基于多路sEMG时序分析的人体运动模式识别方法

佟丽娜; 侯增广; 彭亮; 王卫群; 陈翼雄; 谭民

doi:10.3724/SP.J.1004.2014.00810

基于多路sEMG时序分析的人体运动模式识别方法

doi: 10.3724/SP.J.1004.2014.00810

1.
中国科学院自动化研究所复杂系统与管理国家重点实验室, 北京 100190;
2.
中国矿业大学 (北京)机电与信息工程学院, 北京 100083

基金项目:

国家自然科学基金（61305140，61225017，61175076，61203342），国家国际科技合作专项（2011DFG13390）资助

详细信息

作者简介:
佟丽娜中国科学院自动化研究所复杂系统管理与控制国家重点实验室控制科学与工程专业博士后，中国矿业大学(北京) 机电与信息工程学院讲师. 2011 年取得中国科学技术大学控制科学与工程博士学位. 主要研究方向为机器人与人机交互. E-mail：lina.tong@ia.ac.cn

计量
- 文章访问数: 3242
- HTML全文浏览量: 111
- PDF下载量: 2066
- 被引次数: 0
出版历程
- 收稿日期: 2013-03-26
- 修回日期: 2013-11-05
- 刊出日期: 2014-05-20

Multi-channel sEMG Time Series Analysis Based Human Motion Recognition Method

1.
State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190;
2.
School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing 100083

Funds:

Supported by National Natural Science Foundation of China (61305140, 61225017, 61175076, 61203342) and the International S & T Cooperation Project of China (2011DFG13390)

摘要

摘要: 针对主动康复训练中人体运动识别问题，提出了一种基于多路表面肌电（Surface electro myo gram，sEMG）时序特征的人体运动模式识别方法.设计评估类周期sEMG信号波形相似度的方法来对多路sEMG信号进行特征选择；以二维科荷伦自组织竞争网络（Self-organizati on mappingnet，SOM）对多路信息进行编码；最后，建立描述各运动过程多路sEMG时序特征的隐马尔科夫模型（Hidden Markov model，HMM），基于最大似然估计法对多模型匹配进行综合判决获取识别结果.并在对下肢踏车、椭圆、步行运动模式的识别实验中，相对于经典线性及非线性算法，识别率由72.5%和88.33%提高到91.67%，验证了本文方法的有效性.
- 康复训练 /
- 表面肌电 /
- 人体运动意图识别 /
- 自组织神经网络 /
- 隐马尔科夫模型
Abstract: Towards human motion intention recognition during active rehabilitation, a multi-channel suface electromyogram (sEMG) time series based human motion pattern recognition method is proposed. An evaluation method for sEMG signal waveform similarity is designed to select the features, which are coded by a 2D Kohonen self-organization mapping net (SOM) net to get feature series. At last, hidden Markov models (HMM) are built to describe the multi-channel sEMG time series features during each motion process, and then get recognition results based on maximum likelihood estimation method for multi-model synthesis decision. This method showed a good performance on real time and accuracy in the experiment: the treadmill, elliptical and walk training modes are identified by an accuracy of 91.67%, while the classical linear and nonlinear methods showed accuracies of 72.5% and 88.33%.
- Rehabilitation /
- surface electromyogram (sEMG) /
- human motion intention recognition /
- self-organization mapping net (SOM) /
- hidden Markov model (HMM)

HTML全文

参考文献(32)

[1]	Chen R L, Balami J S, Esiri M M, Chen L K, Buchan A M. Ischemic stroke in the elderly: an overview of evidence. Nature Reviews Neurology, 2010, 6(5): 256-265
[2]	Donnan G A, Fisher M, Macleod M, Davis S M. Stroke. The Lancet, 2008, 371(9624): 1612-1623
[3]	Coffey E C, Cummings J L, Starkstein S, Robinson R. The American Psychiatric Press Textbook of Geriatric Neuropsychiatry (Second Edition). Washington D.C.: American Psychiatric Press, 2000.
[4]	Liepert J, Bauder H, Wolfgang H R, Miltner W H, Taub E, Weiller C. Treatment-induced cortical reorganization after stroke in humans. Stroke, 2000, 31: 1210-1216
[5]	Wang Xing-Yu, Jin Jing, Zhang Yu, Wang Bei. Brain control: human-computer integration control based on brain-computer interface. Acta Automatica Sinica, 2013, 39(3): 208-221(王行愚, 金晶, 张宇, 王蓓. 脑控: 基于脑——机接口的人机融合控制. 自动化学报, 2013, 39(3): 208-221)
[6]	Lotze M, Braun C, Birbaumer N, Anders S, Cohen L G. Motor learning elicited by voluntary drive. Brain, 2003, 126(4): 866-872
[7]	Rosati G, Gallina P, Masiero S. Design, implementation and clinical tests of a wire-based robot for neurorehabilitation. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2007, 15(4): 560-569
[8]	Weiss L, Silver J K, Weiss J. EASY EMG: A Guide to Performing Nerve Conduction Studies and Electromyography. Singapore: Elsevier Pte Ltd., 2007
[9]	Kamen G, Gabriel D. Essentials of Electromyography. USA: Human Kinetics Publishers, 2009
[10]	Frigo C, Crenna P. Multichannel SEMG in clinical gait analysis: a review and state-of-the-art. Clinical Biomechanics, 2009, 24(3): 236-245
[11]	Naik G R, Kumar D K, Jayadeva. Twin SVM for gesture classification using the surface electromyogram. IEEE Transactions on Information Technology in Biomedicine, 2010, 14(2): 301-308
[12]	Momen K, Krishnan S, Chau T. Electromyographic signals corresponding to user-selected intentional movements for multifunction prosthesis control. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2007, 15(4): 535-542
[13]	Khushaba R N, Kodagoda S, Takruri M, Dissanayake G. Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals. Expert Systems with Applications, 2012, 39(12): 10731-10738
[14]	Miljković N, Bijeli G, Garcia G A, Popovi M B. Independent component analysis of EMG for posture detection: sensitivity to variation of posture properties. In: Proceedings of the 19th International Conference on Telecommunications Forum Telfor. Belgrade: IEEE, 2011. 47-50
[15]	Li Yang, Tian Yan-Tao, Chen Wan-Zhong. Modeling and classifying of sEMG based on FFT blind identification. Acta Automatica Sinica, 2012, 38(1): 128-134(李阳, 田彦涛, 陈万忠. 基于FFT 盲辨识的肌电信号建模及模式识别. 自动化学报, 2012, 38(1): 128-134)
[16]	Clancy E A, Liu L K, Liu P, Moyer D V Z. Identification of constant-posture EMG-torque relationship about the elbow using nonlinear dynamic models. IEEE Transactions on Biomedical Engineering, 2012, 59(1): 205-212
[17]	Choi C, Kwon S, Park W, Lee H, Kim J. Real-time pinch force estimation by surface electromyography using an artificial neural network. Medical Engineering & Physics, 2010, 32: 429-436
[18]	Staudenmann D, Roeleveld K, Stegeman D F, Dieën van J H. Methodological aspects of SEMG recordings for force estimation——a tutorial and review. Journal of Electromyography and Kinesiology, 2010, 20(3): 375-387
[19]	Earp J E, Newton R U, Cormie P, Blazevich A J. Knee angle-specific EMG normalization: the use of polynomial based EMG-angle relationships. Journal of Electromyography and Kinesiology, 2013, 23(1): 238-244
[20]	Shrirao N A, Reddy N P, Kosuri D R. Neural network committees for finger joint angle estimation from surface EMG signals. Biomedical Eng Online, 2009, 8(2): 1-14
[21]	Zhang F, Li P F, Hou Z G, Lu Z, Chen Y X, Li Q L, Tan M. sEMG-based continuous estimation of joint angles of human legs by using BP neural network. Neurocomputing, 2012, 78(1): 139-148
[22]	Werner C, Bardeleben A, Mauritz K H, Kirker S, Hesse S. Treadmill training with partial body weight support and physiotherapy in stroke patients: a preliminary comparison. European Journal of Neurology, 2002, 9(6): 639-644
[23]	Eich H J, Mach H, Werner C, Hesse S. Aerobic treadmill plus bobath walking training improves walking in subacute stroke: a randomized controlled trial. Clinical Rehabilitation, 2004, 18(6): 640-651
[24]	Ryait H S, Arora A S, Agarwal R. Interpretations of Wrist/Grip operations from sEMG signals at different locations on arm. IEEE Transactions on Biomedical Circuits and Systems, 2010, 4(2): 101-111
[25]	Gao Shi-Lian. Lower Limb Atlas of Practical Anatomy (3rd Edition). Shanghai: Shanghai Century Publishing Co., Ltd., 2012 (高士濂. 实用解剖图谱·下肢分册(第3版). 上海: 上海世纪出版股份有限公司, 2012)
[26]	Wang Jian. Some advances in the research of sEMG signal analysis and its application. Sports Science, 2000, 20(4): 56-60(王健. sEMG信号分析及其应用研究进展. 体育科学, 2000, 20(4): 56-60)
[27]	Lv Jie, Cao Jin-Feng, Fang Lei, Fang Min, Yan Jun-Tao, Xu Shi-Xiong. A new approach to evaluate the similarity of approximate periodic signal and its application in uniform analysis of gun-rolling manipulation. Acta Shanghai University of Traditional Chinese Medicine, 2010, 24(6): 54-57(吕杰, 曹金凤, 方磊, 房敏, 严隽陶, 许世雄. 一种评价近似周期信号相似度的新方法及其对中医法均匀性的分析. 上海中医药大学学报, 2010, 24(6): 54-57)
[28]	Zeng Feng, Zhong Zhi-Chu, Yang Tong, Yao Shan. Scattered point cloud normal vector calculation based on SOM. Computer Engineering, 2012, 38(8): 287-290 (曾锋, 钟治初, 杨通, 姚山. 基于SOM的散乱点云法矢计算. 计算机工程, 2012, 38(8): 287-290)
[29]	Zheng Hui-Cheng, Shen Wei. A localized linear manifold self-organizing map. Acta Automatica Sinica, 2008, 34(10): 1298-1304(郑慧诚, 沈伟. 一种局部化的线性流形自组织映射. 自动化学报, 2008, 34(10): 1298-1304)
[30]	Rabiner L R. A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE, 1989, 77(2): 257-286
[31]	Gomez R, Toda T, Saruwatari H, Shikano K. Techniques in rapid unsupervised speaker adaptation based on HMM-sufficient statistics. Speech Communication, 2009, 51(1): 42-57
[32]	Englehart K, Hudgins B. A robust, real-time control scheme for multifunction myoelectric control. IEEE Transactions on Biomedical Engineering, 2003, 50(7): 848-854