基于人工神经网络的表面肌电信号分类器研究进展

doi:10.16180/j.cnki.issn1007-7820.2021.02.011

摘要/Abstract

摘要：

表面肌电信号是一种重要的生理电信号。基于表面肌电信号建立人体康复动作识别系统操作方便,对身体无侵入性,对运动无干扰,有广阔的应用前景。肢体康复动作识别系统很大程度上依赖于信号特征提取和分类器的使用。文中对近几年基于人工神经网络建立的表面肌电信号分类器,包括LVQ分类器、ELM分类器、WNN分类器、ANFIS分类器、Alex Net分类器和GRNN分类器进行了回顾和探讨。通过对各种分类器的回顾比较,发现现有的不足之处并针对分类器的未来研究方向和发展趋势进行了分析和展望,为今后相关方面的研究提供一定的参考依据。

关键词: 表面肌电信号, 模式识别, 信号处理, 分类算法, 人工神经网络, 分类器

Abstract:

The surface electromyography signal is an important physiological electrical signal. The human body rehabilitation motion recognition system based on the surface electromyography is easy to operate, hurtless to the body and no interference to motion, and has broad application prospects. The limb rehabilitation motion recognition system heavily relies on signal feature extraction and the use of classifiers. In this paper, the surface electromyography signal based on artificial neural network including LVQ classifier, ELM classifier, WNN classifier, ANFIS classifier, Alex Net classifier, and GRNN classifier are reviewed and discussed. After the review and comparison of various classifiers, some shortcomings are found and the future research directions and development trends of the classifiers are analyzed and prospected, which provides a reference for relevant research in the future.

Key words: surface electromyography, pattern recognition, signal processing, classification algorithm, artificial neural network, classifier

中图分类号:

TP18

周小波,邹任玲,卢旭华,王海滨,张俊翔. 基于人工神经网络的表面肌电信号分类器研究进展[J]. 电子科技, 2021, 34(2): 62-67.

ZHOU Xiaobo,ZOU Renling,LU Xuhua,WANG Haibin,ZHANG Junxiang. Research Progress of Surface Electromyography Signal Classifier Based on Artificial Neural Network[J]. Electronic Science and Technology, 2021, 34(2): 62-67.

图/表 10

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

参考文献 29

[1]	Park S, Chung W K, Kim K. Training-free Bayesian self-adaptive classification for SEMG pattern recognition including motion transition[J]. IEEE Transactions on Biomedical Engineering, 2020,67(6):1775-1786. doi: 10.1109/TBME.2019.2947089 pmid: 31613748
[2]	Harper R H R. The role of HCI in the age of AI[J]. International Journal of Human-Computer Interaction, 2019,35(15):1331-1344.
[3]	Liu L, Song Y M, Yang P, et al. Pattern recognition of artificial legs based on WPT and LVQ [C].Tianjin:Chinese Intelligent Automation Conference, 2017.
[4]	Russakovsky O, Deng J, Su H, et al. ImageNet large scale visual recognition challenge[J]. International Journal of Computer Vision, 2015,115(3):211-252.
[5]	Kohonen T. The “neural”phonetic typewriter [C].London: The Second European Seminar on Neural Computing: Commercial Prospects, 1988.
[6]	Qiu S, Gao L, Wang J. Classification and regression of ELM, LVQ and SVM for E-nose data of strawberry juice[J]. Journal of Food Engineering, 2015,144(7):77-85.
[7]	Liu L, Song Y, Yang P, et al. Pattern recognition of artificial legs based on WPT and LVQ[C].Tianjin:Chinese Intelligent Automation Conference(CIAC), 2017.
[8]	Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks[C]. Budapest:IEEE International Joint Conference on Neural Networks (IJCNN), 2004.
[9]	Anam K, Al-Jumaily A. Evaluation of extreme learning machine for classification of individual and combined finger movements using electromyography on amputees and non-amputees[J]. Neural Networks: the Official Journal of the International Neural Network Society, 2016,85(9):51-68.
[10]	Wang J H, Qi L, Wang X. Surface EMG signals based motion intent recognition using multilayer ELM [C].Changchun: Conference on LIDAR Imaging Detection and Target Recognition, 2017.
[11]	Kuo Y, Zhen Z. Real-time pattern recognition for hand gesture based on ANN and surface EMG[C].Chongqing:IEEE the Eighth Joint International Information Technology and Artificial Intelligence Conference (ITAIC), 2019.
[12]	Zhang Q, Benveniste A. Wavelet networks[J]. IEEE Transactions on Neural Networks, 1992,3(6):89-98.
[13]	Feng Y, Cui N B, Zhao L, et al. Comparison of ELM,GANN, WNN and empirical models for estimating reference evapotranspiration in humid region of Southwest China[J]. Journal of Hydrology, 2016,53(6):376-383.
[14]	Cheng R, Bai Y P. A novel approach to fuzzy wavelet neural network modeling and optimization[J]. International Journal of Electrical Power and Energy Systems, 2015,64(8):671-678.
[15]	Duan F, Dai L, Chang W, et al. SEMG-based identification of hand motion commands using wavelet neural network combined with discrete wavelet transform[J]. IEEE Transactions on Industrial Electronics, 2016,63(3):1923-1934.
[16]	Jang J S R. ANFIS:adaptive-network-based fuzzy inference system[J]. IEEE Transactions on Systems, Man and Cybernetics, 1993,23(3):665-685.
[17]	Suganthi L, Iniyan S, Samuel A A. Applications of fuzzy logic in renewable energy systems-A review[J]. Renewable and Sustainable Energy Reviews, 2015,48(9):585-607.
[18]	石绍应, 王小谟, 曹晨, 等. 规则数确定的自适应模糊分类器[J]. 西安电子科技大学学报, 2017,44(2):81-87.
	Shi Shaoying, Wang Xiaomo, Cao Chen, et al. Adaptive fuzzy classifier with a fixed number of fuzzy rules[J]. Journal of Xidian University, 2017,44(2):81-87.
[19]	Fariman H J, Ahmad S A, Marhaban M H, et al. Simple and computationally efficient movement classification approach for EMG-controlled prosthetic hand: ANFIS vs. Artificial Neural Network[J]. Intelligent Automation and Soft Computing, 2015,21(4):559-573. doi: 10.1080/10798587.2015.1008735
[20]	Caesarendra W, Tjahjowidodo T, Nico Y, et al. EMG finger movement classification based on ANFIS [C].Medan: International Conference on Mechanical, Electronics, Computer, and Industrial Technology, 2018.
[21]	Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks[J]. Communications of the Acm, 2017,60(6):84-90.
[22]	刘如意, 宋建锋, 权义宁. 一种自动的高分辨率遥感影像道路提取方法[J]. 西安电子科技大学学报, 2017,44(1):100-105.
	Liu Ruyi, Song Jianfeng, Quan Yining. Automatic road extraction method for high resolution remote sensing images[J]. Journal of Xidian University, 2017,44(1):100-105.
[23]	Han X B, Zhong Y F, Cao L Q, et al. Pre-Trained AlexNet architecture with pyramid pooling and supervision for high spatial resolution remote sensing image scene classification[J]. Remote Sens, 2017,9(8):1-22.
[24]	Akhundov R, Saxby D J, Edwards S, et al. Development of a deep neural network for automated electromyographic pattern classification[J]. Journal of Experimental Biology, 2019,222(5):1-5.
[25]	Xingqun Z, Fei W, Jianhui W, et al. Deep learning based gesture recognition and its application in interactive control of intelligent wheelchair [C].Shenyang:The Twelfth International Conference on Intelligent Robotics and Applications, 2019.
[26]	Specht D F. A general regression neural network[J]. IEEE Transactions on Neural Networks, 1991,2(6):568-576. pmid: 18282872
[27]	Noda K, Yamaguchi Y, Nakadai K, et al. Audio-visual speech recognition using deep learning[J]. Applied Intelligence, 2015,42(4):722-737. doi: 10.1007/s10489-014-0629-7
[28]	王文恺. 基于倒谱与频谱分析的模糊核估计算法[J]. 电子科技, 2019,32(2):4-8.
	Wang Wenkai. Blur kernel estimation algorithm based on cepstrum and spectrum analysis[J]. Electronic Science and Technology, 2019,32(2):4-8.
[29]	Yavuz E, Eyupoglu C. A cepstrum analysis-based classification method for hand movement surface EMG signals[J]. Medical and Biological Engineering and Computing, 2019,57(10):2179-2201. doi: 10.1007/s11517-019-02024-8 pmid: 31388900

分类器	动作部位	实验对象	平均准确率
LVQ	下肢	健康学生	96.00%
ELM	手指	健康成人	99.50%
ELM	手臂	健康成人	99.20%
WNN	手臂	健康成人	94.67%
WNN	手臂	截肢患者	85.17%
ANFIS	手臂	健康学生	88.90%
ANFIS	手指	健康学生	72.00%
AlexNet	下肢	数据集	99.55%
AlexNet	手指	健康学生	95.00%
GRNN	手指	健康学生	99.23%