reduces the dimensionality of the classifier considerably, and removes the effects of scaling and rotation, and makes it easier to solve for the unknown parameters in the galaxy classifier. To judge the quality of training and classification we develop the concept of Mathews coefficients for the galaxy classification community. Mathews coefficients are single numbers that quantify classifier performance even with unequal prior probabilities of the classes.

A Machine Learning Ensemble Classifier for Early Prediction of Diabetic Retinopathy.

Science.gov (United States)

S K, Somasundaram; P, Alli

2017-11-09

The main complication of diabetes is Diabetic retinopathy (DR), retinal vascular disease and it leads to the blindness. Regular screening for early DR disease detection is considered as an intensive labor and resource oriented task. Therefore, automatic detection of DR diseases is performed only by using the computational technique is the great solution. An automatic method is more reliable to determine the presence of an abnormality in Fundus images (FI) but, the classification process is poorly performed. Recently, few research works have been designed for analyzing texture discrimination capacity in FI to distinguish the healthy images. However, the feature extraction (FE) process was not performed well, due to the high dimensionality. Therefore, to identify retinal features for DR disease diagnosis and early detection using Machine Learning and Ensemble Classification method, called, Machine Learning Bagging Ensemble Classifier (ML-BEC) is designed. The ML-BEC method comprises of two stages. The first stage in ML-BEC method comprises extraction of the candidate objects from Retinal Images (RI). The candidate objects or the features for DR disease diagnosis include blood vessels, optic nerve, neural tissue, neuroretinal rim, optic disc size, thickness and variance. These features are initially extracted by applying Machine Learning technique called, t-distributed Stochastic Neighbor Embedding (t-SNE). Besides, t-SNE generates a probability distribution across high-dimensional images where the images are separated into similar and dissimilar pairs. Then, t-SNE describes a similar probability distribution across the points in the low-dimensional map. This lessens the Kullback-Leibler divergence among two distributions regarding the locations of the points on the map. The second stage comprises of application of ensemble classifiers to the extracted features for providing accurate analysis of digital FI using machine learning. In this stage, an automatic detection

Classifying and mapping wetlands and peat resources using digital cartography

Science.gov (United States)

Cameron, Cornelia C.; Emery, David A.

1992-01-01

Digital cartography allows the portrayal of spatial associations among diverse data types and is ideally suited for land use and resource analysis. We have developed methodology that uses digital cartography for the classification of wetlands and their associated peat resources and applied it to a 1:24 000 scale map area in New Hampshire. Classifying and mapping wetlands involves integrating the spatial distribution of wetlands types with depth variations in associated peat quality and character. A hierarchically structured classification that integrates the spatial distribution of variations in (1) vegetation, (2) soil type, (3) hydrology, (4) geologic aspects, and (5) peat characteristics has been developed and can be used to build digital cartographic files for resource and land use analysis. The first three parameters are the bases used by the National Wetlands Inventory to classify wetlands and deepwater habitats of the United States. The fourth parameter, geological aspects, includes slope, relief, depth of wetland (from surface to underlying rock or substrate), wetland stratigraphy, and the type and structure of solid and unconsolidated rock surrounding and underlying the wetland. The fifth parameter, peat characteristics, includes the subsurface variation in ash, acidity, moisture, heating value (Btu), sulfur content, and other chemical properties as shown in specimens obtained from core holes. These parameters can be shown as a series of map data overlays with tables that can be integrated for resource or land use analysis.

An analysis of error patterns in children′s backward digit recall in noise

Directory of Open Access Journals (Sweden)

Homira Osman

2015-01-01

Full Text Available The purpose of the study was to determine whether perceptual masking or cognitive processing accounts for a decline in working memory performance in the presence of competing speech. The types and patterns of errors made on the backward digit span in quiet and multitalker babble at -5 dB signal-to-noise ratio (SNR were analyzed. The errors were classified into two categories: item (if digits that were not presented in a list were repeated and order (if correct digits were repeated but in an incorrect order. Fifty five children with normal hearing were included. All the children were aged between 7 years and 10 years. Repeated measures of analysis of variance (RM-ANOVA revealed the main effects for error type and digit span length. In terms of listening condition interaction, it was found that the order errors occurred more frequently than item errors in the degraded listening condition compared to quiet. In addition, children had more difficulty recalling the correct order of intermediate items, supporting strong primacy and recency effects. Decline in children′s working memory performance was not primarily related to perceptual difficulties alone. The majority of errors was related to the maintenance of sequential order information, which suggests that reduced performance in competing speech may result from increased cognitive processing demands in noise.

Classifier fusion for VoIP attacks classification

Science.gov (United States)

Safarik, Jakub; Rezac, Filip

2017-05-01

SIP is one of the most successful protocols in the field of IP telephony communication. It establishes and manages VoIP calls. As the number of SIP implementation rises, we can expect a higher number of attacks on the communication system in the near future. This work aims at malicious SIP traffic classification. A number of various machine learning algorithms have been developed for attack classification. The paper presents a comparison of current research and the use of classifier fusion method leading to a potential decrease in classification error rate. Use of classifier combination makes a more robust solution without difficulties that may affect single algorithms. Different voting schemes, combination rules, and classifiers are discussed to improve the overall performance. All classifiers have been trained on real malicious traffic. The concept of traffic monitoring depends on the network of honeypot nodes. These honeypots run in several networks spread in different locations. Separation of honeypots allows us to gain an independent and trustworthy attack information.

Autoregressive Integrated Adaptive Neural Networks Classifier for EEG-P300 Classification

Directory of Open Access Journals (Sweden)

Demi Soetraprawata

2013-06-01

Full Text Available Brain Computer Interface has a potency to be applied in mechatronics apparatus and vehicles in the future. Compared to the other techniques, EEG is the most preferred for BCI designs. In this paper, a new adaptive neural network classifier of different mental activities from EEG-based P300 signals is proposed. To overcome the over-training that is caused by noisy and non-stationary data, the EEG signals are filtered and extracted using autoregressive models before passed to the adaptive neural networks classifier. To test the improvement in the EEG classification performance with the proposed method, comparative experiments were conducted using Bayesian Linear Discriminant Analysis. The experiment results show that the all subjects achieve a classification accuracy of 100%.

A comparative study of machine learning classifiers for modeling travel mode choice

NARCIS (Netherlands)

Hagenauer, J; Helbich, M

2017-01-01

The analysis of travel mode choice is an important task in transportation planning and policy making in order to understand and predict travel demands. While advances in machine learning have led to numerous powerful classifiers, their usefulness for modeling travel mode choice remains largely

Staining pattern classification of antinuclear autoantibodies based on block segmentation in indirect immunofluorescence images.

Directory of Open Access Journals (Sweden)

Jiaqian Li

Full Text Available Indirect immunofluorescence based on HEp-2 cell substrate is the most commonly used staining method for antinuclear autoantibodies associated with different types of autoimmune pathologies. The aim of this paper is to design an automatic system to identify the staining patterns based on block segmentation compared to the cell segmentation most used in previous research. Various feature descriptors and classifiers are tested and compared in the classification of the staining pattern of blocks and it is found that the technique of the combination of the local binary pattern and the k-nearest neighbor algorithm achieve the best performance. Relying on the results of block pattern classification, experiments on the whole images show that classifier fusion rules are able to identify the staining patterns of the whole well (specimen image with a total accuracy of about 94.62%.

Application Of t-Cherry Junction Trees in Pattern Recognition

Directory of Open Access Journals (Sweden)

Edith Kovacs

2010-06-01

Full Text Available Pattern recognition aims to classify data (patterns based ei-
ther on a priori knowledge or on statistical information extracted from the data. In this paper we will concentrate on statistical pattern recognition using a new probabilistic approach which makes possible to select the so called 'informative' features. We develop a pattern recognition algorithm which is based on the conditional independence structure underlying the statistical data. Our method was succesfully applied on a real problem of recognizing Parkinson's disease on the basis of voice disorders.

Classifying Sources Influencing Indoor Air Quality (IAQ Using Artificial Neural Network (ANN

Directory of Open Access Journals (Sweden)

Shaharil Mad Saad

2015-05-01

Full Text Available Monitoring indoor air quality (IAQ is deemed important nowadays. A sophisticated IAQ monitoring system which could classify the source influencing the IAQ is definitely going to be very helpful to the users. Therefore, in this paper, an IAQ monitoring system has been proposed with a newly added feature which enables the system to identify the sources influencing the level of IAQ. In order to achieve this, the data collected has been trained with artificial neural network or ANN—a proven method for pattern recognition. Basically, the proposed system consists of sensor module cloud (SMC, base station and service-oriented client. The SMC contain collections of sensor modules that measure the air quality data and transmit the captured data to base station through wireless network. The IAQ monitoring system is also equipped with IAQ Index and thermal comfort index which could tell the users about the room’s conditions. The results showed that the system is able to measure the level of air quality and successfully classify the sources influencing IAQ in various environments like ambient air, chemical presence, fragrance presence, foods and beverages and human activity.

Feature extraction for dynamic integration of classifiers

NARCIS (Netherlands)

Pechenizkiy, M.; Tsymbal, A.; Puuronen, S.; Patterson, D.W.

2007-01-01

Recent research has shown the integration of multiple classifiers to be one of the most important directions in machine learning and data mining. In this paper, we present an algorithm for the dynamic integration of classifiers in the space of extracted features (FEDIC). It is based on the technique

Classifying Floating Potential Measurement Unit Data Products as Science Data

Science.gov (United States)

Coffey, Victoria; Minow, Joseph

2015-01-01

We are Co-Investigators for the Floating Potential Measurement Unit (FPMU) on the International Space Station (ISS) and members of the FPMU operations and data analysis team. We are providing this memo for the purpose of classifying raw and processed FPMU data products and ancillary data as NASA science data with unrestricted, public availability in order to best support science uses of the data.

Classifying Returns as Extreme

DEFF Research Database (Denmark)

Christiansen, Charlotte

2014-01-01

I consider extreme returns for the stock and bond markets of 14 EU countries using two classification schemes: One, the univariate classification scheme from the previous literature that classifies extreme returns for each market separately, and two, a novel multivariate classification scheme tha...

The Protection of Classified Information: The Legal Framework

National Research Council Canada - National Science Library

Elsea, Jennifer K

2006-01-01

Recent incidents involving leaks of classified information have heightened interest in the legal framework that governs security classification, access to classified information, and penalties for improper disclosure...

Pattern analysis of defecography in patients with chronic functional constipation: is it predictable for the responsiveness of biofeedback therapy?

Energy Technology Data Exchange (ETDEWEB)

Yang, Hye Rin; Kim, Ah Young; Hong, Seong Sook; Byun, Jae Ho; Myung Seung Jae; Ha, Hyun Kwon [University of Ulsan of Medicine, Seoul (Korea, Republic of)

2005-08-15

To determine of pattern analysis of defecography can predict the responsiveness of biofeedback therapy in patients with chronic functional constipation. Over a two-year period, 104 patients with chronic functional constipation underwent defecography and biofeedback therapy. Two blinded readers analyzed the defecographic findings and classified them into six types; I = normal defecation, II = hypertonic lower anal sphincter (poor anal opening due to a persistent contraction of the lower anal sphincter), III dyskinetic puborectal sling (inadequate laxity of the puborectal sling), IV spastic pelvic floor syndrome (persistent contraction of both the puborectal sling and the lower and sphincter), V unclassified (including paradoxical contraction of the anal sphincter), VI anatomical obstruction. In addition, the degree of rectal contraction during defecation was scored (grade 0 to 3). After biofeedback therapy, the differences in the defecography patterns or rectal contraction between the two groups, the responsive or non-responsive group, were analyzed. The defecograms revealed that the type IV of the spastic pelvic floor syndrome was most common (50 of 104 patients, 48%), followed by II (21/104, 20%), III (12/104, 11.5%), V (9/104, 9%) and VI (12/104, 11.5%). Biofeedback therapy showed a therapeutic response in 71 out of 104 patients (68%) but failed in 33 patients (32%). However, there were no significant differences in the defecographic pattern between the responsive and non-responsive groups ({rho} = 0.630). The defecograms revealed contractions in 78 patients (75%) and moderate to vigorous contractions (more than grade 2) in 66 patients. Most of the biofeedback-responsive group showed rectal contractions (66 of 71 patients, 93%, {rho} < 0.001). In patients with chronic functional constipation, there was no significant difference in the morphological patterns of the defecogram between the responsive and non-responsive biofeedback groups. However, the presence of

Pattern analysis of defecography in patients with chronic functional constipation: is it predictable for the responsiveness of biofeedback therapy?

International Nuclear Information System (INIS)

Yang, Hye Rin; Kim, Ah Young; Hong, Seong Sook; Byun, Jae Ho; Myung Seung Jae; Ha, Hyun Kwon

2005-01-01

To determine of pattern analysis of defecography can predict the responsiveness of biofeedback therapy in patients with chronic functional constipation. Over a two-year period, 104 patients with chronic functional constipation underwent defecography and biofeedback therapy. Two blinded readers analyzed the defecographic findings and classified them into six types; I = normal defecation, II = hypertonic lower anal sphincter (poor anal opening due to a persistent contraction of the lower anal sphincter), III dyskinetic puborectal sling (inadequate laxity of the puborectal sling), IV spastic pelvic floor syndrome (persistent contraction of both the puborectal sling and the lower and sphincter), V unclassified (including paradoxical contraction of the anal sphincter), VI anatomical obstruction. In addition, the degree of rectal contraction during defecation was scored (grade 0 to 3). After biofeedback therapy, the differences in the defecography patterns or rectal contraction between the two groups, the responsive or non-responsive group, were analyzed. The defecograms revealed that the type IV of the spastic pelvic floor syndrome was most common (50 of 104 patients, 48%), followed by II (21/104, 20%), III (12/104, 11.5%), V (9/104, 9%) and VI (12/104, 11.5%). Biofeedback therapy showed a therapeutic response in 71 out of 104 patients (68%) but failed in 33 patients (32%). However, there were no significant differences in the defecographic pattern between the responsive and non-responsive groups (ρ = 0.630). The defecograms revealed contractions in 78 patients (75%) and moderate to vigorous contractions (more than grade 2) in 66 patients. Most of the biofeedback-responsive group showed rectal contractions (66 of 71 patients, 93%, ρ < 0.001). In patients with chronic functional constipation, there was no significant difference in the morphological patterns of the defecogram between the responsive and non-responsive biofeedback groups. However, the presence of rectal

Manual versus Automated Narrative Analysis of Agrammatic Production Patterns: The Northwestern Narrative Language Analysis and Computerized Language Analysis

Science.gov (United States)

Hsu, Chien-Ju; Thompson, Cynthia K.

2018-01-01

Purpose: The purpose of this study is to compare the outcomes of the manually coded Northwestern Narrative Language Analysis (NNLA) system, which was developed for characterizing agrammatic production patterns, and the automated Computerized Language Analysis (CLAN) system, which has recently been adopted to analyze speech samples of individuals…

Foot-strike pattern and performance in a marathon.

Science.gov (United States)

Kasmer, Mark E; Liu, Xue-Cheng; Roberts, Kyle G; Valadao, Jason M

2013-05-01

To determine prevalence of heel strike in a midsize city marathon, if there is an association between foot-strike classification and race performance, and if there is an association between foot-strike classification and gender. Foot-strike classification (forefoot, midfoot, heel, or split strike), gender, and rank (position in race) were recorded at the 8.1-km mark for 2112 runners at the 2011 Milwaukee Lakefront Marathon. 1991 runners were classified by foot-strike pattern, revealing a heel-strike prevalence of 93.67% (n = 1865). A significant difference between foot-strike classification and performance was found using a Kruskal-Wallis test (P strike. No significant difference between foot-strike classification and gender was found using a Fisher exact test. In addition, subgroup analysis of the 126 non-heel strikers found no significant difference between shoe wear and performance using a Kruskal-Wallis test. The high prevalence of heel striking observed in this study reflects the foot-strike pattern of most mid-distance to long-distance runners and, more important, may predict their injury profile based on the biomechanics of a heel-strike running pattern. This knowledge can help clinicians appropriately diagnose, manage, and train modifications of injured runners.

Stacking machine learning classifiers to identify Higgs bosons at the LHC

International Nuclear Information System (INIS)

Alves, A.

2017-01-01

Machine learning (ML) algorithms have been employed in the problem of classifying signal and background events with high accuracy in particle physics. In this paper, we compare the performance of a widespread ML technique, namely, stacked generalization , against the results of two state-of-art algorithms: (1) a deep neural network (DNN) in the task of discovering a new neutral Higgs boson and (2) a scalable machine learning system for tree boosting, in the Standard Model Higgs to tau leptons channel, both at the 8 TeV LHC. In a cut-and-count analysis, stacking three algorithms performed around 16% worse than DNN but demanding far less computation efforts, however, the same stacking outperforms boosted decision trees. Using the stacked classifiers in a multivariate statistical analysis (MVA), on the other hand, significantly enhances the statistical significance compared to cut-and-count in both Higgs processes, suggesting that combining an ensemble of simpler and faster ML algorithms with MVA tools is a better approach than building a complex state-of-art algorithm for cut-and-count.

Assessment of fractures classified as non-mineralised in the Sicada database

International Nuclear Information System (INIS)

Claesson Liljedahl, Lillemor; Munier, Raymond; Sandstroem, Bjoern; Drake, Henrik; Tullborg, Eva-Lena

2011-03-01

The general objective of this report was to describe the results of the investigation of fractures classified as non-mineralised in Sicada. Such fractures exist at Forsmark and at Laxemar. The main aims of the investigation of these fractures were to: - Quantify the number of non-mineralised fractures (i.e. fractures lacking mineral coating) in Sicada (table: p f ract c ore e shi). - Closely examine a selection of fractures recorded as non-mineralised in Sicada. - Outline possible reasons for the existence of non-mineralised fractures. The work has involved extraction of fracture data from Sicada and subsequent statistical analysis. Since several thousand fractures are classified as non-mineralised in Sicada, it was not a practical possibility to include all these in this study, we examined one fracture sub-set from each site. We investigated a sample of 204 of these fractures in detail (see Sections 1.1 and 2.4). Rock mechanical differences between Forsmark and Laxemar and kinematic analysis of fracture surfaces is not discussed in this report

Detection of tuberculosis patterns in digital photographs of chest X-ray images using Deep Learning: feasibility study.

Science.gov (United States)

Becker, A S; Blüthgen, C; Phi van, V D; Sekaggya-Wiltshire, C; Castelnuovo, B; Kambugu, A; Fehr, J; Frauenfelder, T

2018-03-01

To evaluate the feasibility of Deep Learning-based detection and classification of pathological patterns in a set of digital photographs of chest X-ray (CXR) images of tuberculosis (TB) patients. In this prospective, observational study, patients with previously diagnosed TB were enrolled. Photographs of their CXRs were taken using a consumer-grade digital still camera. The images were stratified by pathological patterns into classes: cavity, consolidation, effusion, interstitial changes, miliary pattern or normal examination. Image analysis was performed with commercially available Deep Learning software in two steps. Pathological areas were first localised; detected areas were then classified. Detection was assessed using receiver operating characteristics (ROC) analysis, and classification using a confusion matrix. The study cohort was 138 patients with human immunodeficiency virus (HIV) and TB co-infection (median age 34 years, IQR 28-40); 54 patients were female. Localisation of pathological areas was excellent (area under the ROC curve 0.82). The software could perfectly distinguish pleural effusions from intraparenchymal changes. The most frequent misclassifications were consolidations as cavitations, and miliary patterns as interstitial patterns (and vice versa). Deep Learning analysis of CXR photographs is a promising tool. Further efforts are needed to build larger, high-quality data sets to achieve better diagnostic performance.

Energy-Efficient Neuromorphic Classifiers.

Science.gov (United States)

Martí, Daniel; Rigotti, Mattia; Seok, Mingoo; Fusi, Stefano

2016-10-01

Neuromorphic engineering combines the architectural and computational principles of systems neuroscience with semiconductor electronics, with the aim of building efficient and compact devices that mimic the synaptic and neural machinery of the brain. The energy consumptions promised by neuromorphic engineering are extremely low, comparable to those of the nervous system. Until now, however, the neuromorphic approach has been restricted to relatively simple circuits and specialized functions, thereby obfuscating a direct comparison of their energy consumption to that used by conventional von Neumann digital machines solving real-world tasks. Here we show that a recent technology developed by IBM can be leveraged to realize neuromorphic circuits that operate as classifiers of complex real-world stimuli. Specifically, we provide a set of general prescriptions to enable the practical implementation of neural architectures that compete with state-of-the-art classifiers. We also show that the energy consumption of these architectures, realized on the IBM chip, is typically two or more orders of magnitude lower than that of conventional digital machines implementing classifiers with comparable performance. Moreover, the spike-based dynamics display a trade-off between integration time and accuracy, which naturally translates into algorithms that can be flexibly deployed for either fast and approximate classifications, or more accurate classifications at the mere expense of longer running times and higher energy costs. This work finally proves that the neuromorphic approach can be efficiently used in real-world applications and has significant advantages over conventional digital devices when energy consumption is considered.

Pattern Recognition of the Multiple Sclerosis Syndrome

Science.gov (United States)

Stewart, Renee; Healey, Kathleen M.

2017-01-01

During recent decades, the autoimmune disease neuromyelitis optica spectrum disorder (NMOSD), once broadly classified under the umbrella of multiple sclerosis (MS), has been extended to include autoimmune inflammatory conditions of the central nervous system (CNS), which are now diagnosable with serum serological tests. These antibody-mediated inflammatory diseases of the CNS share a clinical presentation to MS. A number of practical learning points emerge in this review, which is geared toward the pattern recognition of optic neuritis, transverse myelitis, brainstem/cerebellar and hemispheric tumefactive demyelinating lesion (TDL)-associated MS, aquaporin-4-antibody and myelin oligodendrocyte glycoprotein (MOG)-antibody NMOSD, overlap syndrome, and some yet-to-be-defined/classified demyelinating disease, all unspecifically labeled under MS syndrome. The goal of this review is to increase clinicians’ awareness of the clinical nuances of the autoimmune conditions for MS and NMSOD, and to highlight highly suggestive patterns of clinical, paraclinical or imaging presentations in order to improve differentiation. With overlay in clinical manifestations between MS and NMOSD, magnetic resonance imaging (MRI) of the brain, orbits and spinal cord, serology, and most importantly, high index of suspicion based on pattern recognition, will help lead to the final diagnosis. PMID:29064441

Classifying MCI Subtypes in Community-Dwelling Elderly Using Cross-Sectional and Longitudinal MRI-Based Biomarkers

Directory of Open Access Journals (Sweden)

Hao Guan

2017-09-01

Full Text Available Amnestic MCI (aMCI and non-amnestic MCI (naMCI are considered to differ in etiology and outcome. Accurately classifying MCI into meaningful subtypes would enable early intervention with targeted treatment. In this study, we employed structural magnetic resonance imaging (MRI for MCI subtype classification. This was carried out in a sample of 184 community-dwelling individuals (aged 73–85 years. Cortical surface based measurements were computed from longitudinal and cross-sectional scans. By introducing a feature selection algorithm, we identified a set of discriminative features, and further investigated the temporal patterns of these features. A voting classifier was trained and evaluated via 10 iterations of cross-validation. The best classification accuracies achieved were: 77% (naMCI vs. aMCI, 81% (aMCI vs. cognitively normal (CN and 70% (naMCI vs. CN. The best results for differentiating aMCI from naMCI were achieved with baseline features. Hippocampus, amygdala and frontal pole were found to be most discriminative for classifying MCI subtypes. Additionally, we observed the dynamics of classification of several MRI biomarkers. Learning the dynamics of atrophy may aid in the development of better biomarkers, as it may track the progression of cognitive impairment.

Universal Keyword Classifier on Public Key Based Encrypted Multikeyword Fuzzy Search in Public Cloud

Directory of Open Access Journals (Sweden)

Shyamala Devi Munisamy

2015-01-01

Full Text Available Cloud computing has pioneered the emerging world by manifesting itself as a service through internet and facilitates third party infrastructure and applications. While customers have no visibility on how their data is stored on service provider’s premises, it offers greater benefits in lowering infrastructure costs and delivering more flexibility and simplicity in managing private data. The opportunity to use cloud services on pay-per-use basis provides comfort for private data owners in managing costs and data. With the pervasive usage of internet, the focus has now shifted towards effective data utilization on the cloud without compromising security concerns. In the pursuit of increasing data utilization on public cloud storage, the key is to make effective data access through several fuzzy searching techniques. In this paper, we have discussed the existing fuzzy searching techniques and focused on reducing the searching time on the cloud storage server for effective data utilization. Our proposed Asymmetric Classifier Multikeyword Fuzzy Search method provides classifier search server that creates universal keyword classifier for the multiple keyword request which greatly reduces the searching time by learning the search path pattern for all the keywords in the fuzzy keyword set. The objective of using BTree fuzzy searchable index is to resolve typos and representation inconsistencies and also to facilitate effective data utilization.

Convenience-based food purchase patterns: identification and associations with dietary quality, sociodemographic factors and attitudes.

Science.gov (United States)

Peltner, Jonas; Thiele, Silke

2018-02-01

The present study aimed to derive food purchase patterns considering the convenience level of foods. Associations between identified patterns and dietary quality were analysed, as well as household characteristics associated with the dietary patterns. A Convenience Food Classification Scheme (CFCS) was developed. After classifying basic food groups into the CFCS, the formed groups were used to apply a factor analysis to identify convenience-based food purchase patterns. For these patterns nutrient and energy densities were examined. Using regression analysis, associations between the adherence to the patterns and household characteristic and attitude variables were analysed. The study used representative German food purchase data from 2011. Approximately 12 million purchases of 13 131 households were recorded in these data. Three convenience-based patterns were identified: a low-convenience, a semi-convenience and a ready-to-eat food pattern. Tighter adherence to the semi-convenience pattern was shown to result in the lowest nutrient and highest energy densities. Important factors influencing adherence to the patterns were household size, presence of children and attitudes. Working full-time was negatively associated with adherence to the low-convenience pattern and positively with the ready-to-eat pattern. Convenience foods were an important part of households' food baskets which in some cases led to lower nutritional quality. Therefore, it is important to offer convenience foods higher in nutrient density and lower in energy density. Interventions targeted on enhancing cooking skills could be an effective strategy to increase purchases of unprocessed foods, which, in turn, could also contribute to an improved diet quality.

Axi-symmetric patterns of active polar filaments on spherical and composite surfaces

Science.gov (United States)

Srivastava, Pragya; Rao, Madan

2014-03-01

Experiments performed on Fission Yeast cells of cylindrical and spherical shapes, rod-shaped bacteria and reconstituted cylindrical liposomes suggest the influence of cell geometry on patterning of cortical actin. A theoretical model based on active hydrodynamic description of cortical actin that includes curvature-orientation coupling predicts spontaneous formation of acto-myosin rings, cables and nodes on cylindrical and spherical geometries [P. Srivastava et al, PRL 110, 168104(2013)]. Stability and dynamics of these patterns is also affected by the cellular shape and has been observed in experiments performed on Fission Yeast cells of spherical shape. Motivated by this, we study the stability and dynamics of axi-symmetric patterns of active polar filaments on the surfaces of spherical, saddle shaped and conical geometry and classify the stable steady state patterns on these surfaces. Based on the analysis of the fluorescence images of Myosin-II during ring slippage we propose a simple mechanical model for ring-sliding based on force balance and make quantitative comparison with the experiments performed on Fission Yeast cells. NSF Grant DMR-1004789 and Syracuse Soft Matter Program.

Exploration of Hand Grasp Patterns Elicitable Through Non-Invasive Proximal Nerve Stimulation.

Science.gov (United States)

Shin, Henry; Watkins, Zach; Hu, Xiaogang

2017-11-29

Various neurological conditions, such as stroke or spinal cord injury, result in an impaired control of the hand. One method of restoring this impairment is through functional electrical stimulation (FES). However, traditional FES techniques often lead to quick fatigue and unnatural ballistic movements. In this study, we sought to explore the capabilities of a non-invasive proximal nerve stimulation technique in eliciting various hand grasp patterns. The ulnar and median nerves proximal to the elbow joint were activated transcutanously using a programmable stimulator, and the resultant finger flexion joint angles were recorded using a motion capture system. The individual finger motions averaged across the three joints were analyzed using a cluster analysis, in order to classify the different hand grasp patterns. With low current intensity (grasp patterns including single finger movement and coordinated multi-finger movements. This study provides initial evidence on the feasibility of a proximal nerve stimulation technique in controlling a variety of finger movements and grasp patterns. Our approach could also be developed into a rehabilitative/assistive tool that can result in flexible movements of the fingers.

Rotation-invariant neural pattern recognition system with application to coin recognition.

Science.gov (United States)

Fukumi, M; Omatu, S; Takeda, F; Kosaka, T

1992-01-01

In pattern recognition, it is often necessary to deal with problems to classify a transformed pattern. A neural pattern recognition system which is insensitive to rotation of input pattern by various degrees is proposed. The system consists of a fixed invariance network with many slabs and a trainable multilayered network. The system was used in a rotation-invariant coin recognition problem to distinguish between a 500 yen coin and a 500 won coin. The results show that the approach works well for variable rotation pattern recognition.

Classifying multiple types of hand motions using electrocorticography during intraoperative awake craniotomy and seizure monitoring processes—case studies

Science.gov (United States)

Xie, Tao; Zhang, Dingguo; Wu, Zehan; Chen, Liang; Zhu, Xiangyang

2015-01-01

In this work, some case studies were conducted to classify several kinds of hand motions from electrocorticography (ECoG) signals during intraoperative awake craniotomy & extraoperative seizure monitoring processes. Four subjects (P1, P2 with intractable epilepsy during seizure monitoring and P3, P4 with brain tumor during awake craniotomy) participated in the experiments. Subjects performed three types of hand motions (Grasp, Thumb-finger motion and Index-finger motion) contralateral to the motor cortex covered with ECoG electrodes. Two methods were used for signal processing. Method I: autoregressive (AR) model with burg method was applied to extract features, and additional waveform length (WL) feature has been considered, finally the linear discriminative analysis (LDA) was used as the classifier. Method II: stationary subspace analysis (SSA) was applied for data preprocessing, and the common spatial pattern (CSP) was used for feature extraction before LDA decoding process. Applying method I, the three-class accuracy of P1~P4 were 90.17, 96.00, 91.77, and 92.95% respectively. For method II, the three-class accuracy of P1~P4 were 72.00, 93.17, 95.22, and 90.36% respectively. This study verified the possibility of decoding multiple hand motion types during an awake craniotomy, which is the first step toward dexterous neuroprosthetic control during surgical implantation, in order to verify the optimal placement of electrodes. The accuracy during awake craniotomy was comparable to results during seizure monitoring. This study also indicated that ECoG was a promising approach for precise identification of eloquent cortex during awake craniotomy, and might form a promising BCI system that could benefit both patients and neurosurgeons. PMID:26483627

Verification of classified fissile material using unclassified attributes

International Nuclear Information System (INIS)

Nicholas, N.J.; Fearey, B.L.; Puckett, J.M.; Tape, J.W.

1998-01-01

This paper reports on the most recent efforts of US technical experts to explore verification by IAEA of unclassified attributes of classified excess fissile material. Two propositions are discussed: (1) that multiple unclassified attributes could be declared by the host nation and then verified (and reverified) by the IAEA in order to provide confidence in that declaration of a classified (or unclassified) inventory while protecting classified or sensitive information; and (2) that attributes could be measured, remeasured, or monitored to provide continuity of knowledge in a nonintrusive and unclassified manner. They believe attributes should relate to characteristics of excess weapons materials and should be verifiable and authenticatable with methods usable by IAEA inspectors. Further, attributes (along with the methods to measure them) must not reveal any classified information. The approach that the authors have taken is as follows: (1) assume certain attributes of classified excess material, (2) identify passive signatures, (3) determine range of applicable measurement physics, (4) develop a set of criteria to assess and select measurement technologies, (5) select existing instrumentation for proof-of-principle measurements and demonstration, and (6) develop and design information barriers to protect classified information. While the attribute verification concepts and measurements discussed in this paper appear promising, neither the attribute verification approach nor the measurement technologies have been fully developed, tested, and evaluated

Ictal cerebral perfusion patterns in partial epilepsy: SPECT subtraction

International Nuclear Information System (INIS)

Lee, Hyang Woon; Hong, Seung Bong; Tae, Woo Suk; Kim, Sang Eun; Seo, Dae Won; Jeong, Seung Cheol; Yi, Ji Young; Hong, Seung Chyul

2000-01-01

To investigate the various ictal perfusion patterns and find the relationships between clinical factors and different perfusion patterns. Interictal and ictal SPECT and SPECT subtraction were performed in 61 patients with partial epilepsy. Both positive images showing ictal hyperperfusion and negative images revealing ictal hypoperfusion were obtained by SPECT subtraction. The ictal perfusion patterns of subtracted SPECT were classified into focal hyperperfusion, hyperperfusion-plus, combined hyperperfusion-hypoperfusion, and focal hypoperfusion only. The concordance rates with epileptic focus were 91.8% in combined analysis of ictal hyperperfusion and hypoperfusion images of subtracted SPECT, 85.2% in hyperperfusion images only of subtracted SPECT, and 68.9% in conventional ictal SPECT analysis. Ictal hypoperfusion occurred less frequently in temporal lobe epilepsy (TLE) than extratemporal lobe epilepsy. Mesial temporal hyperperfusion alone was seen only in mesial TLE while lateral temporal hyperperfusion alone was observed only in neocortical TLE. Hippocampal sclerosis had much lower incidence of ictal hypoperfusion than any other pathology. Some patients showed ictal hypoperfusion at epileptic focus with ictal hyperperfusion in the neighboring brain regions where ictal discharges propagated. Hypoperfusion as well as hyperperfusion in ictal SPECT should be considered for localizing epileptic focus. Although the mechanism of ictal hypoperfusion could be an intra-ictal early exhaustion of seizure focus or a steal phenomenon by the propagation of ictal discharges to adjacent brain areas, further study is needed to elucidate it.=20

Ictal cerebral perfusion patterns in partial epilepsy: SPECT subtraction

Energy Technology Data Exchange (ETDEWEB)

Lee, Hyang Woon; Hong, Seung Bong; Tae, Woo Suk; Kim, Sang Eun; Seo, Dae Won; Jeong, Seung Cheol; Yi, Ji Young; Hong, Seung Chyul [Sungkyunkwan Univ. School of Medicine, Seoul (Korea, Republic of)

2000-06-01

To investigate the various ictal perfusion patterns and find the relationships between clinical factors and different perfusion patterns. Interictal and ictal SPECT and SPECT subtraction were performed in 61 patients with partial epilepsy. Both positive images showing ictal hyperperfusion and negative images revealing ictal hypoperfusion were obtained by SPECT subtraction. The ictal perfusion patterns of subtracted SPECT were classified into focal hyperperfusion, hyperperfusion-plus, combined hyperperfusion-hypoperfusion, and focal hypoperfusion only. The concordance rates with epileptic focus were 91.8% in combined analysis of ictal hyperperfusion and hypoperfusion images of subtracted SPECT, 85.2% in hyperperfusion images only of subtracted SPECT, and 68.9% in conventional ictal SPECT analysis. Ictal hypoperfusion occurred less frequently in temporal lobe epilepsy (TLE) than extratemporal lobe epilepsy. Mesial temporal hyperperfusion alone was seen only in mesial TLE while lateral temporal hyperperfusion alone was observed only in neocortical TLE. Hippocampal sclerosis had much lower incidence of ictal hypoperfusion than any other pathology. Some patients showed ictal hypoperfusion at epileptic focus with ictal hyperperfusion in the neighboring brain regions where ictal discharges propagated. Hypoperfusion as well as hyperperfusion in ictal SPECT should be considered for localizing epileptic focus. Although the mechanism of ictal hypoperfusion could be an intra-ictal early exhaustion of seizure focus or a steal phenomenon by the propagation of ictal discharges to adjacent brain areas, further study is needed to elucidate it.

Patterns, Severity, and Management of Maxillofacial Injuries in a ...

African Journals Online (AJOL)

exposure.[3]. The changing etiological factors and patterns of maxillofacial injuries reported .... Ivy and Curtis[13] system while maxillary fractures were classified .... diligence and compliance to keep a good oral hygiene and prevent infection.

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.

Reinforcement Learning Based Artificial Immune Classifier

Directory of Open Access Journals (Sweden)

Mehmet Karakose

2013-01-01

Full Text Available One of the widely used methods for classification that is a decision-making process is artificial immune systems. Artificial immune systems based on natural immunity system can be successfully applied for classification, optimization, recognition, and learning in real-world problems. In this study, a reinforcement learning based artificial immune classifier is proposed as a new approach. This approach uses reinforcement learning to find better antibody with immune operators. The proposed new approach has many contributions according to other methods in the literature such as effectiveness, less memory cell, high accuracy, speed, and data adaptability. The performance of the proposed approach is demonstrated by simulation and experimental results using real data in Matlab and FPGA. Some benchmark data and remote image data are used for experimental results. The comparative results with supervised/unsupervised based artificial immune system, negative selection classifier, and resource limited artificial immune classifier are given to demonstrate the effectiveness of the proposed new method.

Optimal reduced-rank quadratic classifiers using the Fukunaga-Koontz transform with applications to automated target recognition

Science.gov (United States)

Huo, Xiaoming; Elad, Michael; Flesia, Ana G.; Muise, Robert R.; Stanfill, S. Robert; Friedman, Jerome; Popescu, Bogdan; Chen, Jihong; Mahalanobis, Abhijit; Donoho, David L.

2003-09-01

In target recognition applications of discriminant of classification analysis, each 'feature' is a result of a convolution of an imagery with a filter, which may be derived from a feature vector. It is important to use relatively few features. We analyze an optimal reduced-rank classifier under the two-class situation. Assuming each population is Gaussian and has zero mean, and the classes differ through the covariance matrices: ∑1 and ∑2. The following matrix is considered: Λ=(∑1+∑2)-1/2∑1(∑1+∑2)-1/2. We show that the k eigenvectors of this matrix whose eigenvalues are most different from 1/2 offer the best rank k approximation to the maximum likelihood classifier. The matrix Λ and its eigenvectors have been introduced by Fukunaga and Koontz; hence this analysis gives a new interpretation of the well known Fukunaga-Koontz transform. The optimality that is promised in this method hold if the two populations are exactly Guassian with the same means. To check the applicability of this approach to real data, an experiment is performed, in which several 'modern' classifiers were used on an Infrared ATR data. In these experiments, a reduced-rank classifier-Tuned Basis Functions-outperforms others. The competitive performance of the optimal reduced-rank quadratic classifier suggests that, at least for classification purposes, the imagery data behaves in a nearly-Gaussian fashion.

Use of Design Patterns According to Hand Dominance in a Mobile User Interface

Science.gov (United States)

Al-Samarraie, Hosam; Ahmad, Yusof

2016-01-01

User interface (UI) design patterns for mobile applications provide a solution to design problems and can improve the usage experience for users. However, there is a lack of research categorizing the uses of design patterns according to users' hand dominance in a learning-based mobile UI. We classified the main design patterns for mobile…

Intelligent Garbage Classifier