42 5 Vol. 42 No Journal of Jiangxi Normal University Natural Science Sep semg

Size: px

Start display at page:

Download "42 5 Vol. 42 No Journal of Jiangxi Normal University Natural Science Sep semg"

芙褚
5 years ago
Views:

1 42 5 Vol 42 No Journal of Jiangxi Normal University Natural Science Sep semg surface electromyography semg semg BP back propagation 2 semg % BP TP A DOI /j cnki issn semg 8 semg semg % 9 semg semg 11 support vector machines hidden markov models 2 12% semg yuhailonglong@ hotmail com

2 5 semg % 2 semg semg 2 2 semg BP 12 V semg - 5 ~ + 5 V 50 BP 0 ~ + 5 V PCI 1 6 MHz Ag /AgCl 1 semg 3 11 ~ Hz BP i m E a = 1 E n n i E i = x 2 i + x 2 i x 2 i +m-1 /m i = 1 n ii T V 1 y i = x i E a T V { 1 2 semg 0 E a < T V LPC i 50 E i = semg L-1 y 2 i n n = 0 2 y i n L ii

514 2018 Z i = 1 2 L-1 n = 0 sgn y i n - sgn y i n - 1 sgn x = { - 1 x < 0 1 x 0 i = 1 2 n j = 1 2 l k = 1 2 m iii ω jk = ω jk + ηh j e k η H z = G 1 - p i = 1 a i z -i ω ij ω jk ω ij = ω ij + ηh j 1

3 Z i = 1 2 L-1 n = 0 sgn y i n - sgn y i n - 1 sgn x = { - 1 x < 0 1 x 0 i = 1 2 n j = 1 2 l k = 1 2 m iii ω jk = ω jk + ηh j e k η H z = G 1 - p i = 1 a i z -i ω ij ω jk ω ij = ω ij + ηh j 1 - H j x i m G ω jk e k k = j = 1 2 l b k = b k + e k k = 1 2 m BP 3 vii X n Y m ω ij ii ω jk BP k = 1 ω jk e k vi a b a j = a j + ηh j 1 - H j m 2 OK BP 2 2 min BP 4 BP i n = 26 l = 17 m = 6 ω ij ω jk a b ii H 4 6 H j = f n ω ij x i - a j j = 1 2 l 2 2 i = 1 f x = e -x iii O O k = l j = 1 k = 1 2 m iv O Y e e k = Y k - O k k = 1 2 m v e 1 0 V semg 1 1 BP H j ω jk - b k ~ 0 1 V ~ 0 7 V ~

4 5 semg a b c d e OK f LPC 2 5 BP ~ 6 OK LPC % 6 LPC 93 69% 95 50% LPC

5 a b c d e OK f 8 12 OK % % 5 1 Lambelet C Lyu M Woolley D et al The ewrist-a wearable wrist exoskeleton with semg-based force control for 95 02% stroke rehabilitation C Rehabilitation Robotics ICORR 2017 International Conference on IEEE Meng Qingyun Meng Qiaoling Yu Hongliu A survey on semg control strategies of wearable handexoskeleton for rehabilitation C Intelligent Robot Systems ACIRS nd Asia-Pacific Conference on IEEE Wu Jian Tian Zhongjun Sun Lu Real-time American sign language recognition using wrist-worn motion and surface 10 EMG sensors C Wearable and Implantable Body Sensor Networks BSN 2015 IEEE 12th International Conference on IEEE Kim J Kim E Park S et al Implementation of a sign lan- 3 guage primitive framework using EMG and motion sensors 2 C Consumer Electronics 2016 IEEE 5th Global Con-

6 5 semg 517 ference on IEEE Su Ruiliang Chen Xiang Cao Shuai et al Random forestbased recognition of isolated sign language subwords using data from accelerometers and surface electromyographicsensors J Sensors Sun Guanghao Yu Wenwei Development of an EMGbased human-machine interface on open-source linux platform for evaluating the motor skill acquisition process C The 17th International Conference on Biomedical Engineering Springer Singapore Huang Youjia Liu Honghai Performances of surface EMG and ultrasound signals in recognizing finger motion C Human System Interactions HSI th International Conference on IEEE Lu Zhiyuan Chen Xiang Li Qiang A hand gesture recognition framework and wearable gesture-based interaction prototype for mobile devices J IEEE Transactions on Human-Machine Systems Benatti S Milosevic B Casamassima F et al EMG-based hand gesture recognition with flexible analog front end C Biomedical Circuits and Systems Conference Bio- CAS 2014 IEEE IEEE Ju Zhaojie Liu Honghai Human hand motion analysis with multisensory information M Berlin Human Motion Sensing and Recognition Springer Berlin Heidelberg Rossi M Benatti S Farella E et al Hybrid EMG classifier based on HMM and SVM for hand gesture recognition in prosthetics C Industrial Technology ICIT 2015 IEEE International Conference on IEEE Palermo F Cognolato M Gijsberts A et al Repeatability of grasp recognition for robotic hand prosthesis control based on semg data C Rehabilitation Robotics ICORR 2017 International Conference on IEEE Raj R Sivanandan K S Comparative study on estimation of elbow kinematics based on EMG time domain parameters using neural network and ANFIS NARX model J Journal of Intelligent and Fuzzy Systems Reaz M B I Hussain M S Mohd-Yasin F Techniques of EMG signal analysis detection processing classification and applications J Biological Procedures Online Mahapatra S Mohanta D Mohanty P K et al Classification of EMG signals using ANFIS for the detection of neuromuscular disorders M Singapore Recent Developments in Intelligent Computing Communication and Devices Springer The Study of Hand Gesture Recognition Method Based on semg Signal YU Hailong 1 FAN Xueli 1 GONG Hailan 2 XIE Le School of Electrical Engineering and Mechano-Electronic Engineering Xuchang University Xuchang Henan China 2 Shanghai Information Technology College Shanghai China 3 Natinoal Digital Manufacturing Technology Center Shanghai Jiaotong University Shanghai China 4 School of Biomedical Engineering Shanghai Jiaotong University Shanghai China Abstract The research of gesture recognition based on semg is becoming a hot spot in recent years with the development of robotics In view of the complex relationship between semg and hand gestures and the difficulty of practical application a pattern recognition system based on BP back propagation neural network is proposed which can recognize six hand gestures by the semg of superficial digital muscle and flex muscle The signal envelope is extract by the first-order infinite impulse response digital low-pass filter And the energy eigenvalues are chosen to do endpoint detection short-time energy and zero crossing rates and 12 level linear prediction coefficient are adopted to do pattern recognition Finally a pattern recognition experiment has been done which recearchs the relationship between the semg and six different hand gestures and the accuracy is above 90% The result shows that the method proposed in this study can achieve a high recognition rate and has a practical application prospect Key words semg signal mode recognition BP neural network endpoint detection

[1] Liu Hongwei,2013, Study on Comprehensive Evaluation of Iron and Steel Enterprises Production System s Basic Capacities, International Asia Confere

[1] Liu Hongwei,2013, Study on Comprehensive Evaluation of Iron and Steel Enterprises Production System s Basic Capacities, International Asia Confere 刘洪伟工业工程系副教授 CV 下载办公电话 : 电子邮箱 :hw_liu999@tju.edu.cn 研究方向 : 精益生产与精益管理理论及应用 ; 工业工程与信息技术集成管理 ; 系统可靠性理论与方法 ; 医院管理理论及应用教育与工作经历时间单位专