Search

The accuracy of time-delay estimation (TDE) in ultrasound elastography is usually measured by calculating the value of normalized cross correlation (NCC) at the estimated displacement. NCC value, however, could be very high at a displacement estimate with large error, a well-known problem in TDE referred to as peak-hopping. Furthermore, NCC value could suffer from jitter error, which is due to electric noise and signal decorrelation. Herein, we propose a novel method to assess the accuracy of TDE by investigating the NCC profile around the estimated time-delay. We extract several features from the NCC profile, and utilize support vector machine to classify peak-hopping and jitter error. The results on simulation, phantom, and in vivo data show the significant improvement of the proposed algorithm compared to the state of the art techniques. [ABSTRACT FROM PUBLISHER]

Model selection plays an important role in cost-sensitive SVM (CS-SVM). It has been proven that the global minimum cross validation (CV) error can be efficiently computed based on the solution path for one parameter learning problems. However, it is a challenge to obtain the global minimum CV error for CS-SVM based on one-dimensional solution path and traditional grid search, because CS-SVM is with two regularization parameters. In this paper, we propose a solution and error surfaces based CV approach (CV-SES). More specifically, we first compute a two-dimensional solution surface for CS-SVM based on a bi-parameter space partition algorithm, which can fit solutions of CS-SVM for all values of both regularization parameters. Then, we compute a two-dimensional validation error surface for each CV fold, which can fit validation errors of CS-SVM for all values of both regularization parameters. Finally, we obtain the CV error surface by superposing $K$ validation error surfaces, which can find the global minimum CV error of CS-SVM. Experiments are conducted on seven datasets for cost sensitive learning and on four datasets for imbalanced learning. Experimental results not only show that our proposed CV-SES has a better generalization ability than CS-SVM with various hybrids between grid search and solution path methods, and than recent proposed cost-sensitive hinge loss SVM with three-dimensional grid search, but also show that CV-SES uses less running time. [ABSTRACT FROM AUTHOR]

The problem of estimating the dynamic direction of arrival (DOA) of far-field signals impinging on a uniform linear array, with mutual coupling effects, is addressed. This paper proposes two novel approaches able to provide accurate solutions, including at the endfire regions of the array. First, a Bayesian compressive sensing Kalman filter is developed, which accounts for the predicted estimated signals rather than using the traditional sparse prior. The posterior probability density function of the received source signals and the expression for the related marginal likelihood function are derived theoretically. Next, a Gibbs sampling-based approach with indicator variables in the sparsity prior is developed. This allows sparsity to be explicitly enforced in different ways, including when an angle is too far from the previous estimate. The proposed approaches are validated and evaluated over different test scenarios and compared to the traditional relevance vector machine (RVM)-based method. An improved accuracy in terms of average root-mean-square error values is achieved (up to 73.39% for the modified RVM-based approach and 86.36% for the Gibbs sampling-based approach). The proposed approaches prove to be particularly useful for DOA estimation when the angle of arrival moves into the endfire region of the array. [ABSTRACT FROM AUTHOR]

Vehicle detection and vehicle viewpoint estimation are both crucial for assistive and autonomous driving systems. In this paper, we propose a soft discriminative mixture of viewpoint (SDMoV) models for joint vehicle detection and vehicle viewpoint estimation. The proposed SDMoV model is learned in two steps. First, a discriminative viewpoint-specific component model, which aims to maximize vehicle viewpoint classification accuracy, is learned for each cluster of vehicle images with similar viewpoint. Second, a new soft margin objective function, which aims to maximize vehicle detection accuracy, is designed to retrain these component models into a mixture of viewpoint models. The proposed SDMoV model is capable of detecting vehicles and estimating their viewpoints simultaneously. Experiments on three state-of-the-art datasets show that the proposed SDMoV model achieves superior accuracy for both vehicle detection and vehicle viewpoint estimation tasks. [ABSTRACT FROM AUTHOR]

Traditional gene selection methods for microarray data mainly considered the features’ relevance by evaluating their utility for achieving accurate predication or exploiting data variance and distribution, and the selected genes were usually poorly explicable. To improve the interpretability of the selected genes as well as prediction accuracy, an improved gene selection method based on binary particle swarm optimization (BPSO) and prior information is proposed in this paper. In the proposed method, BPSO encoding gene-to-class sensitivity (GCS) information is used to perform gene selection. The gene-to-class sensitivity information, extracted from the samples by extreme learning machine (ELM), is encoded into the selection process in four aspects: initializing particles, updating the particles, modifying maximum velocity, and adopting mutation operation adaptively. Constrained by the gene-to-class sensitivity information, the new method can select functional gene subsets which are significantly sensitive to the samples’ classes. With the few discriminative genes selected by the proposed method, ELM, K-nearest neighbor and support vector machine classifiers achieve much high prediction accuracy on five public microarray data, which in turn verifies the efficiency and effectiveness of the proposed gene selection method. [ABSTRACT FROM PUBLISHER]

Physiological signals are often organized in the form of multiple dimensions (e.g., channel, time, task, and 3-D voxel), so it is better to preserve original organization structure when processing. Unlike vector-based methods that destroy data structure, canonical polyadic decomposition (CPD) aims to process physiological signals in the form of multiway array, which considers relationships between dimensions and preserves structure information contained by the physiological signal. Nowadays, CPD is utilized as an unsupervised method for feature extraction in a classification problem. After that, a classifier, such as support vector machine, is required to classify those features. In this manner, classification task is achieved in two isolated steps. We proposed supervised CPD by directly incorporating auxiliary label information during decomposition, by which a classification task can be achieved without an extra step of classifier training. The proposed method merges the decomposition and classifier learning together, so it reduces procedure of classification task compared with that of respective decomposition and classification. In order to evaluate the performance of the proposed method, three different kinds of signals, synthetic signal, EEG signal, and MEG signal, were used. The results based on evaluations of synthetic and real signals demonstrated that the proposed method is effective and efficient. [ABSTRACT FROM AUTHOR]

Blur detection in a single image is challenging especially when the blur is spatially-varying. Developing discriminative blur features is an open problem. In this paper, we propose a new kernel-specific feature vector consisting of the information of a blur kernel and the information of an image patch. Specifically, the kernel specific-feature is composed of the multiplication of the variance of filtered kernel and the variance of filtered patch gradients. The feature origins from a blur-classification theorem and its discrimination can also be intuitively explained. To make the kernel-specific features useful for real applications, we build a pool of kernels consisting of motion-blur kernels, defocus-blur (out-of-focus) kernels, and their combinations. By extracting such features followed by the classifiers, the proposed algorithm outperforms the state-of-the-art blur detection method. Experimental results on public databases demonstrate the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]

Deep convolutional networks have proven to be very successful in learning task specific features that allow for unprecedented performance on various computer vision tasks. Training of such networks follows mostly the supervised learning paradigm, where sufficiently many input-output pairs are required for training. Acquisition of large training sets is one of the key challenges, when approaching a new task. In this paper, we aim for generic feature learning and present an approach for training a convolutional network using only unlabeled data. To this end, we train the network to discriminate between a set of surrogate classes. Each surrogate class is formed by applying a variety of transformations to a randomly sampled ‘seed’ image patch. In contrast to supervised network training, the resulting feature representation is not class specific. It rather provides robustness to the transformations that have been applied during training. This generic feature representation allows for classification results that outperform the state of the art for unsupervised learning on several popular datasets (STL-10, CIFAR-10, Caltech-101, Caltech-256). While features learned with our approach cannot compete with class specific features from supervised training on a classification task, we show that they are advantageous on geometric matching problems, where they also outperform the SIFT descriptor. [ABSTRACT FROM AUTHOR]

In this paper, we analyze the spectrum occupancy in cognitive radio networks (CRNs) using different machine learning techniques. Both supervised techniques [naive Bayesian classifier (NBC), decision trees (DT), support vector machine (SVM), linear regression (LR)] and unsupervised algorithms [hidden Markov model (HMM)] are studied to find the best technique with the highest classification accuracy (CA). A detailed comparison of the supervised and unsupervised algorithms in terms of the computational time and the CA is performed. The classified occupancy status is further utilized to evaluate the blocking probability of secondary user for future time slots, which can be used by system designers to define spectrum-allocation and spectrum-sharing policies. Numerical results show that SVM is the best algorithm among all the supervised and unsupervised classifiers. Based on this, we proposed a new SVM algorithm by combining it with a firefly algorithm (FFA), which is shown to outperform all the other algorithms. [ABSTRACT FROM PUBLISHER]

This paper proposes a spectral–spatial feature learning (SSFL) method to obtain robust features of hyperspectral images (HSIs). It combines the spectral feature learning and spatial feature learning in a hierarchical fashion. Stacking a set of SSFL units, a deep hierarchical model called the spectral–spatial networks (SSN) is further proposed for HSI classification. SSN can exploit both discriminative spectral and spatial information simultaneously. Specifically, SSN learns useful high-level features by alternating between spectral and spatial feature learning operations. Then, kernel-based extreme learning machine (KELM), a shallow neural network, is embedded in SSN to classify image pixels. Extensive experiments are performed on two benchmark HSI datasets to verify the effectiveness of SSN. Compared with state-of-the-art methods, SSN with a deep hierarchical architecture obtains higher classification accuracy in terms of the overall accuracy, average accuracy, and kappa ( \kappa ) coefficient of agreement, especially when the number of the training samples is small. [ABSTRACT FROM PUBLISHER]

An automated fall detection system based on smartphone audio features is developed. The spectrogram, mel frequency cepstral coefficents (MFCCs), linear predictive coding (LPC), and matching pursuit (MP) features of different fall and no-fall sound events are extracted from experimental data. Based on the extracted audio features, four different machine learning classifiers: k-nearest neighbor classifier (k-NN), support vector machine (SVM), least squares method (LSM), and artificial neural network (ANN) are investigated for distinguishing between fall and no-fall events. For each audio feature, the performance of each classifier in terms of sensitivity, specificity, accuracy, and computational complexity is evaluated. The best performance is achieved using spectrogram features with ANN classifier with sensitivity, specificity, and accuracy all above $98\%$. The classifier also has acceptable computational requirement for training and testing. The system is applicable in home environments where the phone is placed in the vicinity of the user. [ABSTRACT FROM AUTHOR]

An emerging trend in feature selection is the development of two-objective algorithms that analyze the tradeoff between the number of features and the classification performance of the model built with these features. Since these two objectives are conflicting, a typical result stands in a set of Pareto-efficient subsets, each having a different cardinality and a corresponding discriminating power. However, this approach overlooks the fact that, for a given cardinality, there can be several subsets with similar information content. The study reported here addresses this problem, and introduces a novel multiobjective feature selection approach conceived to identify: 1) a subset that maximizes the performance of a given classifier and 2) a set of subsets that are quasi equally informative, i.e., have almost same classification performance, to the performance maximizing subset. The approach consists of a wrapper [Wrapper for Quasi Equally Informative Subset Selection (W-QEISS)] built on the formulation of a four-objective optimization problem, which is aimed at maximizing the accuracy of a classifier, minimizing the number of features, and optimizing two entropy-based measures of relevance and redundancy. This allows conducting the search in a larger space, thus enabling the wrapper to generate a large number of Pareto-efficient solutions. The algorithm is compared against the mRMR algorithm, a two-objective wrapper and a computationally efficient filter [Filter for Quasi Equally Informative Subset Selection (F-QEISS)] on 24 University of California, Irvine, (UCI) datasets including both binary and multiclass classification. Experimental results show that W-QEISS has the capability of evolving a rich and diverse set of Pareto-efficient solutions, and that their availability helps in: 1) studying the tradeoff between multiple measures of classification performance and 2) understanding the relative importance of each feature. The quasi equally informative subsets are identified at the cost of a marginal increase in the computational time thanks to the adoption of Borg Multiobjective Evolutionary Algorithm and Extreme Learning Machine as global optimization and learning algorithms, respectively. [ABSTRACT FROM PUBLISHER]

Respiratory disorder is a highly prevalent condition associated with many adverse health problems. As the current means of diagnosis are obtrusive and ill-suited for real-time m-health applications, we explore a convenient and low-cost automatic approach that uses wearable microelectromechanical system sensor technology. The proposed system introduces the use of motion sensors to detect the changes in the anterior–posterior diameter of the chest wall during breathing function as well as extracting the informative respiratory features to be used for breathing disorders classification. Extensive evaluations are provided on six well-known classifiers with novel feature extraction techniques to distinguish among eight different pathological breathing patterns. The effects of the number of sensors, sensor placement, as well as feature selection on the classification performance are discussed. The experimental results conducted with ten subjects show the best accuracy rates of 97.50% by support vector machine and 97.37% with decision tree bagging (DTB) with all features and after feature selection, correspondingly. Furthermore, a binary classification is proposed for distinguishing between healthy people and patients with breath problems. The different assessments of classification parameters are provided by measuring the accuracy, sensitivity, specificity, F1-score and Mathew correlation coefficient. The accuracy rates above 98% suggest superior performance of DTB in binary recognition supported by the suggested new features. [ABSTRACT FROM PUBLISHER]

Wireless capsule endoscopy (WCE) needs computerized method to reduce the review time for its large image data. In this paper, we propose an improved bag of feature (BoF) method to assist classification of polyps in WCE images. Instead of utilizing a single scale-invariant feature transform (SIFT) feature in the traditional BoF method, we extract different textural features from the neighborhoods of the key points and integrate them together as synthetic descriptors to carry out classification tasks. Specifically, we study influence of the number of visual words, the patch size and different classification methods in terms of classification performance. Comprehensive experimental results reveal that the best classification performance is obtained with the integrated feature strategy using the SIFT and the complete local binary pattern (CLBP) feature, the visual words with a length of 120, the patch size of 8*8, and the support vector machine (SVM). The achieved classification accuracy reaches 93.2%, confirming that the proposed scheme is promising for classification of polyps in WCE images. [ABSTRACT FROM AUTHOR]

In this paper, we propose SVR-NoC, a network-on-chip (NoC) latency model using support vector regression (SVR). More specifically, based on the application communication information and the NoC routing algorithm, the channel and source queue waiting times are first estimated using an analytical queuing model with two equivalent queues. To improve the prediction accuracy, the queuing theory-based delay estimations are included as features in the learning process. We then propose a learning framework that relies on SVR to collect training data and predict the traffic flow latency. The proposed learning methods can be used to analyze various traffic scenarios for the target NoC platform. Experimental results on both synthetic and real-application traffic demonstrate on average less than 12% prediction error in network saturation load, as well as more than $100\times $ speedup compared to cycle-accurate simulations can be achieved. [ABSTRACT FROM PUBLISHER]

Large image datasets such as ImageNet or open-ended photo websites like Flickr are revealing new challenges to image classification that were not apparent in smaller, fixed sets. In particular, the efficient handling of dynamically growing datasets, where not only the amount of training data but also the number of classes increases over time, is a relatively unexplored problem. In this challenging setting, we study how two variants of Random Forests (RF) perform under four strategies to incorporate new classes while avoiding to retrain the RFs from scratch. The various strategies account for different trade-offs between classification accuracy and computational efficiency. In our extensive experiments, we show that both RF variants, one based on Nearest Class Mean classifiers and the other on SVMs, outperform conventional RFs and are well suited for incrementally learning new classes. In particular, we show that RFs initially trained with just 10 classes can be extended to 1,000 classes with an acceptable loss of accuracy compared to training from the full data and with great computational savings compared to retraining for each new batch of classes. [ABSTRACT FROM PUBLISHER]

With different principles, support vector machines (SVMs) and multiple classifier systems (MCSs) have shown excellent performances for classifying hyperspectral remote sensing images. In order to further improve the performance, we propose a novel ensemble approach, namely, rotation-based SVM (RoSVM), which combines SVMs and MCSs together. The basic idea of RoSVM is to generate diverse SVM classification results using random feature selection and data transformation, which can enhance both individual accuracy and diversity within the ensemble simultaneously. Two simple data transformation methods, i.e., principal component analysis and random projection, are introduced into RoSVM. An empirical study on three hyperspectral data sets demonstrates that the proposed RoSVM ensemble method outperforms the single SVM and random subspace SVM. The impacts of the parameters on the overall accuracy of RoSVM (different training sets, ensemble sizes, and numbers of features in the subset) are also investigated in this paper. [ABSTRACT FROM PUBLISHER]

An accurate algorithm for lithium polymer battery state-of-charge (SOC) estimation is proposed based on adaptive unscented Kalman filters (AUKF) and least-square support vector machines (LSSVM). A novel approach using the moving window method is applied, with AUKF and LSSVM to accurately establish the battery model with limited initial training samples. The effectiveness of the moving window modeling method is validated by both simulations and lithium polymer battery experimental results. The measurement equation of the proposed AUKF method is established by the LSSVM battery model and AUKF has the advantage of adaptively adjusting noise covariance during the estimation process. In addition, the developed LSSVM model is continuously updated online with new samples during the battery operation, in order to minimize the influence of the changes in battery internal characteristics on modeling accuracy and estimation results after a period of operation. Finally, a comparison of accuracy and performance between the AUKF and UKF is made. Simulation and experiment results indicate that the proposed algorithm is capable of predicting lithium battery SOC with a limited number of initial training samples. [ABSTRACT FROM PUBLISHER]

Time series classification (TSC) arises in many fields and has a wide range of applications. Here, we adopt the bag-of-words (BoW) framework to classify time series. Our algorithm first samples local subsequences from time series at feature-point locations when available. It then builds local descriptors, and models their distribution by Gaussian mixture models (GMM), and at last it computes a Fisher Vector (FV) to encode each time series. The encoded FV representations of time series are readily used by existing classifiers, e.g., SVM, for training and prediction. In our work, we focus on detecting better feature points and crafting better local representations, while using existing techniques to learn codebook and encode time series. Specifically, we develop an efficient and effective peak and valley detection algorithm from real-case time series data. Subsequences are sampled from these peaks and valleys, instead of sampled randomly or uniformly as was done previously. Then, two local descriptors, Histogram of Oriented Gradients (HOG-1D) and Dynamic time warping-Multidimensional scaling (DTW-MDS), are designed to represent sampled subsequences. Both descriptors complement each other, and their fused representation is shown to be more descriptive than individual ones. We test our approach extensively on 43 UCR time series datasets, and obtain significantly improved classification accuracies over existing approaches, including NNDTW and shapelet transform. [ABSTRACT FROM PUBLISHER]

The increasing use of touchscreen smartphones to access sensitive and privacy data has given rise to the need of secure and usable authentication technique. Smartphone users have their own unique behavioral characteristics when performing touch operations. These personal characteristics are reflected on different rhythm, strength, and angle preferences of touch-interaction behavior. This paper investigates the reliability and applicability on the usage of users’ touch-interaction behavior for active authentication on smartphones. For each common type of touch operations, both static and dynamic features are extracted and analyzed for fine-grained characterization of users’ touch behavior. Classification techniques (nearest neighbor, neural network, support vector machine, and random forest) are applied to the feature space for performing the task of active authentication. Analyses are conducted using data from around 134 900 touch operations of 71 participants in real-world scenarios, and the authentication performance is evaluated across various types of touch operations, varying operation lengths, different application tasks, and different application scenarios. The extensive experimental results are included to show that touch-interaction behavior exhibits sufficient discriminability and stability among smartphone users for active authentication, and achieves equal-error rates between 1.72% and 9.01% for different types of touch operations with the operation length of 11; the authentication accuracies improve when having long observation or small timespan between the training and testing phases, and express more reliably and stably in a specific task than in the free task. We also discuss a number of avenues for additional research that we believe are necessary to advance the state-of-the-art in this area. [ABSTRACT FROM PUBLISHER]

Wireless capsule endoscopy (WCE) enables noninvasive and painless direct visual inspection of a patient's whole digestive tract, but at the price of long time reviewing large amount of images by clinicians. Thus, an automatic computer-aided technique to reduce the burden of physicians is highly demanded. In this paper, we propose a novel color feature extraction method to discriminate the bleeding frames from the normal ones, with further localization of the bleeding regions. Our proposal is based on a twofold system. First, we make full use of the color information of WCE images and utilize K-means clustering method on the pixel represented images to obtain the cluster centers, with which we characterize WCE images as words-based color histograms. Then, we judge the status of a WCE frame by applying the support vector machine (SVM) and K-nearest neighbor methods. Comprehensive experimental results reveal that the best classification performance is obtained with YCbCr color space, cluster number 80 and the SVM. The achieved classification performance reaches 95.75% in accuracy, 0.9771 for AUC, validating that the proposed scheme provides an exciting performance for bleeding classification. Second, we propose a two-stage saliency map extraction method to highlight bleeding regions, where the first-stage saliency map is created by means of different color channels mixer and the second-stage saliency map is obtained from the visual contrast. Followed by an appropriate fusion strategy and threshold, we localize the bleeding areas. Quantitative as well as qualitative results show that our methods could differentiate the bleeding areas from neighborhoods correctly. [ABSTRACT FROM AUTHOR]

This paper proposes a novel contextual method for classification of polarimetric synthetic aperture radar data. The method combines support vector machine (SVM) and Wishart classifiers to benefit from both parametric and nonparametric methods. This method computes the energy function of a Markov random field (MRF) in the neighborhoods of the pixel using Wishart distribution. It then relates the Markovian energydifference function to the SVM classifier. Therefore, the salt-and-pepper effect on the classified map is reduced using a contextual classifier. Moreover, to achieve the full advantage of spatial information, texture features are added into the contextual classification. Texture features are extracted from SPAN images and are added to the SVM classifier. In this paper, two Radarsat-2 polarimetric images acquired in the leaf-off and leaf-on seasons are used from a forest area. Efficient multitemporal information is exploited using composite kernels in SVM. Comparison of the proposed algorithm with the Wishart, Wishart-MRF, SVM, and SVM with composite kernel classifiers shows a 21.72%, 16.17%, 11.29%, and 8.19% improvement in overall accuracy, respectively. Moreover, incorporating texture features into classification results significant increase in the average accuracy in forest species compared with the use of only polarimetric features. [ABSTRACT FROM PUBLISHER]

In order to enhance the performance of bearing defect classification, feature extraction and dimensionality reduction have become important. In order to extract the effective features, wavelet kernel local fisher discriminant analysis (WKLFDA) is first proposed; herein, a new wavelet kernel function is proposed to construct the kernel function of LFDA. In order to automatically select the parameters of WKLFDA, a particle swarm optimization (PSO) algorithm is employed, yielding a new PSO-WKLFDA. When compared with the other state-of-the-art methods, the proposed PSO-WKLFDA yields better performance. However, the use of a single global transformation of PSO-WKLFDA for the multiclass task does not provide excellent classification accuracy due to the fact that the projected data still significantly overlap with each other in the projected subspace. In order to enhance the performance of bearing defect classification, a novel method is then proposed by transforming the multiclass task into all possible binary classification tasks using a one-against-one (OAO) strategy. Then, individual PSO-WKLFDA (I-PSO-WKLFDA) is used for extracting effective features of each binary class. The extracted effective features of each binary class are input to a support vector machine (SVM) classifier. Finally, a decision fusion mechanism is employed to merge the classification results from each SVM classifier to identify the bearing condition. Simulation results using synthetic data and experimental results using different bearing fault types show that the proposed method is well suited and effective for bearing defect classification. [ABSTRACT FROM PUBLISHER]

A non-linear support vector machine (NLSVM) seizure classification SoC with 8-channel EEG data acquisition and storage for epileptic patients is presented. The proposed SoC is the first work in literature that integrates a feature extraction (FE) engine, patient specific hardware-efficient NLSVM classification engine, 96 KB SRAM for EEG data storage and low-noise, high dynamic range readout circuits. To achieve on-chip integration of the NLSVM classification engine with minimum area and energy consumption, the FE engine utilizes time division multiplexing (TDM)-BPF architecture. The implemented log-linear Gaussian basis function (LL-GBF) NLSVM classifier exploits the linearization to achieve energy consumption of 0.39 \mu J/operation and reduces the area by 28.2% compared to conventional GBF implementation. The readout circuits incorporate a chopper-stabilized DC servo loop to minimize the noise level elevation and achieve noise RTI of 0.81 \mu V{{rms}} for 0.5–100 Hz bandwidth with an NEF of 4.0. The 5\, \times \,5 mm^2 SoC is implemented in a 0.18 \mum 1P6M CMOS process consuming 1.83 \mu J/classification for 8-channel operation. SoC verification has been done with the Children's Hospital Boston-MIT EEG database, as well as with a specific rapid eye-blink pattern detection test, which results in an average detection rate, average false alarm rate and latency of 95.1%, 0.94% (0.27 false alarms/hour) and 2 s, respectively. [ABSTRACT FROM PUBLISHER]

A hybrid framework composed of two stages for gene selection and classification of DNA microarray data is proposed. At the first stage, five traditional statistical methods are combined for preliminary gene selection (Multiple Fusion Filter). Then, different relevant gene subsets are selected by using an embedded Genetic Algorithm (GA), Tabu Search (TS), and Support Vector Machine (SVM). A gene subset, consisting of the most relevant genes, is obtained from this process, by analyzing the frequency of each gene in the different gene subsets. Finally, the most frequent genes are evaluated by the embedded approach to obtain a final relevant small gene subset with high performance. The proposed method is tested in four DNA microarray datasets. From simulation study, it is observed that the proposed approach works better than other methods reported in the literature. [ABSTRACT FROM PUBLISHER]

Nowadays people spend a substantial amount of time waiting in different places such as supermarkets and amusement parks. Detecting the status of queuing may benefit both users and business. In this paper, we present QueueSense, a queuing recognition system to assist in a queue management system. QueueSense consists of clients on smartphones that provide automatic, energy-efficient, and accurate queuing recognition, and a server in the cloud that collects data, identifies multi-queue lines, and provides waiting time estimation. In order to be useful, QueueSense should be able to recognize queuing behavior in various queuing scenarios without greatly decreasing the battery life of mobile phones. We present features of queuing and build the classifier on smartphones to automatically recognize queue classifier without human input. We investigate the complicated nature of energy consumption for queue recognition on phones and design an effective algorithm to maximize energy savings while guaranteeing accuracy of queue recognition. We evaluate QueueSense performance using the data set from real world queuing scenarios collected over a three-month period. Empirical results show that QueueSense is adaptive to various queuing scenarios with both high recognition accuracy and energy efficiency. We further implemented a prototype of QueueSense, the first queue detection system using smartphones. We conducted real-world experiments in a dining hall and a supermarket near a university campus. Through implementation and evaluation, we demonstrate that QueueSense is capable of detecting waiting lines that occur in our daily lives. [ABSTRACT FROM PUBLISHER]

Automated seizure prediction has a potential in epilepsy monitoring, diagnosis, and rehabilitation. Electroencephalogram (EEG) is widely used for seizure detection and prediction. This paper proposes a new seizure prediction approach based on spatiotemporal relationship of EEG signals using phase correlation. This measures the relative change between current and reference vectors of EEG signals which can be used to identify preictal/ictal (before the actual seizure onset/ actual seizure period) and interictal (period between adjacent seizures) EEG signals to predict the seizure. The experiments show that the proposed method is less sensitive to artifacts and provides higher prediction accuracy (i.e., 91.95%) and lower number of false alarms compared to the state-of-the-art methods using intracranial EEG signals in different brain locations of 21 patients from a benchmark data set. [ABSTRACT FROM PUBLISHER]

As one of the key components of the smart grid, advanced metering infrastructure brings many potential advantages such as load management and demand response. However, computerizing the metering system also introduces numerous new vectors for energy theft. In this paper, we present a novel consumption pattern-based energy theft detector, which leverages the predictability property of customers’ normal and malicious consumption patterns. Using distribution transformer meters, areas with a high probability of energy theft are short listed, and by monitoring abnormalities in consumption patterns, suspicious customers are identified. Application of appropriate classification and clustering techniques, as well as concurrent use of transformer meters and anomaly detectors, make the algorithm robust against nonmalicious changes in usage pattern, and provide a high and adjustable performance with a low-sampling rate. Therefore, the proposed method does not invade customers’ privacy. Extensive experiments on a real dataset of 5000 customers show a high performance for the proposed method. [ABSTRACT FROM PUBLISHER]

Wafer defects, which are primarily defective chips on a wafer, are of the key challenges facing the semiconductor manufacturing companies, as they could increase the yield losses to hundreds of millions of dollars. Fortunately, these wafer defects leave unique patterns due to their spatial dependence across wafer maps. It is thus possible to identify and predict them in order to find the point of failure in the manufacturing process accurately. This paper introduces a novel simplified subspaced regression framework for the accurate and efficient identification of defect patterns in semiconductor wafer maps. It can achieve a test error comparable to or better than the state-of-the-art machine-learning (ML)-based methods, while maintaining a low computational cost when dealing with large-scale wafer data. The effectiveness and utility of the proposed approach has been demonstrated by our experiments on real wafer defect datasets, achieving detection accuracy of 99.884% and ${{{R}}^{2}}$ of 99.905%, which are far better than those of any existing methods reported in the literature. [ABSTRACT FROM PUBLISHER]

In this study, we used structural and evolutionary based features to represent the sequences of gram-positive and gram-negative subcellular localizations. To do this, we proposed a normalization method to construct a normalize Position Specific Scoring Matrix (PSSM) using the information from original PSSM. To investigate the effectiveness of the proposed method we compute feature vectors from normalize PSSM and by applying support vector machine (SVM) and naïve Bayes classifier, respectively, we compared achieved results with the previously reported results. We also computed features from original PSSM and normalized PSSM and compared their results. The archived results show enhancement in gram-positive and gram-negative subcellular localizations. Evaluating localization for each feature, our results indicate that employing SVM and concatenating features (amino acid composition feature, Dubchak feature (physicochemical-based features), normalized PSSM based auto-covariance feature and normalized PSSM based bigram feature) have higher accuracy while employing naïve Bayes classifier with normalized PSSM based auto-covariance feature proves to have high sensitivity for both benchmarks. Our reported results in terms of overall locative accuracy is 84.8% and overall absolute accuracy is 85.16% for gram-positive dataset; and, for gram-negative dataset, overall locative accuracy is 85.4% and overall absolute accuracy is 86.3%. [ABSTRACT FROM PUBLISHER]

Structural SVM is an extension of the support vector machine for the joint prediction of structured labels from multiple measurements. Following a large margin principle, the training of structural SVM ensures that the ground-truth labeling of each sample receives a score higher than that of any other labeling. However, no specific score ranking is imposed among the other labelings. In this letter, we extend the standard constraint set of structural SVM with constraints between “almost-correct” labelings and less desirable ones to obtain a partial-ranking structural SVM (PR-SSVM) approach. Experimental results on action segmentation and classification with two challenging datasets (the TUM Kitchen mocap dataset and the CMU-MMAC video dataset) show that the proposed method achieves better detection and false alarm rates and higher F1 scores than both the conventional structural SVM and a comparable unstructured predictor. The proposed method also achieves higher accuracy than the state of the art on these datasets in excess of 14 and 31 percentage points, respectively. [ABSTRACT FROM PUBLISHER]

We present a novel multistage learning system, called grouping estimation fusion (GEF), for human age estimation via facial images. The GEF consists of three stages: 1) age grouping; 2) age estimation within age groups; and 3) decision fusion for final age estimation. In the first stage, faces are classified into different groups, where each group has a different age range. In the second stage, three methods are adopted to extract global features from the whole face and local features from facial components (e.g., eyes, nose, and mouth). Each global or local feature is individually utilized for age estimation in each group. Thus, several decisions (i.e., estimation results) are derived. In the third stage, we obtain the final estimated age by fusing the diverse decisions from the second stage. To create diverse decisions for fusion, we investigate multiple age grouping systems in the first stage, where each system has a different number of groups and different age ranges. Thus, various decisions can be made from the second stage, and will be delivered to the third stage for fusion. Totally, six fusion schemes (i.e., intra-system fusion, inter-system fusion, intra-inter fusion, inter-intra fusion, maximum-diversity fusion, and composite fusion) are developed and compared. The performance of the GEF system is evaluated on the Face and Gesture Recognition Research Network and the MORPH-II databases, and it outperforms the existing state-of-the-art age estimation methods by a significant margin. That is, the mean absolute errors of age estimation are reduced from 4.48 to 2.81 years on FG-NET and 3.82 to 2.97 years on MORPH-II. [ABSTRACT FROM PUBLISHER]

The shape of a machined surface significantly impacts its functional performance and exhibits different spatial variation patterns that reflect process conditions. Classification of these surface patterns into interpretable classes can greatly facilitate manufacturing process fault detection and diagnosis. High-definition metrology (HDM) can generate high density data and detect small differences of workpiece surfaces, which exhibits better performance than traditional measurement methods in process diagnosis. In this paper, a novel adaptive support vector machine (SVM)-based workpiece surface classification system is developed based on HDM. A nonsubsampled contourlet transform is used to extract features before classification with its characteristics of multiscale, multidirection, and less dimension of feature vectors. An adaptive particle swam optimization (APSO) algorithm is developed to search the optimal parameters of penalty coefficient and kernel function of SVM and is helpful to escape from the local minimum by its strong ability of global search. A varied step-length pattern search algorithm is explored to optimize the global point in every iteration of the APSO algorithm by its good performance in local search. These two algorithms are combined with their relative merits to find the optimal parameters for building an adaptive SVM classifier. The results of case studies show that the proposed adaptive SVM-based classification system can achieve a relatively high classification accuracy in the field of workpiece surface classification. [ABSTRACT FROM PUBLISHER]

In this paper, a machine learning (ML) approach is presented that exploits accelerometers data to deal with gesture recognition (GR) problems. The proposed methodology aims at providing high accuracy classification for home automation systems, which are generally user independent, device independent, and device orientation independent, an heterogeneous scenario that has not been fully investigated in previous GR literature. The approach illustrated in this paper is composed of three main steps: event identification; feature extraction; and ML-based classification. The elements of the novelty of the proposed approach are 1) a preprocessing phase based on principal component analysis to increase the performance in real-world scenario conditions and 2) the development of parsimonious novel classification techniques based on sparse Bayesian learning. This methodology is tested on two datasets of four gesture classes (horizontal, vertical, circles, and eight-shaped movements) and on a further dataset with eight classes. In order to authentically describe a real-world home automation environment, the gesture movements are collected from more than 30 people who freely perform any gesture. It results in a dictionary of 12 and 20 different movements, respectively, in the case of the four-class and the eight-class databases. [ABSTRACT FROM AUTHOR]

This work deals with the problem of producing a fast and accurate data classification, learning it from a possibly small set of records that are already classified. The proposed approach is based on the framework of the so-called Logical Analysis of Data (LAD), but enriched with information obtained from statistical considerations on the data. A number of discrete optimization problems are solved in the different steps of the procedure, but their computational demand can be controlled. The accuracy of the proposed approach is compared to that of the standard LAD algorithm, of support vector machines and of label propagation algorithm on publicly available datasets of the UCI repository. Encouraging results are obtained and discussed. [ABSTRACT FROM AUTHOR]

Support vector machines (SVMs) have been applied to land cover classification, and a number of studies have demonstrated their ability to increase classification accuracy. The high correlation between the data set and SVM training model parameters indicates the high performance of the classification model. To improve the correlation, research has focused on the integration of SVMs and other algorithms for data set selection and SVM training model parameter estimation. This letter proposes a novel method, based on a particle filter (PF), of estimating SVM training model parameters according to an observation system. By treating the SVM training function as the observation system of the PF, the new method automatically updates the SVM training model parameters to values that are more appropriate for the data set and can provide a better classification model than can the original model, wherein the parameters are set by trial and error. Various experiments were conducted using Radarsat-2 synthetic aperture radar data from the 2011 Thailand flood. The proposed method provides superior performance and a more accurate analysis compared with the standard SVM. [ABSTRACT FROM PUBLISHER]

A concern in hyperspectral image classification is the high number of required training samples. When traditional classifiers are applied, feature reduction (FR) techniques are the most common approaches to deal with this problem. Subspace-based classifiers, which are developed based on high-dimensional space characteristics, are another way to handle the high dimension of hyperspectral images. In this letter, a novel subspace-based classification approach is proposed and compared with basic and improved subspace-based classifiers. The proposed classifier is also compared with traditional classifiers that are accompanied by an FR technique and the well-known support vector machine classifier. Experimental results prove the efficiency of the proposed method, especially when a limited number of training samples are available. Furthermore, the proposed method has a very high level of automation and simplicity, as it has no parameters to be set. [ABSTRACT FROM PUBLISHER]

Machine learning algorithms allow us to directly predict brain states based on functional magnetic resonance imaging (fMRI) data. In this study, we demonstrate the application of this framework to neuromarketing by predicting purchase decisions from spatio-temporal fMRI data. A sample of 24 subjects were shown product images and asked to make decisions of whether to buy them or not while undergoing fMRI scanning. Eight brain regions which were significantly activated during decision-making were identified using a general linear model. Time series were extracted from these regions and input into a recursive cluster elimination based support vector machine (RCE-SVM) for predicting purchase decisions. This method iteratively eliminates features which are unimportant until only the most discriminative features giving maximum accuracy are obtained. We were able to predict purchase decisions with 71% accuracy, which is higher than previously reported. In addition, we found that the most discriminative features were in signals from medial and superior frontal cortices. Therefore, this approach provides a reliable framework for using fMRI data to predict purchase-related decision-making as well as infer its neural correlates. [ABSTRACT FROM PUBLISHER]

Extreme learning machine (ELM) has recently attracted many researchers’ interest due to its very fast learning speed, good generalization ability, and ease of implementation. It provides a unified solution that can be used directly to solve regression, binary, and multiclass classification problems. In this paper, we propose a stacked ELMs (S-ELMs) that is specially designed for solving large and complex data problems. The S-ELMs divides a single large ELM network into multiple stacked small ELMs which are serially connected. The S-ELMs can approximate a very large ELM network with small memory requirement. To further improve the testing accuracy on big data problems, the ELM autoencoder can be implemented during each iteration of the S-ELMs algorithm. The simulation results show that the S-ELMs even with random hidden nodes can achieve similar testing accuracy to support vector machine (SVM) while having low memory requirements. With the help of ELM autoencoder, the S-ELMs can achieve much better testing accuracy than SVM and slightly better accuracy than deep belief network (DBN) with much faster training speed. [ABSTRACT FROM PUBLISHER]

Time series Landsat data have been used to track ecosystem disturbances using an algorithm such as the vegetation change tracker. However, efficiently identifying and separating types of disturbances (e.g., wildfires and harvests) still remain a technical challenge. In this letter, we tested the support vector machine algorithm in separating forest disturbance types, including wildfires, harvests, and other disturbance types (a generalized disturbance class, including insect disease outbreak, tornado, snow damage, and drought-induced mortality) in the Greater Yellowstone Ecosystem (GYE) using annual Landsat images from 1984 to 2010. The algorithm has been proven to be highly reliable, with overall accuracy about 87% for the study region. Average producer's and user's accuracy for wildfires and harvests were 85% and 90%, respectively. Based on the mapped forest disturbance type results, fire was the most dominant disturbance in GYE National Parks (NPs) from 1984 to 2010, affecting over 37% of the forested area in GYE NPs, whereas other disturbances such as insect and disease outbreaks were more frequent in national forests of the region during this time interval. With the free public access of the Landsat data and careful selection of training samples, this method can be useful in other ecosystems with similar disturbance dynamics as GYE. [ABSTRACT FROM PUBLISHER]

In this letter, a semisupervised block-sparse graph is proposed for discriminant analysis of hyperspectral imagery. To overcome the difficulty of not having enough training samples in the previously developed block-sparse graph approach, unlabeled samples are selected to participate in graph construction. Both sparse and collaborative representations are used for unlabeled sample selection. The experimental results demonstrate that the proposed semisupervised block-sparse graph can significantly outperform the supervised version with limited training samples. The sparse and collaborative representation-based selection methods perform comparably with the collaborative version requiring much lower computational cost. [ABSTRACT FROM PUBLISHER]

Semisupervised classification has become popular, since it can make use of a limited amount of prior knowledge in hyperspectral images. However, spectral internal-class variability adds a great challenge to the task. To address these issues, we propose a novel semisupervised spectral–spatial classification method based on affinity scoring (AS) (SCAS). Adapted from fuzzy logic, AS exploits spectral and spatial features with their fuzzy contributions to classification by weighing on three factors: local class consistency, spectral similarity, and prior knowledge. SCAS consists of three main steps: oversegmentation, semisupervised classification, and modification. The first step generates superpixels and uses them to maintain local class consistency. The second and third steps employ AS to classify the superpixels and refine the classified map, respectively. Experiments show that the proposed method can outperform some classic methods and state-of-the-art classifiers. [ABSTRACT FROM PUBLISHER]

In this letter, we explore the use of self-dual attribute profiles (SDAPs) for the classification of hyperspectral images. The hyperspectral data are reduced into a set of components by nonparametric weighted feature extraction (NWFE), and a morphological processing is then performed by the SDAPs separately on each of the extracted components. Since the spatial information extracted by SDAPs results in a high number of features, the NWFE is applied a second time in order to extract a fixed number of features, which are finally classified. The experiments are carried out on two hyperspectral images, and the support vector machines and random forest are used as classifiers. The effectiveness of SDAPs is assessed by comparing its results against those obtained by an approach based on extended APs. [ABSTRACT FROM PUBLISHER]

Earthen levees have a significant role in protecting large areas of inhabited and cultivated land in the United States from flooding. Failure of the levees can result in loss of life and property. Slough slides are among the problems which can lead to complete levee failure during a high water event. In this paper, we develop a method to detect such slides using X-band synthetic aperture radar (SAR) data. Our proposed methodology includes: 1) radiometric normalization of the TerraSAR image using high-resolution digital elevation map (DEM) data; 2) extraction of features including backscatter and texture features from the levee; 3) a feature selection method based on minimum redundancy maximum relevance (mRMR); and 4) training a support vector machine (SVM) classifier and testing on the area of interest. To validate the proposed methodology, ground-truth data are collected from slides and healthy areas of the levee. The study area is part of the levee system along the lower Mississippi River in the United States. The output classes are healthy and slide areas of the levee. The results show the average classification accuracies of approximately 0.92 and Cohen’s kappa measures of 0.85 for both healthy and slide pixels using ten optimal features selected by mRMR with a sigmoid SVM. A comparison of the SVM performance to the maximum likelihood (ML) and back propagation neural network (BPNN) shows that the average accuracy of the SVM is superior to that of the BPNN and ML classifiers. [ABSTRACT FROM PUBLISHER]

The focus of this paper is the development of a low-cost research platform for a surface electromyogram (EMG)-based prosthetic hand control to evaluate various pattern recognition techniques and to study the real-time implementation. This comprehensible research platform may enlighten the biomedical research in developing countries for analyzing and evaluating the surface EMG signals. Major challenges in this work were as follows: the design and development of an EMG signal conditioning module, a pattern recognition module, and a prosthetic hand at low cost. Besides, EMG pattern recognition techniques were evaluated for identifying six hand motions in offline with signals acquired from ten healthy subjects and two transradial amputees. Features calculated from EMG signals were grouped into six ensembles to apprehend the vitality of the ensemble in classifiers namely simple logistic regression (SLR), J48 algorithm for decision tree, logistic model tree, neural network, linear discriminant analysis, and support vector machine. The classification performance was also evaluated with the prolonged EMG data recorded on a day at every 1 h interval to study the robustness of the classifier. The results show the average classification accuracy, processing time and memory requirement of the SLR was found to be better and robust with time-domain features consisting of statistical as well as autoregression coefficients. The statistical analysis of variance test also showed that computation time and memory space required for SLR were significantly less compared to the other classifiers. The performance of the classifier was tested in online with transradial amputee for actuation of prosthetic hand for two intended motions with a TMS320F28335 controller. This proposed research platform for evaluation of EMG pattern recognition and real-time implementation has been achieved at a cost of 25 000 Indian rupee (INR). [ABSTRACT FROM PUBLISHER]

Proline residues are common source of kinetic complications during folding. The X-Pro peptide bond is the only peptide bond for which the stability of the cis and trans conformations is comparable. The cis-trans isomerization (CTI) of X-Pro peptide bonds is a widely recognized rate-limiting factor, which can not only induces additional slow phases in protein folding but also modifies the millisecond and sub-millisecond dynamics of the protein. An accurate computational prediction of proline CTI is of great importance for the understanding of protein folding, splicing, cell signaling, and transmembrane active transport in both the human body and animals. In our earlier work, we successfully developed a biophysically motivated proline CTI predictor utilizing a novel tree-based consensus model with a powerful metalearning technique and achieved 86.58 percent Q2 accuracy and 0.74 Mcc, which is a better result than the results (70-73 percent Q2 accuracies) reported in the literature on the well-referenced benchmark dataset. In this paper, we describe experiments with novel randomized subspace learning and bootstrap seeding techniques as an extension to our earlier work, the consensus models as well as entropy-based learning methods, to obtain better accuracy through a precise and robust learning scheme for proline CTI prediction. [ABSTRACT FROM PUBLISHER]

It is necessary while quite challenging to select features strongly relevant to a thematic class, i.e., class-specific features, from very high resolution (VHR) remote sensing images. To meet this challenge, a class-specific feature selection method based on sparse similar samples (CFS4) is proposed. Specifically, CFS4 incorporates the local geometrical structure and discriminative information of the data into a sparsity regularization problem. The experimental results on VHR satellite images well validate the effectiveness and practicability of the proposed method. [ABSTRACT FROM PUBLISHER]