A Performance Comparison of EMG Classification Methods for Hand and Finger Motion

2014 ◽  
Author(s):  
Sungtae Shin ◽  
Reza Langari ◽  
Reza Tafreshi
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Discriminant Analysis ◽  
Dimension Reduction ◽  
Time Domain ◽  
Classification Accuracy ◽  
Human Motion ◽  
Support Vector ◽  
Classification Methods ◽  
Data Set

For recognizing human motion intent, electromyogram (EMG) based pattern recognition approaches have been studied for many years. A number of methods for classifying EMG patterns have been introduced in the literature. On the purpose of selecting the best performing method for the practical application, this paper compares EMG pattern recognition methods in terms of motion type, feature extraction, dimension reduction, and classification algorithm. Also, for more usability of this research, hand and finger EMG motion data set which had been published online was used. Time-domain, empirical mode decomposition, discrete wavelet transform, and wavelet packet transform were adopted as the feature extraction. Three cases, such as no dimension reduction, principal component analysis (PCA), and linear discriminant analysis (LDA), were compared. Six classification algorithms were also compared: naïve Bayes, k-nearest neighbor, quadratic discriminant analysis, support vector machine, multi-layer perceptron, and extreme machine learning. The performance of each case was estimated by three perspectives: classification accuracy, train time, and test (prediction) time. From the experimental results, the time-domain feature set and LDA were required for the highest classification accuracy. Fast train time and test time are dependent on the classification methods.

scholarly journals Improvement of EMG Pattern Recognition Model Performance in Repeated Uses by Combining Feature Selection and Incremental Transfer Learning

2021 ◽  
Vol 15 ◽  
Author(s):  
Qi Li ◽  
Anyuan Zhang ◽  
Zhenlan Li ◽  
Yan Wu
Keyword(s):  
Pattern Recognition ◽  
Feature Selection ◽  
Classification Accuracy ◽  
Fine Tuning ◽  
Support Vector ◽  
Classification Methods ◽  
Data Set ◽  
Feature Vectors ◽  
Emg Pattern Recognition ◽  
Sequential Forward Search

Electromyography (EMG) pattern recognition is one of the widely used methods to control the rehabilitation robots and prostheses. However, the changes in the distribution of EMG data due to electrodes shifting results in classification decline, which hinders its clinical application in repeated uses. Adaptive learning can solve this problem but takes additional time. To address this, an efficient scheme is developed by comparing the performance of 12 combinations of three feature selection methods [no feature selection (NFS), sequential forward search (SFS), and particle swarm optimization (PSO)] and four classification methods [non-adaptive support vector machine (N-SVM), incremental SVM (I-SVM), SVM based on TrAdaBoost (T-SVM), and I-SVM based on TrAdaBoost (TI-SVM)] in the classification of EMG data of 12 subjects for 5 consecutive days. Our results showed that TI-SVM achieved the highest classification accuracy among the classification methods (p < 0.05). The SFS method achieved the same classification accuracy as that of the scheme trained with the feature vectors selected by the NFS method (p = 0.999) while achieving a lower training time than that of TI-SVM combined with the NFS method (p = 0.043). Although the PSO method outperformed the NFS and SFS methods by achieving reduced training and response times (p < 0.05), the PSO method achieved a considerably lower classification accuracy than that of the scheme trained with the feature vectors selected by the NFS (p = 0.001) or SFS (p = 0.001) method. Furthermore, TI-SVM combined with the SFS method outperformed the CNN method with fine-tuning in classification accuracy on a small data set (p = 0.001). The results indicate that TI-SVM combined with the SFS method is suitable for improving the performance of EMG pattern recognition in repeated uses.

scholarly journals Classification of standing and sitting phases based on in-socket piezoelectric sensors in a transfemoral amputee

2020 ◽  
Vol 0 (0) ◽  
Author(s):  
Tawfik Yahya ◽  
Nur Azah Hamzaid ◽  
Sadeeq Ali ◽  
Farahiyah Jasni ◽  
Hanie Nadia Shasmin
Keyword(s):  
Time Domain ◽  
Classification Accuracy ◽  
Sensory System ◽  
Metabolic Energy ◽  
Support Vector ◽  
Data Set ◽  
Transfemoral Amputee ◽  
Sit To Stand ◽  
Optimal Classifier ◽  
The Impact

AbstractA transfemoral prosthesis is required to assist amputees to perform the activity of daily living (ADL). The passive prosthesis has some drawbacks such as utilization of high metabolic energy. In contrast, the active prosthesis consumes less metabolic energy and offers better performance. However, the recent active prosthesis uses surface electromyography as its sensory system which has weak signals with microvolt-level intensity and requires a lot of computation to extract features. This paper focuses on recognizing different phases of sitting and standing of a transfemoral amputee using in-socket piezoelectric-based sensors. 15 piezoelectric film sensors were embedded in the inner socket wall adjacent to the most active regions of the agonist and antagonist knee extensor and flexor muscles, i. e. region with the highest level of muscle contractions of the quadriceps and hamstring. A male transfemoral amputee wore the instrumented socket and was instructed to perform several sitting and standing phases using an armless chair. Data was collected from the 15 embedded sensors and went through signal conditioning circuits. The overlapping analysis window technique was used to segment the data using different window lengths. Fifteen time-domain and frequency-domain features were extracted and new feature sets were obtained based on the feature performance. Eight of the common pattern recognition multiclass classifiers were evaluated and compared. Regression analysis was used to investigate the impact of the number of features and the window lengths on the classifiers’ accuracies, and Analysis of Variance (ANOVA) was used to test significant differences in the classifiers’ performances. The classification accuracy was calculated using k-fold cross-validation method, and 20% of the data set was held out for testing the optimal classifier. The results showed that the feature set (FS-5) consisting of the root mean square (RMS) and the number of peaks (NP) achieved the highest classification accuracy in five classifiers. Support vector machine (SVM) with cubic kernel proved to be the optimal classifier, and it achieved a classification accuracy of 98.33 % using the test data set. Obtaining high classification accuracy using only two time-domain features would significantly reduce the processing time of controlling a prosthesis and eliminate substantial delay. The proposed in-socket sensors used to detect sit-to-stand and stand-to-sit movements could be further integrated with an active knee joint actuation system to produce powered assistance during energy-demanding activities such as sit-to-stand and stair climbing. In future, the system could also be used to accurately predict the intended movement based on their residual limb’s muscle and mechanical behaviour as detected by the in-socket sensory system.

scholarly journals USING PIXEL-BASED AND OBJECT-BASED METHODS TO CLASSIFY URBAN HYPERSPECTRAL FEATURES

2016 ◽  
Vol 42 (3) ◽  
pp. 92-105 ◽  
Author(s):  
Ahmad Hadavand ◽  
Mehdi Mokhtarzadeh ◽  
Mohammad Javad Valadan Zoej ◽  
Saeid Homayouni ◽  
Mohammad Saadatseresht
Keyword(s):  
Image Analysis ◽  
Feature Extraction ◽  
Classification Accuracy ◽  
Support Vector ◽  
Classification Methods ◽  
Spectral Angle Mapper ◽  
Object Based Image Analysis ◽  
Analysis Methods ◽  
Object Based ◽  
Percent Improvement

Object-based image analysis methods have been developed recently. They have since become a very active research topic in the remote sensing community. This is mainly because the researchers have begun to study the spatial structures within the data. In contrast, pixel-based methods only use the spectral content of data. To evaluate the applicability of object-based image analysis methods for land-cover information extraction from hyperspectral data, a comprehensive comparative analysis was performed. In this study, six supervised classification methods were selected from pixel-based category, including the maximum likelihood (ML), fisher linear likelihood (FLL), support vector machine (SVM), binary encoding (BE), spectral angle mapper (SAM) and spectral information divergence (SID). The classifiers were conducted on several features extracted from original spectral bands in order to avoid the problem of the Hughes phenomenon, and obtain a sufficient number of training samples. Three supervised and four unsupervised feature extraction methods were used. Pixel based classification was conducted in the first step of the proposed algorithm. The effective feature number (EFN) was then obtained. Image objects were thereafter created using the fractal net evolution approach (FNEA), the segmentation method implemented in eCognition software. Several experiments have been carried out to find the best segmentation parameters. The classification accuracy of these objects was compared with the accuracy of the pixel-based methods. In these experiments, the Pavia University Campus hyperspectral dataset was used. This dataset was collected by the ROSIS sensor over an urban area in Italy. The results reveal that when using any combination of feature extraction and classification methods, the performance of object-based methods was better than pixel-based ones. Furthermore the statistical analysis of results shows that on average, there is almost an 8 percent improvement in classification accuracy when we use the object-based methods.

scholarly journals Comparison of Parametric and Non-parametric EEG Feature Extraction Methods in Detection of Pediatric Migraine without Aura

2018 ◽  
Author(s):  
S Kazemi ◽  
P Katibeh
Keyword(s):  
Support Vector Machine ◽  
Feature Extraction ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Extraction Methods ◽  
Dominant Frequency ◽  
Support Vector ◽  
Classification Methods ◽  
Linear Discriminant ◽  
Non Parametric

Background: Migraine headache without aura is the most common type of migraine especially among pediatric patients. It has always been a great challenge of migraine diagnosis using quantitative electroencephalography measurements through feature classification. It has been proven that different feature extraction and classification methods vary in terms of performance regarding detection and diagnostic accuracy. Previous work on the subject was controversial, hence a comparison of these methods seems necessary.Objectives: The aim of this research is to compare two parametric and non-parametric feature extraction methods and also two classification methods in order to obtain optimal combinations of diagnostic accuracy.Materials and Methods: Having recorded background EEG from 24 pediatric migraineurs and 19 control subjects, data was processed by Welch’s and Yule-Walker’s methods. Features were selected using genetic algorithm, and then given to a support vector machine and the linear discriminant analysis for the classification. Accuracy was calculated for all combinations having the dominant frequency and the correlated absolute power of each EEG wave band (theta, alpha, and beta) and for all wave bands combined.Results: The highest migraine detection accuracy of 93% was obtained utilizing Welch’s method for EEG feature extraction alongside support vector machine for a classifier. Besides, Yule-Walker autoregressive method showed better performance than Welch’s, when only power bands (and not the dominant frequency) were used as classification input.Conclusion: The superiority of Welch’s method over Yule-Walker’s and the support vector machine over linear discriminant analysis can be great help for further researches on computer aided EEG-based diagnosis of migraine

scholarly journals TWO LEVELS FUSION DECISION FOR MULTISPECTRAL IMAGE PATTERN RECOGNITION

2015 ◽  
Vol II-2/W2 ◽  
pp. 69-74
Author(s):  
H. Elmannai ◽  
M. A. Loghmari ◽  
M. S. Naceur
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Majority Vote ◽  
Source Separation ◽  
Curvelet Transform ◽  
Training Data ◽  
Gabor Wavelet ◽  
Support Vector ◽  
Data Set ◽  
Non Linear

Major goal of multispectral data analysis is land cover classification and related applications. The dimension drawback leads to a small ratio of the remote sensing training data compared to the number of features. Therefore robust methods should be associated to overcome the dimensionality curse. The presented work proposed a pattern recognition approach. Source separation, feature extraction and decisional fusion are the main stages to establish an automatic pattern recognizer. <br><br> The first stage is pre-processing and is based on non linear source separation. The mixing process is considered non linear with gaussians distributions. The second stage performs feature extraction for Gabor, Wavelet and Curvelet transform. Feature information presentation provides an efficient information description for machine vision projects. <br><br> The third stage is a decisional fusion performed in two steps. The first step assign the best feature to each source/pattern using the accuracy matrix obtained from the learning data set. The second step is a source majority vote. Classification is performed by Support Vector Machine. Experimentation results show that the proposed fusion method enhances the classification accuracy and provide powerful tool for pattern recognition.

A NOVEL IMAGE PROCESSING ALGORITHM TO AUTOMATICALLY EXTRACT AND CLASSIFY LIVER BEARING TUMORS USING PATTERN RECOGNITION AND FUZZY TRANSFORM

2021 ◽  
Author(s):  
Ghous Bakhsh Narejo ◽  
Ayesha Amir Siddiqi ◽  
Adnan Hashmi
Keyword(s):  
Pattern Recognition ◽  
Feature Extraction ◽  
Classification Accuracy ◽  
Morphological Processing ◽  
Disease Classification ◽  
Support Vector ◽  
Gray Level ◽  
Ct Image ◽  
Fuzzy Transformation ◽  
Occurrence Matrix

This study presents a novel liver disease classification method by applying pattern recognition technique to automatically segmented liver from the images of computed tomographic (CT) scans. The methodology comprises of disease classification by the extraction of textural features from focal liver region bearing tumors. Two types of liver textures are investigated in this study for classification accuracy judgement. First, original liver texture is considered for feature extraction. Second, liver is used for feature extraction. The CT image dataset comprises 308 liver samples with 193 samples of malignant tumor and 115 samples of benign tumor. The entire liver tissue bearing tumor is segmented from the CT image automatically in the pre-processing stage using fuzzy transformation function and morphological processing. Four sets of textural feature matrices are applied to the liver for feature extraction. Gray level co-occurrence matrix (GLCM), standard deviation gray level co-occurrence matrix (SDGLCM), seven-moment matrix (7MM) and seven-moment gray level co-occurrence matrix (7MGLCM) are the combinational feature matrices applied to classify the liver as malignant or benign using support vector machines (SVMs). The best classification accuracy is achieved for original liver texture by 7MGLCM, which is 97% with AUC[Formula: see text]0.99 for training dataset and 97.8% with AUC[Formula: see text]1 for test dataset.

scholarly journals Method of Analyzing and Managing Volleyball Action by Using Action Sensor of Mobile Device

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Xu Sun ◽  
Kai Zhao ◽  
Wei Jiang ◽  
Xinlong Jin
Keyword(s):  
Pattern Recognition ◽  
Support Vector Machine ◽  
Feature Extraction ◽  
Human Motion ◽  
Classification Algorithm ◽  
Support Vector ◽  
Motion Sensors ◽  
Support Vector Machine Algorithm ◽  
Motion Information ◽  
Motion Recognition

With the development of electronic technology and sensor technology, more and more intelligent electronic devices integrate micro inertial sensors, which makes the research of human action recognition based on action sensing data have great application value. Data-based action recognition is a new research direction in the field of pattern recognition, which is essentially a process of action data acquisition, feature extraction, feature extraction, and recognition, the process of classification and recognition. Inertial motion information includes acceleration and angular velocity information, which is ubiquitous in daily life. Compared with motion recognition based on visual information, it can more directly reflect the meaning of action. This study mainly discusses the method of analyzing and managing volleyball action by using the action sensor of mobile device. Based on the motion recognition algorithm of support vector machine, the motion recognition process of support vector machine is constructed. When the data terminal and gateway of volleyball players are not in the same LAN, the classification algorithm classifies the samples to be tested through the characteristic data, which directly affects the recognition results. In this paper, the support vector machine algorithm is selected as the data classification algorithm, and the calculation of the classification process is reduced by designing an appropriate kernel function. For multiclass problems, the hierarchical structure of directed acyclic graph is optimized to improve the recognition rate. We need to bind motion sensors to human joints. In order to realize real-time recognition of human motion, mobile devices need to add windows to the motion capture data, that is, divide the data into a small sequence of specified length, and provide more application scenarios for the device. This method of embedding motion sensors into devices to read motion information is widely used, which provides a convenient data acquisition method for human motion pattern recognition based on motion information. The multiclassification support vector machine algorithm is used to train the classification algorithm model with action data. When the signal strength of the sensor is 90 t and the speed is 2.0 m/s and 0.5 m/s, the detection accuracy of the adaptive threshold is 93% and 95%, respectively. The results show that the SVM method based on hybrid kernel function can greatly improve the recognition accuracy of volleyball stroke, and the recognition time is short.

scholarly journals Comparative Analysis of Texture Patterns on Mammograms for Classification

2021 ◽  
Vol 38 (2) ◽  
pp. 379-386
Author(s):  
Nagadevi Darapureddy ◽  
Nagaprakash Karatapu ◽  
Tirumala Krishna Battula
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Discriminant Analysis ◽  
Classification Accuracy ◽  
Texture Feature ◽  
Gradient Boosting ◽  
Support Vector ◽  
Texture Feature Extraction ◽  
Support Vector Classifier ◽  
Tree Classifier

Breast cancer is a cancerous tumor that arrives within the tissues of the breast. Women are mostly attacked than men. To detect early cancer medical specialists, suggest mammography for screening. Algorithms in Machine learning were executed on mammogram images to classify whether the tissues are deleterious or not. An analysis is done based on the texture feature extraction using different techniques like Frequency decoded local binary pattern (FDLBP), Local Bit-plane Decoded Pattern (LBDP), Local Diagonal Extrema Pattern (LDEP), Local Directional Order Pattern (LDOP), Local Wavelet Pattern (LWP). The features extracted are tested on 322 images from MIA’s database of three different classes. The algorithms in Machine learning like K-Nearest Neighbor classifier (KNN), Support vector classifier (SVC), Decision Tree classifier (DTC), Random Forest classifier (RFC), AdaBoost classifier (AC), Gradient Boosting classifier (GBC), Gaussian Naive Bayes classifier (GNB), Linear Discriminant Analysis classifier (LDA), Quadratic Discriminant Analysis classifier (QDA) were used to evaluate the accuracy of classification. This paper examines the comparison of accuracy using different texture features. KNN algorithm with LDEP for texture feature extraction gives classification accuracy of 64.61%, SVC with all the texture patterns mentioned gives classification accuracy of 63.07%, DTC with FDLBP, LBDP gives classification accuracy of 47.69, RFC with LBDP and AC with LDOP and GBC with FDLBP gives 61.53% classification accuracy, GNB and LDA with FDLBP gives 60% and 63.07% classification accuracy respectively, QDA with LBDP gives 64.61 classification accuracy. Of all the Algorithms support vector classifier gives good accuracy results with all the texture patterns mentioned.

Minimum Within-Class and Maximum Between-Class Scatter Support Vector Machine

2011 ◽  
Vol 58-60 ◽  
pp. 79-84
Author(s):  
Zhong Bao Liu ◽  
Shi Tong Wang
Keyword(s):  
Pattern Recognition ◽  
Support Vector Machine ◽  
Discriminant Analysis ◽  
Linear Discriminant Analysis ◽  
Classification Accuracy ◽  
Support Vector ◽  
Linear Discriminant

Classification is one of most important tasks in pattern recognition. Support vector machine (SVM) and its improved algorithms are quite important to classification. Although these approaches perform well in practice, they can’t take within-class and between-class scatter into consideration. Inspired from the Fisher’s discriminant ratio in linear discriminant analysis (LDA), a minimum within-class and maximum between-class scatter support vector machine (MMSVM) is proposed. MMSVM has the advantages of SVM and LDA and reflects distributions of classes, therefore, classification accuracy is improved in most cases. Experiments on many datasets verify the effectiveness of the proposed algorithm.

scholarly journals Acceleration Feature Extraction of Human Body Based on Wearable Devices

Energies ◽  
2021 ◽  
Vol 14 (4) ◽  
pp. 924
Author(s):  
Zhenzhen Huang ◽  
Qiang Niu ◽  
Ilsun You ◽  
Giovanni Pau
Keyword(s):  
Genetic Algorithm ◽  
Feature Extraction ◽  
Kalman Filter ◽  
Human Body ◽  
Wearable Devices ◽  
Human Motion ◽  
Data Set ◽  
Feature Extraction Method ◽  
Motion Data ◽  
Kalman Filter Algorithm

Wearable devices used for human body monitoring has broad applications in smart home, sports, security and other fields. Wearable devices provide an extremely convenient way to collect a large amount of human motion data. In this paper, the human body acceleration feature extraction method based on wearable devices is studied. Firstly, Butterworth filter is used to filter the data. Then, in order to ensure the extracted feature value more accurately, it is necessary to remove the abnormal data in the source. This paper combines Kalman filter algorithm with a genetic algorithm and use the genetic algorithm to code the parameters of the Kalman filter algorithm. We use Standard Deviation (SD), Interval of Peaks (IoP) and Difference between Adjacent Peaks and Troughs (DAPT) to analyze seven kinds of acceleration. At last, SisFall data set, which is a globally available data set for study and experiments, is used for experiments to verify the effectiveness of our method. Based on simulation results, we can conclude that our method can distinguish different activity clearly.

Sign in / Sign up

Export Citation Format

Share Document