A novel feature extraction method for machine learning based on surface electromyography from healthy brain

被引:104
|
作者
Li, Gongfa [1 ,3 ,4 ]
Li, Jiahan [1 ]
Ju, Zhaojie [2 ]
Sun, Ying [1 ,5 ]
Kong, Jianyi [1 ,5 ]
机构
[1] Wuhan Univ Sci & Technol, Key Lab Met Equipment & Control Technol, Minist Educ, Wuhan 430080, Hubei, Peoples R China
[2] Univ Portsmouth, Sch Comp, Portsmouth PO1 3HE, Hants, England
[3] Wuhan Univ Sci & Technol, Res Ctr Biomimet Robot & Intelligent Measurement, Wuhan 430081, Hubei, Peoples R China
[4] Wuhan Univ Sci & Technol, Inst Precis Mfg, Wuhan 430081, Hubei, Peoples R China
[5] Wuhan Univ Sci & Technol, Hubei Key Lab Mech Transmiss & Mfg Engn, Wuhan 430080, Hubei, Peoples R China
来源
NEURAL COMPUTING & APPLICATIONS | 2019年 / 31卷 / 12期
基金
中国国家自然科学基金;
关键词
sEMG; New feature; Active muscle regions; Machine learning; MYOELECTRIC CONTROL; CLASSIFICATION; EMG; PROSTHESES; SIGNAL; STRATEGY;
D O I
10.1007/s00521-019-04147-3
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Feature extraction is one of most important steps in the control of multifunctional prosthesis based on surface electromyography (sEMG) pattern recognition. In this paper, a new sEMG feature extraction method based on muscle active region is proposed. This paper designs an experiment to classify four hand motions using different features. This experiment is used to prove that new features have better classification performance. The experimental results show that the new feature, active muscle regions (AMR), has better classification performance than other traditional features, mean absolute value (MAV), waveform length (WL), zero crossing (ZC) and slope sign changes (SSC). The average classification errors of AMR, MAV, WL, ZC and SSC are 13%, 19%, 26%, 24% and 22%, respectively. The new EMG features are based on the mapping relationship between hand movements and forearm active muscle regions. This mapping relationship has been confirmed in medicine. We obtain the active muscle regions data from the original EMG signal by the new feature extraction algorithm. The results obtained from this algorithm can well represent hand motions. On the other hand, the new feature vector size is much smaller than other features. The new feature can narrow the computational cost. This proves that the AMR can improve sEMG pattern recognition accuracy rate.
引用
收藏
页码:9013 / 9022
页数:10
相关论文
共 50 条
  • [1] A novel feature extraction method for machine learning based on surface electromyography from healthy brain
    Gongfa Li
    Jiahan Li
    Zhaojie Ju
    Ying Sun
    Jianyi Kong
    Neural Computing and Applications, 2019, 31 : 9013 - 9022
  • [2] An Improved Feature Extraction Method for Surface Electromyography Based on Muscle Activity Regions
    Ma, Luyao
    Tao, Qing
    Chen, Qingzheng
    Zhao, Zirui
    IEEE ACCESS, 2023, 11 : 68410 - 68420
  • [3] A novel feature extraction method of eddy current testing for defect detection based on machine learning
    Yin, Liyuan
    Ye, Bo
    Zhang, Zhaolin
    Tao, Yang
    Xu, Hanyang
    Avila, Jorge R. Salas
    Yin, Wuliang
    NDT & E INTERNATIONAL, 2019, 107
  • [4] Electromyography based hand movement classification and feature extraction using machine learning algorithms
    Ekinci, Ekin
    Garip, Zeynep
    Serbest, Kasim
    JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, 2023, 26 (04):
  • [5] Surface Electromyography Feature Extraction Based on Wavelet Transform
    Mahdavi, Farzaneh Akhavan
    Ahmad, Siti Anom
    Marhaban, Mohd Hamiruce
    Akbarzadeh-T, Mohammad-R.
    INTERNATIONAL JOURNAL OF INTEGRATED ENGINEERING, 2012, 4 (03): : 1 - 7
  • [6] The Surface Crack Extraction Method Based on Machine Learning of Image and Quantitative Feature Information Acquisition Method
    Zhang, Fan
    Hu, Zhenqi
    Yang, Kun
    Fu, Yaokun
    Feng, Zewei
    Bai, Mingbo
    REMOTE SENSING, 2021, 13 (08)
  • [7] Surface Electromyography (sEMG) Feature Extraction based on Daubechies Wavelets
    Elamvazuthi, I.
    Ling, G. A.
    Nurhanim, K. A. R. Ku
    Vasant, P.
    Parasuraman, S.
    PROCEEDINGS OF THE 2013 IEEE 8TH CONFERENCE ON INDUSTRIAL ELECTRONICS AND APPLICATIONS (ICIEA), 2013, : 1492 - 1495
  • [8] Machine Learning and Stereoelectroencephalographic Feature Extraction for Brain Tissue Classification
    Lopes, Pedro Henrique Peres Morais
    Machado, Mariana Mulinari Pinheiro
    Voda, Alina
    Besancon, Gildas
    Kahane, Philippe
    David, Olivier
    IFAC PAPERSONLINE, 2021, 54 (15): : 340 - 345
  • [9] Automatic Feature Extraction and Selection For Machine Learning Based Intrusion Detection
    Liu, Jinjie
    Chung, Sun Sunnie
    2019 IEEE SMARTWORLD, UBIQUITOUS INTELLIGENCE & COMPUTING, ADVANCED & TRUSTED COMPUTING, SCALABLE COMPUTING & COMMUNICATIONS, CLOUD & BIG DATA COMPUTING, INTERNET OF PEOPLE AND SMART CITY INNOVATION (SMARTWORLD/SCALCOM/UIC/ATC/CBDCOM/IOP/SCI 2019), 2019, : 1400 - 1405
  • [10] A Novel and Efficient Feature Extraction Method for Deep Learning Based Continuous Estimation
    Ma, Chenfei
    Guo, Weiyu
    Zhang, Hang
    Samuel, Oluwarotimi Williams
    Ji, Xiaopeng
    Xu, Lisheng
    Li, Guanglin
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (04): : 7341 - 7348