EMG signal classification by extreme learning machine

This paper proposes a new classification method based on Dirichlet process mixtures(DPM) to investigate the classification of the four actions from the action surface EMG(ASEMG) signals. This method first builds a classification model of the data by using the multinomial logit model (MNL). Then a classifier is given by using the classification information of training data. For the features of ASEMG, we use a combined method of the empirical mode decomposition(EMD), Largest Lyapunov exponent and Linear discriminant analysis(LDA) dimension reduction. The highest average classification accuracy rates are over 90%. The results indicate that this classification method could be applied the classification of the ASEMG signals.KeywordsDirichlet process mixturethe action Surface EMG(ASEMG) signalempirical mode decomposition(EMD)Largest Lyapunov exponentLinear discriminant analysis(LDA)

The abundant movement information carried by the surface electromyography (sEMG) signal can comprehensively reflect the muscle movement patterns on the surface of the human body, and the characteristics of physiological signals involving movement information have promoted the vigorous development in the field of human-computer interaction in machine learning. This paper takes subtle gestures as the research objects, and proposes a subtle gestures recognition system that uses two-channel sEMG signal and utilizes Quadratic Discriminant Analysis (QDA) and Linear Discriminant Analysis (LDA) which are parameter estimation classifiers based on probability density. First, combining the raw sEMG signal and the envelope sEMG signal, the number of channels for sensors and corresponding position of the muscle groups are preferably selected. Then, we propose to use the Pearson correlation coefficient to optimize the four types of features extracted in the time domain, frequency domain, time-frequency domain and AR model parameters, which effectively ensures the uniqueness of each gesture and eliminates individual differences. Finally, this paper compares four classifiers of QDA, LDA, Support Vector Machine (SVM), and K-Nearest Neighbor (KNN), and explores the pattern recognition classifier suitable for subtle actions. The experiment collects 9 kinds of subtle gestures from 8 subjects. The results show that the system can use only two channels of sEMG signal to recognize 9 kinds of subtle gestures which include multi-finger clicking or pinching or holding objects, and the most suitable classifiers QDA and LDA have the average recognition rates of 95.79% and 95.01%, respectively.

Urban intelligence is an emerging concept which guides a series of infrastructure developments in modern smart cities. Human-computer interaction (HCI) is the interface between residents and the smart cities, it plays a key role in bridging the gap in applicating information technologies in modern cities. Hand gestures have been widely acknowledged as a promising HCI method, recognition human hand gestures using surface electromyogram (sEMG) is an important research topic in the application of sEMG. However, state-of-the-art signal processing technologies are not robust in feature extraction and pattern recognition with sEMG signals, several technical problems are still yet to be solved. For example, how to maintain the availability of myoelectric control in intermittent use, since pattern recognition qualities are greatly affected by time variability, but it is unavoidable during daily use. How to ensure the reliability and effectiveness of myoelectric control system also important in developing a good human-machine interface. In this paper, linear discriminant analysis (LDA) and extreme learning machine (ELM) are implemented in hand gesture recognition system, which is able to reduce the redundant information in sEMG signals and improve recognition efficiency and accuracy. The characteristic map slope (CMS) is extracted by using the feature re-extraction method because CMS can strengthen the relationship of features cross time domain and enhance the feasibility of cross-time identification. This study is focusing on optimizing the time differences in sEMG pattern recognition, the experimental results are beneficial to reducing the time differences in gesture recognition based on sEMG. The recognition framework proposed in this paper can enhance the generalization ability of HCI in the long term use and it also simplifies the data collection stage before training the device ready for daily use, which is of great significance to improve the time generalization performance of an HCI system.

Analysis of EMG signal has been an interested topic in recent years for classifying surface myoelectric signal patterns. Myoelectric control is an unconventional method to control the upper limb prostheses, human-assisting robots and rehabilitation devices. The aim of present work is to assess the time-domain features of EMG signal for myoelectric control of upper extremity prostheses by utilizing scatter plot. Classification accuracy is calculated using linear discriminant classifier for different combination of feature vectors using principal component analysis (PCA) and uncorrelated linear discriminant analysis (ULDA) feature reduction techniques. Results show that willison amplitude and waveform length are the best features for separating the distinct upper-limb motions.

Sleep Disordered Breathing describes a group of disorders characterized by abnormalities of respiratory pattern or the quantity of ventilation during sleep. Sleep Disordered Breathing causes disruptions in sleep, yielding waking somnolence, diminished neurocognitive performance, adverse cardiovascular outcomes, insulin resistance and other metabolic dysfunctions. Electroencephalography and Electromyography signal analysis enables neurologists and sleep specialists to diagnose and monitor Sleep Disordered Breathing events. This paper look into the prospect of identifying sleep disordered breathing events through the analysis of Electroencephalograph and Electromyography signals. EEG and EMG signals corresponding to 25 subjects with previously diagnosed with Sleep Disorder Breathing studied and analyzed. The detection of Sleep Disordered Breathing events were based on the study of power spectral analysis of EEG and EMG signals. The variations in the normalized power of various spectral bands of EEG signals are studied along with the variations in power of the corresponding EMG signals. This paper also discusses the probable causes of the aforementioned variations in the EEG and EMG signals.

Selection of suitable features plays a pivotal role in Electromyography pattern recognition (EMG-PR) based system designing. Time-domain features are widely used in EMG-PR based application and show improved proficiency in the development of rehabilitation robotics. Even though, the performance of existing features is not satisfactory. In this study, we proposed four novel time-domain features obtained by using first-order differentiation of original surface electromyogram (sEMG) signals feature. Here, sEMG signals were acquired from ten healthy volunteers with the help of myotrace400 device for six different arm movements. The data acquisition and pre-processing stage were carried out followed by the feature extraction process for better classification results. Four different classifiers namely, k-nearest neighbors (KNN), Linear discriminant analysis (LDA), Quadratic discriminant analysis (QDA) and Medium tree (MT) classifiers were utilized for the performance evaluation of proposed and conventional features. Experimental results demonstrate that proposed features extracted by using first-order differentiation of sEMG signals feature attained better classification accuracy with MT classifier as compared to the feature extracted from original sEMG signals with the conventional features. The accuracy of proposed feature based on first-order differentiation improved up to 6%. The results indicate that proposed features may be considered for developing the EMG-PR based system designing.

ObjectiveCardiovascular diseases generate the highest mortality in the globe population, mainly due to coronary artery disease (CAD) like arrhythmia, myocardial infarction and heart failure. Therefore, an early identification of CAD and diagnosis is essential. For this, we have proposed a new approach to detect the CAD patients using heart rate variability (HRV) signals. This approach is based on subspaces decomposition of HRV signals using multiscale wavelet packet (MSWP) transform and entropy features extracted from decomposed HRV signals. The detection performance was analyzed using Fisher ranking method, generalized discriminant analysis (GDA) and binary classifier as extreme learning machine (ELM). The ranking strategies designate rank to the available features extracted by entropy methods from decomposed heart rate variability (HRV) signals and organize them according to their clinical importance. The GDA diminishes the dimension of ranked features. In addition, it can enhance the classification accuracy by picking the best discerning of ranked features. The main advantage of ELM is that the hidden layer does not require tuning and it also has a fast rate of detection.MethodologyFor the detection of CAD patients, the HRV data of healthy normal sinus rhythm (NSR) and CAD patients were obtained from a standard database. Self recorded data as normal sinus rhythm (Self_NSR) of healthy subjects were also used in this work. Initially, the HRV time-series was decomposed to 4 levels using MSWP transform. Sixty two features were extracted from decomposed HRV signals by non-linear methods for HRV analysis, fuzzy entropy (FZE) and Kraskov nearest neighbour entropy (K-NNE). Out of sixty-two features, 31 entropy features were extracted by FZE and 31 entropy features were extracted by K-NNE method. These features were selected since every feature has a different physical premise and in this manner concentrates and uses HRV signals information in an assorted technique. Out of 62 features, top ten features were selected, ranked by a ranking method called as Fisher score. The top ten features were applied to the proposed model, GDA with Gaussian or RBF kernal + ELM having hidden node as sigmoid or multiquadric. The GDA method transforms top ten features to only one feature and ELM has been used for classification.ResultsNumerical experimentations were performed on the combination of datasets as NSR-CAD and Self_NSR- CAD subjects. The proposed approach has shown better performance using top ten ranked entropy features. The GDA with RBF kernel + ELM having hidden node as multiquadric method and GDA with Gaussian kernel + ELM having hidden node as sigmoid or multiquadric method achieved an approximate detection accuracy of 100% compared to ELM and linear discriminant analysis (LDA)+ELM for both datasets. The subspaces level-4 and level-3 decomposition of HRV signals by MSWP transform can be used for detection and analysis of CAD patients.

Malware forensics is a field in digital forensics that is dedicated to collecting evidence of a malware attack on a system. Malware is also executable code, but unlike regular executables, it is designed to perform unauthorized actions on victim computers. Being an executable, the malware also performs designated tasks through several processes that can leave its traces (digital footprints) throughout different components of the operating system, such as registries, file systems, DLL calls, API calls, memory usage, CPU utilization, network traffic, etc. Some of these traces can exist even after the removal of the malware and can be used as evidence to verify the occurrence of an attack. The proposed malware forensic analysis technique combines both the static and dynamic features of the malware to trace its evidence. This information is collected using the Cuckoo sandbox, which executes the malware sample files in a virtual environment to generate a JSON-formatted analysis report. The Python script is used to extract the non-volatile features from the JSON format analysis report. However, combining both features results in a very long and sparse feature vector, which negatively affects the classifier’s performance. Therefore, the principal component analysis (PCA) algorithm is adopted to reduce the dimensionality of the feature vectors. The generated reduced dimensionality feature vectors are used to train the extreme learning machine (ELM). The ELM can be trained in a fraction of the time compared to the support vector machine (SVM), while achieving similar accuracy. This makes it a favorable choice, especially for malware forensic analysis, where the classifier needs to train with a large amount of data and requires quick decision-making capabilities. The performance of the proposed techniques is evaluated using 90 malicious code samples containing 41 Trojans, 28 worms, and 21 bots. To demonstrate the superiority of the proposed algorithm, a comparison with some state-of-the-art classification methods, named Hidden Markov Model (HMM), Support Vector Machine (SVM), Artificial Neural Network (ANN), and ELM, was also performed. The comparison results show that the proposed technique achieves approximately 11% higher precision, 10% higher recall, and a 10.5% higher F-score than the competitors.

The objective of this work is to study the EMG signals based on hand motions for specified tasks, and different gripping conditions so as to identify patterns of EMG signals. This will allow therapists to identify weak muscles of patients with motor weakness, such as spinal cord injury (SCI) and post-stroke and concentrate on rehabilitation activities which can strengthen these specific muscles. At the same time, it is hoped that the analysis is able to provide useful data for objective and quantitative assessment towards control applications on the hand rehabilitation device, which is being developed. The analysis of the EMG signals for various hand muscles during functional motions and prehensile tasks has been carried out. The method to identify individual hand motions from EMG signals is described. The EMG signals associated to physical parameters are also illustrated in this paper. Finally, the preliminary works and future research are concluded.

The fields of EMG signal processing technology has been effective in the application of prosthetic control and clinical medicine or sport science. The main purpose of this study is to classify two aggressive action EMG signals which are taken from different people, according to their texture feature vectors. The physical action EMG set is derived from UCI database. The power spectral density (PSD) estimation of EMG signals is calculated by using AR Burg Method. The texture feature vectors of EMG signals are extracted by applying statistical methods to PSD maps of each signal. PSD based feature vectors are given to different type of k-NN classifier as inputs and the performance results of each system are compared. Finally, the best average performance is observed as 97.92 % in k=7, 9 and 10 neighbors structure of k-NN classifier.

The surface electromyographic (sEMG) signal is commonly utilized as principal input information to the controller of robotic systems, such as exoskeleton robots. It has been shown that sEMG signals could vary from subject to subject, and that gender is one of the factors influencing this variation. Thus, the goal of this study is to detect possible gender-related differences in the EMG activity of the two main ankle-flexor muscles (tibialis anterior, TA and gastrocnemius lateralis, GL) during gait at comfortable speed and cadence. The statistical analysis of surface EMG signals, performed in seven male (M-group) and seven female (F-group) age-matched adults, showed clear gender-related differences in the behavior of TA and GL. The estimation of the different activation modalities, indeed, permitted to detect that F-group choose a walking modality with a more elevated number of activations during gait cycle, compared to M-group. This suggests a propensity of females for a more complex recruitment of the muscles during gait. The novel information on gender-related differences provided here suggest considering a separate approach for males and females, in providing electromyographic signals as input information to the controller of exoskeleton robot.

Comparative analysis of SVM and Naive Bayes classifier for the SEMG signal classification

EEG signals analysis for epileptic seizures detection using polynomial transforms, linear discriminant analysis and support vector machines

Surface electromyogram (sEMG) signals have been used to control multifunctional prosthetic hands. Researchers usually focused on the use of several channels with sEMG signals to identify more hand motions without limiting the number of sEMG sensors. However, the residual muscles of an amputee are limited. Therefore, the point of a successful recognition system is to decrease the channels of sEMG signals to classify more hand motions. To achieve this goal, we proposed a hand motion recognition system, in which three channels of sEMG signals can classify nine hand motions. In this recognition system, the time domain features, root mean square ratio (RMSR) and autoregressive (AR) model, were selected to extract the features of the sEMG signals as compared with the time-frequency domain features. Furthermore, the linear discriminant analysis (LDA) was adopted as the classifier. Consequently, the average accuracy rate of the presented system was 91.46%. Therefore, the proposed algorithms in this paper can be reasonably feasible for prosthetic hands.

Atrophy is one of the most common consequences of muscle disorder. This could be a result of both myopathy and neuropathy. Muscle atrophy becomes more possible as people age. As a result of this disorder, the amount and size of muscle fibers decrease, therefore a person cannot produce high amount of force in his/her muscles, leading to difficulties in handling daily activities. The main purpose of this research is to find a way to predict this disorder. In this study the force classification was used for the atrophy disorder detection. The results show that different classifiers and features from the proposed ones, work for this purpose. To approach this goal, data were collected by recording surface EMG (sEMG) signals. Processing the recorded signals, best features with respect to more accuracy and less calculation complexity were selected and reported. After extracting the features from each patient with using different types of classifiers including LDA (Linear Discriminant Analysis), QDA (Quadratic Discriminant Analysis) and SVM (Support Vector Machine), the best approach to separate normal and atrophic people was investigated. It is found that unlike the proposed features such as MAV (Mean Absolute Value), SSC (Slope Sign Change) and WL (Waveform Length) in upper limb movement classification, three features WL, WAMP (Wilson Amplitude) (time domain features) and MNP (Mean Power) (frequency domain feature) show better performance for atrophy characterization. The results show that these features well predict the detection of biceps atrophy.