Recognition of human lower limb movement intention based on surface electromyography of lower limb corresponding to five gaits

doi:10.12307/2022.499

Abstract

Abstract: BACKGROUND: The lower limb exoskeleton robot is used to recover the basic walking ability of patients. To realize the high coordination between humans and robots and to design robot control strategies, it is necessary to recognize the movement intention of the lower limb which includes gait.
OBJECTIVE: To propose a new classifier to recognize gait using surface electromyography.
METHODS: Firstly, surface electromyography data of lower limbs in five gait patterns were collected. Secondly, the collected signals were denoised and the features were extracted to obtain the data sets of five gait patterns. After that, two of them were combined and 10 groups of data sets were built. Thirdly, the probabilistic neural networks were trained with the AdaBoost algorithm based on each group of data sets. Fourthly, ten strong classifiers were obtained by ensemble of trained probabilistic neural networks. Finally, the testing samples were input into 10 strong classifiers and the categories were judged by voting.
RESULTS AND CONCLUSION: An average recognition rate of 90.2% was achieved in the experiment by improved AdaBoost algorithm to recognize the five gait patterns. Compared with separate probabilistic neural network, the average recognition rate of separate probabilistic neural network was 68.2%, which was lower than that of improved AdaBoost algorithm. When the weak classifier was replaced by support vector machine, BP neural network or decision tree was used to construct strong classifiers for comparison. When a weak classifier was utilized, the average recognition rate of separate support vector machine was higher than that of separate probabilistic neural network. However, but the average recognition rate of strong classifier based on probabilistic neural network was higher than that 84.3% based on support vector machine with improved AdaBoost algorithm.

Key words: gait recognition, surface electromyogram, butterworth filter, adaptive filtering, feature extraction, probabilistic neural network, AdaBoost algorithm, multi-classification problem

CLC Number:

Zhao Yiming, Wang Jie, Zhang Gaowei, Sun Jianjun, Yang Peng. Recognition of human lower limb movement intention based on surface electromyography of lower limb corresponding to five gaits[J]. Chinese Journal of Tissue Engineering Research, 2022, 26(12): 1805-1811.

Figures/Tables 3

References

[1] VU HTT, GOMEZ F, CHERELLE P, et al. ED-FNN: A New Deep Learning Algorithm to Detect Percentage of the Gait Cycle for Powered Prostheses. Sensors (Basel). 2018;18(7):2389.
[2] 孟琳,董洪涛,侯捷,等.面向下肢康复的柔性外骨骼机器人进展研究[J].仪器仪表学报,2021,42(6):1-13.
[3] JOO SY, LEE SY, CHO YS, et al. Clinical Utility of an Exoskeleton Robot Using 3-Dimensional Scanner Modeling in Burn Patient: A Case Report. J Burn Care Res. 2021 Apr 21:irab060. doi: 10.1093/jbcr/irab060. Online ahead of print.
[4] LANGHORNE P, BERNHARDT J, KWAKKEL G. Stroke rehabilitation. Lancet. 2011;377(9778):1693-1702.
[5] AHN KK, NGUYEN HTC. Intelligent switching control of a pneumatic muscle robot arm adopting learning vector quantization neural network. Mechatronics. 2007;17(4-5):255-262.
[6] LI Z, HUANG Z, HE W, et al. Adaptive impedance control for an upper limb robotic exoskeleton using biological signals. IEEE Trans Industr Electr. 2017;64(2):1664-1674.
[7] 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.
[8] 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),2013,44(S2):117-121.
[9] 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.
[10] 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.
[11] 龚思远,杨鹏,宋亮,等.基于迭代学习控制智能下肢假肢研制:实现了对健肢步速的跟随[J].中国组织工程研究与临床康复,2010, 14(13):2295-2298.
[12] PURUSHOTHAMAN G, VIKAS R. Identification of a feature selection based pattern recognition scheme for finger movement recognition from multichannel EMG signals. Australas Phys Eng Sci Med. 2018; 41(2):549-559.
[13] LONG Y, DU Z, CONG L, et al. Active disturbance rejection control based human gait tracking for lower extremity rehabilitation exoskeleton. ISA Trans. 2017;67:389-397.
[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] 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.
[16] 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.
[17] GAO F, TIAN T, YAO T, et al. Human Gait Recognition Based on Multiple Feature Combination and Parameter Optimization Algorithms. Comput Intell Neurosci. 2021;2021:6693206.
[18] 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. Neural Netw. 2017;85:51-68.
[19] 周枚林.基于人体下肢肌电信号的复杂步态识别与步长估计研究[D].重庆:重庆大学,2019.
[20] 罗莎,夏国恩,朱新琰.改进Adaboost算法的人体步态识别方法[J].控制工程,2018,25(7):1312-1317.
[21] 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.
[22] STAGSTED RAW, RAMARI C, SKJERBAEK AG, et al. Lower extremity muscle power - A critical determinant of physical function in aging and multiple sclerosis. Exp Gerontol. 2021;150:111347.
[23] DING Z, YANG C, WANG Z, et al. Online Adaptive Prediction of Human Motion Intention Based on sEMG. Sensors (Basel). 2021;21(8):2882.
[24] 梁津国,罗二平,申广浩,等.基于自适应滤波器的表面肌电信号消噪方法研究[J].中国医学物理学杂志,2008(3):679-681.
[25] VALLERY H, BURGKART R, HARTMANN C, et al. Complementary limb motion estimation for the control of active knee prostheses. Biomed Tech (Berl). 2011;56(1):45-51.
[26] 郝静涵.基于SEMG信号及加速度信号的步态辨识研究[D].石家庄:河北工业大学,2019.
[27] 俞毕洪.基于表面肌电信号的穿戴式人体行为识别系统[D].杭州:浙江大学,2018.
[28] WANG W, SUN D. The improved AdaBoost algorithms for imbalanced data classification. Information Sciences. 2021;563:358-374.
[29] 于玲,吴铁军.集成学习:Boosting算法综述[J].模式识别与人工智能,2004,17(1):52-59.
[30] 徐继伟,杨云.集成学习方法:研究综述[J].云南大学学报(自然科学版),2018,40(6):1082-1092.
[31] 张松.基于SVM和Adaboost的多分类算法研究[D].济南:山东师范大学,2019.
[32] 杨新武,马壮,袁顺.基于弱分类器调整的多分类Adaboost算法[J].电子与信息学报,2016,38(2):373-380.
[33] PANG J, ZHAO Z. Real-time Monitoring of Fluidized Bed Agglomerating based on Improved Adaboost Algorithm. Journal of Physics Conference Series. 2021;1924(1):012026.
[34] TANG D. Fault Diagnosis Method of Power Transformer Based on Improved PNN. Journal of Physics Conference Series. 2021;1848(1) :012122.
[35] SHANMUGAM P, RAJA J, PITCHAI R. An automatic recognition of glaucoma in fundus images using deep learning and random forest classifier. Applied Soft Computing. 2021;109:107512.
[36] 方匡南,吴见彬,朱建平,等.随机森林方法研究综述[J].统计与信息论坛,2011,26(3):32-38.
[37] 李婉婉,李国宁.基于GMM聚类和PNN的道岔故障诊断研究[J].控制工程,2021,28(3):429-434.
[38] KIM J, WAGNER J, REHM M, et al. Bi-channel Sensor Fusion for Automatic Sign Language Recognition. Netherlands: 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition. 2008:647-652.
[39] LI Y, CHEN X, ZHANG X, et al. A sign-component-based framework for Chinese sign language recognition using accelerometer and sEMG data. IEEE Trans Biomed Eng. 2012;59(10):2695-2704.
[40] 曹祥红,刘磊,杨鹏,等.利用多源信息和极限学习机的人体运动意图识别[J].传感技术学报,2017,30(8):1171-1177.