|
|
Force-sEMG relations recognition models of forearm exoskeleton for bilateral training |
YANG Zhong-liang1, TANG Zhi-chuan2, CHEN Yu-miao3, GAO Zeng-gui2 |
1. College of Mechanical Engineering, Donghua University, Shanghai 201620, China; 2. Modern Industrial Design Institute, Zhejiang University, Hangzhou 310027, China; 3. Fashion·Art Design Institute, Donghua University, Shanghai 200051, China |
|
|
Abstract To accurately recognize muscle forces of the non-paretic limb movement in forearm exoskeleton system, and drive the paretic limb for bilateral training in stroke, the force and surface electromyography (sEMG) relations recognition models of voluntary muscle contraction were proposed. The sEMG signals and strength values were recorded from 4 participants under 4 levels of forearm grasp forces by experiments. Using one-way ANOVA and multiple comparisons test, 11 features of sEMG time domain indices with significant differences were extracted from homogeneous subsets. The force-sEMG relations classification model and the myodynamia prediction model were constructed based on Elman network. For comparison, another prediction models using support vector machine (SVM) and gene expression programming (GEP) were presented here. Experimental results show that the Elman model can successfully recognize 4 levels of grasp forces, gives better results on modeling efficiency than the GEP model, and gives better generalization performance on myodynamia predicting than the SVM model. A forearm exoskeleton was developed to demonstrate the viability of the present modeling methods in the control of bilateral training.
|
Published: 01 December 2014
|
|
面向双侧训练的前臂外骨骼肌肉力-电关系识别模型
为了使前臂外骨骼系统能准确识别健肢运动的肌力水平,并带动患肢进行双侧训练,提出基于表面肌电的肌肉自主收缩力-电关系识别模型.通过4名被试者,实验采集前臂4种抓握力度下的肌电信号和握力值.利用单因素方差分析与多重比较产生的同类子集,提取11个具有显著性差异的肌电时域指标作为特征值.采用Elman神经网络构建力-电关系分类模型和肌力预测模型,并与基于支持向量机和基因表达式编程的预测模型进行性能比较.实验结果表明:Elman模型能够成功识别4种不同握力水平,建模效率高于基因表达式编程模型,肌力预测的泛化性能优于支持向量机模型.开发一个前臂外骨骼,在双侧训练的控制中验证了方法的有效性.
|
|
[1] FRISOLI A, PROCOPIO C, CHISARI C, et al. Positive effects of robotic exoskeleton training of upper limb reaching movements after stroke[J]. Journal of Neuroengineering and Rehabilitation, 2012, 9(1): 36.
[2] KREBS H I, VOLPE B T, AISEN M L, et al. Increasing productivity and quality of care: robot-aided neuro-rehabilitation[J]. Journal of Rehabilitation Research and Development, 2000, 37(6): 639-652.
[3] LOUREIRO R, AMIRABDOLLAHIAN F, TOPPING M, et al. Upper limb robot mediated stroke therapy-GENTLE/s approach[J]. Autonomous Robots, 2003, 15(1): 35-51.
[4] YUBO Z, ZIXI W, LINHONG J, et al. The clinical application of the upper extremity compound movements rehabilitation training robot[C]∥9th International Conference on Rehabilitation Robotics.[S.l]: IEEE, 2005: 91-94.
[5] 张勤超. 手部功能康复机器人机械系统的设计与研究[D]. 哈尔滨: 哈尔滨工业大学, 2011.
ZHANG Qin-chao. Design and research of the mechanical system for a hand rehabilitation robot[D]. Harbin: Harbin Institute of Technology, 2011.
[6] 徐宝国,彭思,宋爱国.基于运动想象脑电的上肢康复机器人[J].机器人,2011, 33(3): 307-313.
XU Bao-guo, PENG Si, SONG Ai-guo. Upper-limb rehabilitation robot based on motor imagery EEG[J]. Robot, 2011, 33(3): 307-313.
[7] 吴军.上肢康复机器人及相关控制问题研究[D].武汉: 华中科技大学, 2012.
WU Jun. The research on upper limb rehabilitation robot and related control problem[D]. Wuhan: Huazhong University of Science and Technology, 2012.
[8] 王生泽,金韬.一种气动驱动新型上肢康复机器人[J].机械设计与制造, 2011(3): 165-167.
WANG Sheng-ze, JIN Tao. A Novel upper limb rehabilitation robot by pneumatic actuators[J]. Machinery Design & Manufacture, 2011(3): 165-167.
[9] 吴銮.基于FPA的手指康复器研究[D].杭州: 浙江工业大学, 2012.
WU Luan. Research on finger rehabilitation device based on flexible pneumatic actuator FPA[D]. Hangzhou: Zhejiang University of Technology, 2012.
[10] CAURAUGH J H, LODHA N, NAIK S K, et al. Bilateral movement training and stroke motor recovery progress: a structured review and meta-analysis[J]. Human Movement Science, 2010, 29(5): 853-870.
[11] 许纲.偏瘫后上肢及手的双侧训练[J].中华物理医学与康复杂志, 2007,29(4): 275-279.
XU Gang. upper limb and hand bilateral training after hemiplegia[J]. Chinese Journal of Physical Medicine and Rehabilitation, 2007,29(4): 275-279.
[12] LUM P S, BURGAR C G, VAN DER LOOS M, et al. The MIME robotic system for upper-limb neuro-rehabilitation: Results from a clinical trial in subacute stroke[C]∥9th International Conference on Rehabilitation Robotics. [S.l]: IEEE, 2005: 511-514.
[13] FRISOLI A, LOCONSOLE C, LEONARDIS D, et al. A new gaze-BCI-Driven control of an upper limb exoskeleton for rehabilitation in real-world tasks[J]. IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews, 2012, 42(6): 1169-1179.
[14] LI C, INOUE Y, LIU T, et al. A new master-slave control method for implementing force sensing and energy recycling in a bilateral arm training robot[J]. International Journal of Innovative Computing, Information and Control, 2011, 7(1): 471-485.
[15] ROSEN J, PERRY J C. Upper limb powered exoskeleton[J]. International Journal of Humanoid Robotics, 2007, 4(03): 529-548.
[16] 王健.sEMG信号分析及其应用研究进展[J].体育科学, 2000, 20(4): 56-60.
WANG Jian. Some advances in the research of sEMG signal analysis and its application[J]. Sport Science, 2000, 20(4): 56-60.
[17] 张旭.基于表面肌电信号的人体动作识别与交互[D].合肥:中国科学技术大学, 2010.
XU Zhang. Body gesture recognition and interaction based on surface electromyogram[D]. Hefei: Universify of Seience and Teehnology of China, 2010.
[18] LOCONSOLE C, LEONARDIS D, BARSOTTI M, et al. An emg-based robotic hand exoskeleton for bilateral training of grasp[C]∥World Haptics Conference, 2013. \[S.l.\]: IEEE, 2013: 537-542.
[19] 杨钟亮.基于主客观联合测评的动态人机接触面工效学研究[D].杭州:浙江大学, 2012.
YANG Zhong-liang. Ergonomics study of dynamic human-product contact surface based on subjective and objective evaluation[D]. Hangzhou: Zhejiang University, 2012.
[20] 吴剑锋.基于肌电信号的人体下肢运动信息获取技术研究[D].杭州: 浙江大学, 2008.
WU Jian-feng. Researchon human lower-limb motion information acquisition technology based on EMG[D]. Hangzhou: Zhejiang University, 2008.
[21] 梅品高,罗志增.基于小波包分析和Elman网络的肌电信号处理[J].机电工程,2008, 25(1): 710.
MEI Pin-gao, LUO ZHi-zeng. SEMG disposal based on waVelet packet analysis and Elman neural network[J]. Mechanical & Electrical Engineering Magazine, 2008, 25(1): 710.
[22] 杨钟亮,王健,陈育苗.基于表面肌电的头部运动体态语言情感识别模型[J].计算机辅助设计与图形学学报, 2014, 26(9): 1396-1402.
YANG Zhong-liang, WANG Jian, CHEN Yu-miao. Surface EMG based emotion recognition model for body language of head movements[J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(9): 1396-1402.
[23] 杨钟亮,孙守迁,张克俊.基于基因表达式编程的坐姿舒适性主观测评模型与系统[J].计算机集成制造系统,2012, 18(10): 2138-2144.
YANG Zhong-liang, SUN Shou-qian, ZHANG Ke-jun. Subjective evaluation model and system for sitting comfort based on gene expression programming[J]. Computer Integrated Manufacturing Systems, 2012, 18(10): 2138-2144.
[24] SAVILLE D J. Multiple comparison procedures: the practical solution[J]. The American Statistician, 1990, 44(2): 174-180. |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|