Motion compatibility recognition of walk-aid robot based on multi-scale permutation entropy

doi:10.3969/j.issn.2095-4344.1954

Abstract

Abstract:

BACKGROUND: At present, the number of older adults with impaired limb motor ability continues to increase due to the influence of the environment or the deterioration of bodily functions. The decline of the lower limbs' motor ability of the older adults has made the design and development of walk-aid robot become one of current social care focus.

OBJECTIVE: When the motion trajectory of walk-aid robot is inconsistent with the desired trajectory of the human, the adaptive adjustment of walk-aid robot should be realized. This study was to recognize three kinds of situations, such as too large stride, too small stride and appropriate stride.

METHODS: In view of the nonlinearity and strong noise of surface electromyography, a multi-scale permutation entropy method based on wavelet decomposition was proposed to recognize three situations of man-robot’s motion compatibility. First, wavelet decomposition of collected surface electromyography signal was performed. Then, the permutation entropy was calculated for each scale of surface electromyography. Finally, Gaussian kernel support vector machine was used for pattern recognition.

RESULTS AND CONCLUSION: After wavelet decomposition, the signal on the d5 scale could be better recognized. Among them, recognition rate was 92% for too large stride, 90% for too small stride, and 94% for appropriate stride. The average recognition rate was 92%, which was 4.67% higher than that of original surface electromyography. Wavelet decomposition also achieved better results than other commonly used multi-scale methods. Therefore, in the man-machine motion compatibility recognition, the surface electromyography signal can be decomposed by wavelet to extract the permutation entropy on each scale, which can help to increase the recognition accuracy.

Key words: surface electromyography, walk-aid robot, motion compatibility, pattern recognition, wavelet decomposition, multi-scale, permutation entropy, Gaussian kernel support vector machine

CLC Number:

Chen Lingling, Yang Zekun, Sun Jianjun, Zhang Cun. Motion compatibility recognition of walk-aid robot based on multi-scale permutation entropy[J]. Chinese Journal of Tissue Engineering Research, 2019, 23(34): 5473-5478.

Figures/Tables 8

References

[1]Bogue R.Robotic exoskeletons: a review of recent progress. Industrial Robot.2015;42(1):5-10.

[2]Kim S,Bae J.Force-mode control of rotary series elastic actuators in a lower extremity exoskeleton using model-inverse time delay control.IEEE/ASME Trans Mech.2017;22(3):1392-1400.

[3]Yepes JC, Portela MA, Álvaro J, et al. Myoelectric control algorithm for robot-assisted therapy: A hardware-in-the-loop simulation study.Biomed Eng Online.2019;18(1):3.

[4]Lerner ZF,Gasparri GM,Bair MO,et al.An untethered ankle exoskeleton improves walking economy in a pilot study of individuals with cerebral palsy.IEEE Trans Neural Syst Rehabil Eng.2018;26(10):1985-1993.

[5]Li ZJ,Kang Y,Xiao ZY,et al.Human-robot coordination control of robotic exoskeletons by skill transfers.IEEE Trans Ind Electron. 2017;64(6):5171-5181.

[6]Chen ZT,Li ZJ,Chen CLP.Disturbance observer-based fuzzy control of uncertain MIMO mechanical systems with input nonlinearities and its application to robotic exoskeleton.IEEE Trans Cybern. 2017;47(4):984-994.

[7]George T,George KS,Sivanandan KS.Sensing processing and application of EMG signals for HAL (Hybrid Assistive Limb) [C]. International Conference on Sustainable Energy and Intelligent Systems, 2011:749-753.

[8]郭欣,王蕾,宣伯凯,等.基于有监督Kohonen神经网络的步态识别[J].自动化学报,2017,43(3):430-438.

[9]陈玲玲,杨鹏,耿艳利,等.基于肌电信号的膝关节力矩识别方法[J].中南大学学报(自然科学版), 2013(s2):117-121.

[10]刘磊,杨鹏,刘作军,等.采用核主成分分析和相关向量机的人体运动意图识别[J].机器人,2017,39(5): 661-669.

[11]Phukpattaranont P,Thongpanja S,Anam K,et al.Evaluation of feature extraction techniques and classifiers for finger movement recognition using surface electromyography signal.Med Biol Eng Comput.2018;56(12):2259-2271.

[12]Long Y,Du ZJ,Cong L,et al.Active disturbance rejection control based human gait tracking for lower extremity rehabilitation exoskeleton.ISA Trans.2017;67:389-397.

[13]Yang DP,Gu YK,Liu RQ,et al.Dexterous motion recognition for myoelectric control of multifunctional transradial prostheses.Adv Robotics.2014;28(22):1533-1543.

[14]Krasoulis A,Kyranou I,Erden MS,et al.Improved prosthetic hand control with concurrent use of myoelectric and inertial measurements.J Neuroeng Rehabil.2017; 14(1):71.

[15]Wu Y,Jiang D,Liu X,et al.A Human–Machine interface using electrical impedance tomography for hand prosthesis control. IEEE Trans Biomed Circuits Syst. 2018;12(6):1322-1333.

[16]James EG,Karabulut M.Vascular restriction decreases EMG regularity during walking.Hum Mov Sci.2013;32(3):389-399.

[17]Trybek P,Nowakowski M,Salowka J,et al.Sample entropy of sEMG signals at different stages of rectal cancer treatment. Entropy. 2018;20(11):863.

[18]Dostál O,Vysata O,Pazdera L,et al.Permutation entropy and signal energy increase the accuracy of neuropathic change detection in needle EMG.Comput Intell Neurosci. 2018;2018: 5276161.

[19]Wang F,Hao X,Zeng B,et al.Automated discrimination of gait patterns based on sEMG recognition[C]. Proceedings of 2013 Chinese Intelligent Automation Conference.Springer Berlin Heidelberg, 2013:643-651.

[20]Naik GR,Selvan SE,Arjunan SP,et al.An ICA-EBM-based sEMG classifier for recognizing lower limb movements in individuals with and without knee pathology.IEEE Trans Neural Syst Rehabil Eng. 2018;26(3):675-686.

[21]Xi X,Tang M,Miran SM,et al.Evaluation of feature extraction and recognition for activity monitoring and fall detection based on wearable sEMG sensors.Sensors.2017;17(6):1229.

[22]Diab A,Hassan M,Marque C,et al. Performance analysis of four nonlinearity analysis methods using a model with variable complexity and application to uterine EMG signals.Med Eng Phys. 2014;36(6):761-767.

[23]Guo Y,Naik GR,Huang S.Nonlinear multiscale maximal Lyapunov exponent for accurate myoelectric signal classification.Appl Soft Comput.2015;36:633-640.

[24]Dmitriy M,Terry B,Edward B,et al.Quantum theory of mass potentials. PloS One.2018; 13(7):e0198929.

[25]席旭刚,武昊,左静,等.基于排列组合熵和加权核Fisher的肌电跌倒检测[J].上海交通大学学报,2015, 49(11):1685-1689.

[26]姚文坡,刘铁兵,戴加飞,等.脑电信号的多尺度排列熵分析[J].物理学报,2014,63(7):078704.

[27]介丹,李宇驰,阴桂梅,等.基于方差的多尺度时间序列重构方法研究[J].太原理工大学学报,2017, 48(2):220-225.

[28]杜艳琴,黄华.基于独立成分和小波分析的胎儿心电提取[J].中国组织工程研究,2011,15(13): 2394-2397.

[29]张毅,冯晓林,罗元.基于改进小波包与样本熵的表面肌电信号特征提取[J].计算机应用研究,2015, 32(3):701-704.

[30]Hassan VM,Ali A,Yasser B.Optimized watermarking technique using self-adaptive differential evolution based on redundant discrete wavelet transform and singular value decomposition. Expert Syst Appl.2018;114:296-312.

[31]Zheng H,Zhang Y,Liu J,et al.A novel model based on wavelet LS-SVM integrated improved PSO algorithm for forecasting of dissolved gas contents in power transformers.Electr Pow Syst Res.2018;155:196-205.

[32]Chen W,Pourghasemi HR, Kornejady A,et al. Landslide spatial modeling: Introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques.Geoderma.2017;305:314-327.

[33]Kalantar B,Pradhan B,Naghibi SA,et al.Assessment of the effects of training data selection on the landslide susceptibility mapping: a comparison between support vector machine (SVM), logistic regression (LR) and artificial neural networks (ANN).Geomatics, Natural Hazards and Risk. 2018; 9(1):49-69.

[34]He P,Zheng B,Zheng J.Urban PM2. 5 Diffusion Analysis Based on the Improved Gaussian Smoke Plume Model and Support Vector Machine.Aerosol Air Qual Res.2018;18:3177-3186.

[35]Xue Y,Zhang L,Wang B,et al. Nonlinear feature selection using Gaussian kernel SVM-RFE for fault diagnosis.Applied Intelligence, 2018:1-26.

[36]何文斌,刘群锋,熊金志.支持向量机多项式光滑函数的误差理论研究[J].计算机研究与发展,2016, 53(7):1576-1585.

[37]Raghuwanshi BS,Shukla S.Class-specific kernelized extreme learning machine for binary class imbalance learning].Appl Soft Comput.2018;73:1026-1038.

[38]Pimentel A, Gomes R, Olstad BH, et al. A New Tool for the Automatic Detection of Muscular Voluntary Contractions in the Analysis of Electromyographic Signals. Interact Comput.2015; 27(5):492-499.

[39]张燕,郜鑫,陈玲玲,等.基于随机森林算法的地形识别系统在主动型膝上假肢控制中的应用[J].中国组织工程研究,2015,19(53):8609-8614.

[40]王蒙,陈玲玲,耿艳利,等.基于有限状态机的智能下肢假肢控制[J].中国组织工程研究,2012,16(26): 4756-4759.