Feature Projection Methods Research Articles

A new hybrid feature reduction method by using MCMSTClustering algorithm with various feature projection methods: a case study on sleep disorder diagnosis

A new hybrid feature reduction method by using MCMSTClustering algorithm with various feature projection methods: a case study on sleep disorder diagnosis

User-Tailored Hand Gesture Recognition System for Wearable Prosthesis and Armband Based on Surface Electromyogram

Surface electromyogram (sEMG) based hand gesture recognition for prosthesis or armband is an important application of the human-machine interface. However, the measurement location of sensors greatly influences the hand gesture performance, especially with the inter-day or inter-subject validation protocols. Therefore, we acquired two-day hand gesture data of 41 subjects with a 256 (16×16) channel high-density sEMG electrode array. With the acquired data, we initially compared the support vector machine (SVM) and other four state-of-art classifiers under three validation protocols, i.e., intra-day, inter-day and inter-subject validation protocols. Then, we screened 14 feature optimization techniques, including 5 feature-projection methods and 9 feature-ranking approaches. To present the accuracy tendency with varying measure locations, we systematically explored the 10-hand gesture performance using data of 16 prosthesis measurement locations (PMLs) and 15 armband measurement locations (AMLs). As a result, the SVM classifier was suitable for the intra-day and inter-day validation protocols and the 2-dimensional convolutional neural network was selected for the inter-subject validation protocol. The mean accuracies of the hand gesture classification ranged from 95.68% to 99.12% (intra-day validation), from 68.41% to 88.02% (inter-day validation) and from 63.39% to 86.33% (inter-subject validation) for the prosthesis application. In addition, for the armband application, the mean accuracies ranged from 96.25% to 97.43% (intra-day validation), from 67.44% to 75.83% (inter-day validation) and from 65.53% to 75.40% (inter-subject validation). The accuracy is greatly correlated with the measurement location, which is highly associated with the neuromuscular structures of human bodies. In summary, our work can serve as a factor-screening tool for users customizing their systems according to their physical conditions and requirements.

Deep network compression based on partial least squares

Modern visual pattern recognition methods are based on convolutional networks since they are able to learn complex patterns directly from the data. However, convolutional networks are computationally expensive in terms of floating point operations (FLOPs), energy consumption and memory requirements, which hinder their deployment on low-power and resource-constrained systems. To address this problem, many works have proposed pruning strategies, which remove neurons (i.e., filters) in convolutional networks to reduce their computational cost. Despite achieving remarkable results, existing pruning approaches are ineffective since the accuracy of the network is degraded. This loss in accuracy is an effect of the criterion used to remove filters, as it may result in the removal of the filters with high influence to the classification ability of the network. Motivated by this, we propose an approach that eliminates filters based on the relationship of their outputs with the class label, on a low-dimensional space. This relationship is captured using Partial Least Squares (PLS), a discriminative feature projection method. Due to the nature of PLS, our method focuses on keeping discriminative filters. As a consequence, we are able to remove up to 60% of FLOPs while improving network accuracy. We show that our criterion is superior to existing pruning criteria, which include state-of-the-art feature selection techniques and handcrafted approaches. Compared to state-of-the-art pruning strategies, our method achieves the best tradeoff between drop/improvement in accuracy and FLOPs reduction.

Identification of discriminatory antibiotic resistance genes among environmental resistomes using extremely randomized tree algorithm

BackgroundThe interconnectivities of built and natural environments can serve as conduits for the proliferation and dissemination of antibiotic resistance genes (ARGs). Several studies have compared the broad spectrum of ARGs (i.e., “resistomes”) in various environmental compartments, but there is a need to identify unique ARG occurrence patterns (i.e., “discriminatory ARGs”), characteristic of each environment. Such an approach will help to identify factors influencing ARG proliferation, facilitate development of relative comparisons of the ARGs distinguishing various environments, and help pave the way towards ranking environments based on their likelihood of contributing to the spread of clinically relevant antibiotic resistance. Here we formulate and demonstrate an approach using an extremely randomized tree (ERT) algorithm combined with a Bayesian optimization technique to capture ARG variability in environmental samples and identify the discriminatory ARGs. The potential of ERT for identifying discriminatory ARGs was first evaluated using in silico metagenomic datasets (simulated metagenomic Illumina sequencing data) with known variability. The application of ERT was then demonstrated through analyses using publicly available and in-house metagenomic datasets associated with (1) different aquatic habitats (e.g., river, wastewater influent, hospital effluent, and dairy farm effluent) to compare resistomes between distinct environments and (2) different river samples (i.e., Amazon, Kalamas, and Cam Rivers) to compare resistome characteristics of similar environments.ResultsThe approach was found to readily identify discriminatory ARGs in the in silico datasets. Also, it was not found to be biased towards ARGs with high relative abundance, which is a common limitation of feature projection methods, and instead only captured those ARGs that elicited significant profiles. Analyses of publicly available metagenomic datasets further demonstrated that the ERT approach can effectively differentiate real-world environmental samples and identify discriminatory ARGs based on pre-defined categorizing schemes.ConclusionsHere a new methodology was formulated to characterize and compare variances in ARG profiles between metagenomic data sets derived from similar/dissimilar environments. Specifically, identification of discriminatory ARGs among samples representing various environments can be identified based on factors of interest. The methodology could prove to be a particularly useful tool for ARG surveillance and the assessment of the effectiveness of strategies for mitigating the spread of antibiotic resistance. The python package is hosted in the Git repository: https://github.com/gaarangoa/ExtrARG

Linear feature projection-based real-time decoding of limb state from dorsal root ganglion recordings.

Proprioceptive afferent activities recorded by a multichannel microelectrode have been used to decode limb movements to provide sensory feedback signals for closed-loop control in a functional electrical stimulation (FES) system. However, analyzing the high dimensionality of neural activity is one of the major challenges in real-time applications. This paper proposes a linear feature projection method for the real-time decoding of ankle and knee joint angles. Single-unit activity was extracted as a feature vector from proprioceptive afferent signals that were recorded from the L7 dorsal root ganglion during passive movements of ankle and knee joints. The dimensionality of this feature vector was then reduced using a linear feature projection composed of projection pursuit and negentropy maximization (PP/NEM). Finally, a time-delayed Kalman filter was used to estimate the ankle and knee joint angles. The PP/NEM approach had a better decoding performance than did other feature projection methods, and all processes were completed within the real-time constraints. These results suggested that the proposed method could be a useful decoding method to provide real-time feedback signals in closed-loop FES systems.

Linear Feature Projection-Based Sensory Event Detection from the Multiunit Activity of Dorsal Root Ganglion Recordings.

Afferent signals recorded from the dorsal root ganglion can be used to extract sensory information to provide feedback signals in a functional electrical stimulation (FES) system. The goal of this study was to propose an efficient feature projection method for detecting sensory events from multiunit activity-based feature vectors of tactile afferent activity. Tactile afferent signals were recorded from the L4 dorsal root ganglion using a multichannel microelectrode for three types of sensory events generated by mechanical stimulation on the rat hind paw. The multiunit spikes (MUSs) were extracted as multiunit activity-based feature vectors and projected using a linear feature projection method which consisted of projection pursuit and negentropy maximization (PP/NEM). Finally, a multilayer perceptron classifier was used to detect sensory events. The proposed method showed a detection accuracy superior to those of other linear and nonlinear feature projection methods and all processes were completed within real-time constraints. Results suggest that the proposed method could be useful to detect sensory events in real time. We have demonstrated the methodology for an efficient feature projection method to detect real-time sensory events from the multiunit activity of dorsal root ganglion recordings. The proposed method could be applied to provide real-time sensory feedback signals in closed-loop FES systems.

An Efficient Face Recognition using Feature Filter and Subspace Projection Method

Purpose : In this paper we proposed cascade feature filter and projection method for rapid human face recognition for the large-scale high-dimensional face database. Materials and Methods : The relevant features are selected from the large feature set using Fast Correlation-Based Filter method. After feature selection, project them into discriminant using Principal Component Analysis or Linear Discriminant Analysis. Their cascade method reduces the time-complexity without significant degradation of the performance. Results : In our experiments, the ORL database and the extended Yale face database b were used for evaluation. On the ORL database, the processing time was approximately 30-times faster than typical approach with recognition rate 94.22% and on the extended Yale face database b, the processing time was approximately 300-times faster than typical approach with recognition rate 98.74 %. Conclusion : The recognition rate and time-complexity of the proposed method is suitable for real-time face recognition system on the large-scale high-dimensional face database.

A cross-lingual similarity measure for detecting biomedical term translations.

Bilingual dictionaries for technical terms such as biomedical terms are an important resource for machine translation systems as well as for humans who would like to understand a concept described in a foreign language. Often a biomedical term is first proposed in English and later it is manually translated to other languages. Despite the fact that there are large monolingual lexicons of biomedical terms, only a fraction of those term lexicons are translated to other languages. Manually compiling large-scale bilingual dictionaries for technical domains is a challenging task because it is difficult to find a sufficiently large number of bilingual experts. We propose a cross-lingual similarity measure for detecting most similar translation candidates for a biomedical term specified in one language (source) from another language (target). Specifically, a biomedical term in a language is represented using two types of features: (a) intrinsic features that consist of character n-grams extracted from the term under consideration, and (b) extrinsic features that consist of unigrams and bigrams extracted from the contextual windows surrounding the term under consideration. We propose a cross-lingual similarity measure using each of those feature types. First, to reduce the dimensionality of the feature space in each language, we propose prototype vector projection (PVP)—a non-negative lower-dimensional vector projection method. Second, we propose a method to learn a mapping between the feature spaces in the source and target language using partial least squares regression (PLSR). The proposed method requires only a small number of training instances to learn a cross-lingual similarity measure. The proposed PVP method outperforms popular dimensionality reduction methods such as the singular value decomposition (SVD) and non-negative matrix factorization (NMF) in a nearest neighbor prediction task. Moreover, our experimental results covering several language pairs such as English–French, English–Spanish, English–Greek, and English–Japanese show that the proposed method outperforms several other feature projection methods in biomedical term translation prediction tasks.

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

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

Uncorrelated fuzzy neighborhood preserving analysis based feature projection for driver drowsiness recognition

Driver drowsiness is reported as one of the main causal factors in many traffic accidents as it progressively impairs the driver's awareness about external events. Drowsiness detection can be approached through monitoring physiological signals while driving to correlate drowsiness with the change in the corresponding patterns of the Electroencephalogram (EEG), Electrooculogram (EOG), and Electrocardiogram (ECG) signals. The main challenge in such an approach is to extract a set of features that can highly discriminate between the different drowsiness levels. This paper proposes a new Fuzzy Neighborhood Preserving Analysis (FNPA) feature projection method that is used to extract the discriminant information relevant to the loss of attention caused by drowsiness. Unlike existing methods, FNPA considers the fuzzy memberships of the input measurements into the different classes while constructing the graph Laplacian. Thus, it is able to identify both the discriminant and the geometrical structure of the input data while accounting for the overlapping nature of the drowsiness patterns. Furthermore, in order to address the singularity problem that occurs in many real world problems, the singular value decomposition (SVD), and later the QR-Decomposition, are utilized to extract a set of statistically uncorrelated features presenting the Uncorrelated FNPA (UFNPA). In the current preliminary study with datasets collected from 31 subjects only, while performing a driving simulation task, the proposed method is capable of accurately classifying the drowsiness levels using a small number of features with an average accuracy of ≈93%. On the other hand, the possibility of developing a subject-independent drowsiness recognition system is also investigated when the problem is converted into a binary classification task, as imposed by the number of drowsiness levels exhibited by the drivers, with accuracies ranging from 82%-to-84%.

Fast and Accurate Human Detection Using a Cascade of Boosted MS-LBP Features

In this letter, a new scheme for generating local binary patterns (LBP) is presented. This Modified Symmetric LBP (MS-LBP) feature takes advantage of LBP and gradient features. It is then applied into a boosted cascade framework for human detection. By combining MS-LBP with Haar-like feature into the boosted framework, the performances of heterogeneous features based detectors are evaluated for the best trade-off between accuracy and speed. Two feature training schemes, namely Single AdaBoost Training Scheme (SATS) and Dual AdaBoost Training Scheme (DATS) are proposed and compared. On the top of AdaBoost, two multidimensional feature projection methods are described. A comprehensive experiment is presented. Apart from obtaining higher detection accuracy, the detection speed based on DATS is 17 times faster than HOG method.

Application of Linear Discriminant Analysis in Dimensionality Reduction for Hand Motion Classification

The classification of upper-limb movements based on surface electromyography (EMG) signals is an important issue in the control of assistive devices and rehabilitation systems. Increasing the number of EMG channels and features in order to increase the number of control commands can yield a high dimensional feature vector. To cope with the accuracy and computation problems associated with high dimensionality, it is commonplace to apply a processing step that transforms the data to a space of significantly lower dimensions with only a limited loss of useful information. Linear discriminant analysis (LDA) has been successfully applied as an EMG feature projection method. Recently, a number of extended LDA-based algorithms have been proposed, which are more competitive in terms of both classification accuracy and computational costs/times with classical LDA. This paper presents the findings of a comparative study of classical LDA and five extended LDA methods. From a quantitative comparison based on seven multi-feature sets, three extended LDA-based algorithms, consisting of uncorrelated LDA, orthogonal LDA and orthogonal fuzzy neighborhood discriminant analysis, produce better class separability when compared with a baseline system (without feature projection), principle component analysis (PCA), and classical LDA. Based on a 7-dimension time domain and time-scale feature vectors, these methods achieved respectively 95.2% and 93.2% classification accuracy by using a linear discriminant classifier.

Orthogonal Fuzzy Neighborhood Discriminant Analysis for Multifunction Myoelectric Hand Control

Developing accurate and powerful electromyogram (EMG) driven prostheses controllers that can provide the amputees with effective control on their artificial limbs, has been the focus of a great deal of research in the past few years. One of the major challenges in such research is extracting an informative subset of features that can best discriminate between the different forearm movements. In this paper, a new dimensionality reduction method, referred to as orthogonal fuzzy neighborhood discriminant analysis (OFNDA), is proposed as a response to such a challenge. Unlike existing attempts in fuzzy linear discriminant analysis, the objective of the proposed OFNDA is to minimize the distance between samples that belong to the same class and maximize the distance between the centers of different classes, while taking into account the contribution of the samples to the different classes. The proposed OFNDA is validated on EMG datasets collected from seven subjects performing a range of 5 to 10 classes of forearm movements. Practical results indicate the significance of OFNDA in comparison to many other feature projection methods (including locality preserving and uncorrelated variants of discriminant analysis) with accuracies ranging from 97.66% to 87.84% for 5 to 10 classes of movements, respectively, using only two EMG electrodes.

Support Vector Machines with Manifold Learning and Probabilistic Space Projection for Tourist Expenditure Analysis

The significant economic contributions of the tourism industry in recent years impose an unprecedented force for data mining and machine learning methods to analyze tourism data. The intrinsic problems of raw data in tourism are largely related to the complexity, noise and nonlinearity in the data that may introduce many challenges for the existing data mining techniques such as rough sets and neural networks. In this paper, a novel method using SVM-based classification with two nonlinear feature projection techniques is proposed for tourism data analysis. The first feature projection method is based on ISOMAP (Isometric Feature Mapping), which is a class of manifold learning approaches for dimension reduction. By making use of ISOMAP, part of the noisy data can be identified and the classification accuracy of SVMs can be improved by appropriately discarding the noisy training data. The second feature projection method is a probabilistic space mapping technique for scale transformation. Experimental resul...

A Supervised Feature-Projection-Based Real-Time EMG Pattern Recognition for Multifunction Myoelectric Hand Control

Electromyographic (EMG) pattern recognition is essential for the control of a multifunction myoelectric hand. The main goal of this study was to develop an efficient feature- projection method for EMG pattern recognition. To this end, a linear supervised feature projection is proposed that utilizes a linear discriminant analysis (LDA). First, a wavelet packet transform (WPT) is performed to extract a feature vector from four-channel EMG signals. To dimensionally reduce and cluster the WPT features, an LDA, then, incorporates class information into the learning procedure, and identifies a linear matrix to maximize the class separability for the projected features. Finally, a multilayer perceptron classifies the LDA-reduced features into nine hand motions. To evaluate the performance of the LDA for WPT features, the LDA is compared with three other feature-projection methods. From a visualization and quantitative comparison, it is shown that the LDA produces a better performance for the class separability, plus the LDA-projected features improve the classification accuracy with a short processing time. A real-time pattern-recognition system is then implemented for a multifunction myoelectric hand. Experiments show that the proposed method achieves a 97.4% recognition accuracy, and all processes, including the generation of control commands for the myoelectric hand, are completed within 97 ms. Consequently, these results confirm that the proposed method is applicable to real-time EMG pattern recognition for multifunction myoelectric hand control.

실시간 근전도 패턴인식을 위한 특징투영 기법에 관한 연구

EMG pattern recognition is essential for the control of a multifunction myoelectric hand. The main goal of this study is to develop an efficient feature projection method for EMC pattern recognition. To this end, we propose a linear supervised feature projection that utilizes linear discriminant analysis (LDA). We first perform wavelet packet transform (WPT) to extract the feature vector from four channel EMC signals. For dimensionality reduction and clustering of the WPT features, the LDA incorporates class information into the learning procedure, and finds a linear matrix to maximize the class separability for the projected features. Finally, the multilayer perceptron classifies the LDA-reduced features into nine hand motions. To evaluate the performance of LDA for the WPT features, we compare LDA with three other feature projection methods. From a visualization and quantitative comparison, we show that LDA has better performance for the class separability, and the LDA-projected features improve the classification accuracy with a short processing time. We implemented a real-time pattern recognition system for a multifunction myoelectric hand. In experiment, we show that the proposed method achieves 97.2% recognition accuracy, and that all processes, including the generation of control commands for myoelectric hand, are completed within 97 msec. These results confirm that our method is applicable to real-time EMG pattern recognition far myoelectric hand control.