Hostname: page-component-76fb5796d-wq484 Total loading time: 0 Render date: 2024-04-27T21:48:37.463Z Has data issue: false hasContentIssue false
  • English
  • Français

Online pattern recognition of lower limb movements based on sEMG signals and its application in real-time rehabilitation training

Published online by Cambridge University Press:  13 November 2023

Ye Ye Open the ORCID record for Ye Ye [Opens in a new window] ,
Ming-xia Zhu ,
Chang-wei Ou ,
Bing-zhu Wang Open the ORCID record for Bing-zhu Wang [Opens in a new window] ,
Lu Wang  and
Neng-gang Xie
Ye Ye*
Affiliation:
Department of Mechanical Engineering, Anhui University of Technology, Maanshan, Anhui, 243002, China
Ming-xia Zhu
Affiliation:
Department of Mechanical Engineering, Anhui University of Technology, Maanshan, Anhui, 243002, China
Chang-wei Ou
Affiliation:
Department of Management Science and Engineering, Anhui University of Technology, Maanshan, Anhui, 243002, China
Bing-zhu Wang
Affiliation:
College of Mechanics and Materials, Hohai University, Nanjing, 211100, China
Lu Wang
Affiliation:
Department of Mechanical Engineering, Anhui University of Technology, Maanshan, Anhui, 243002, China
Neng-gang Xie*
Affiliation:
Department of Management Science and Engineering, Anhui University of Technology, Maanshan, Anhui, 243002, China
*
Corresponding authors: Ye Ye, Neng-gang; Emails: yeye@ahut.edu.cn, xieng@ahut.edu.cn
Corresponding authors: Ye Ye, Neng-gang; Emails: yeye@ahut.edu.cn, xieng@ahut.edu.cn
Get access Rights & Permissions [Opens in a new window]

Abstract

An online pattern recognition method of lower limb movements is proposed based on the personalized surface electromyography (sEMG) signals, and the corresponding experimental researches are performed in the rehabilitation training. Further, a wireless wearable acquisition instrument is used. Based on this instrument, a host computer for the personal online recognition and real-time control of rehabilitation training is developed. Three time-domain features and two features in the nonlinear dynamics are selected as the joint set of the characteristic values for the sEMG signals. Then a particle swarm optimization (PSO) algorithm is used to optimize the feature channels, and a k-nearest neighbor (KNN) algorithm and the extreme learning machine (ELM) algorithm are combined to classify and recognize individual sample data. Based on the multi-pose lower limb rehabilitation robot, the real-time motion recognition and the corresponding rehabilitation training are carried out by using the online personalized classifier. The experimental results of eight subjects indicate that it takes only 6 min to build an online personalized classifier for the four types of the lower limb movements. The recognition between switches of different rehabilitation training movements is timely and accurate, with an average recognition accuracy of more than 95%. These results demonstrate that this system has a strong practicability.

Keywords

surface electromyography signalsonline pattern recognitionrehabilitation trainingoptimization of feature channel
Type
Research Article
Information
Robotica , Volume 42 , Issue 2 , February 2024 , pp. 389 - 414
Copyright
© The Author(s), 2023. Published by Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

Kusche, R. and Ryschka, M., “Combining bioimpedance and EMG measurements for reliable muscle contraction detection,” IEEE Sens. J. 19(23), 11687–11696 (2019).CrossRefGoogle Scholar
Bi, L.-Z., Feleke, A. G. and Guan, C.-T., “A review on EMG-based motor intention prediction of continuous human upper limb motion for human-robot collaboration,” Biomed. Signal Process. Control 51, 113–127 (2019).CrossRefGoogle Scholar
Hara, Y., “Brain plasticity and rehabilitation in stroke patients,” J. Nippon Med. School 82(1), 4–13 (2015).CrossRefGoogle ScholarPubMed
Jochumsen, M., Navid, M. S., Rashid, U., Haavik, H. and Niazi, I. K., “EMG-versus EEG-triggered electrical stimulation for inducing corticospinal plasticity,” IEEE Trans. Neural Syst. Rehabil. Eng. 27(9), 1901–1908 (2019).CrossRefGoogle ScholarPubMed
Govil, K., Noohu, M. M. and Krebs, H. I., “Effect of EMG biofeedback training of gluteus maximus muscle on gait parameters in incomplete spinal cord injury,” NeuroRehabilitation 33(1), 147–152 (2013).CrossRefGoogle ScholarPubMed
Scheme, E. J., Englehart, K. B. and Hudgins, B. S., “Selective classification for improved robustness of myoelectric control under nonideal conditions,” IEEE Trans. Biomed. Eng. 58(6), 1698–1705 (2011).CrossRefGoogle ScholarPubMed
Ding, Q.-C., Zhao, X.-G. and Han, J.-D., “Hand movement recognition based on fault-tolerant classification of electromyographic signals,” Robot 37(1), 9–16 (2015).Google Scholar
Veer, K., Agarwal, R. and Kumar, A., “Processing and interpretation of surface electromyogram signal to design prosthetic device,” Robotica 34(7), 1486–1494 (2016).CrossRefGoogle Scholar
Phukpattaranont, P., Thongpanja, S., Anam, K., Al-Jumaily, A. and Limsakul, C., “Evaluation of feature extraction techniques and classifiers for finger movement recognition using surface electromyography signal,” Med. Biol. Eng. Comput. 56(12), 2259–2271 (2018).CrossRefGoogle ScholarPubMed
Zheng, H.-P. and Li, Y.-R., “Research on online gesture recognition system based on dual channel surface EMG signals,” Internet Things Technol. 12(3), 17–20+23 (2022).Google Scholar
Gupta, R. and Agarwal, R., “Single channel EMG-based continuous terrain identification with simple classifier for lower limb prosthesis,” Biocybern. Biomed. Eng. 39(3), 775–788 (2019).10.1016/j.bbe.2019.07.002CrossRefGoogle Scholar
Tavakoli, M., Benussi, C. and Lourenco, J. L., “Single channel surface EMG control of advanced prosthetic hands: A simple, low cost and efficient approach,” Expert Syst. Appl. 79, 322–332 (2017).CrossRefGoogle Scholar
Phinyomark, A., Phukpattaranont, P. and Limsakul, C., “Fractal analysis features for weak and single-channel upper-limb EMG signals,” Expert Syst. Appl. 39(12), 11156–11163 (2012).10.1016/j.eswa.2012.03.039CrossRefGoogle Scholar
Zhang, S., Li, J.-T., Bie, D.-Y. and Han, J.-D., “Gesture recognition by single-channel sEMG decomposition and LSTM network,” Chin. J. Sci. Instrum. 42(4), 228–235 (2021).Google Scholar
Xiong, A.-B., Zhang, D., Zhao, X., Han, J. and Liu, G., “Classification of hand gestures based on single-channel sEMG decomposition,” J. Mech. Eng. 52(7), 6–13 (2016).10.3901/JME.2016.07.006CrossRefGoogle Scholar
Shi, X.-J., Application Research on sEMG Man-Machine Interface Environment Control System Based on Finger Movement (South China University of Technology, Guangzhou, 2020).Google Scholar
Matsubara, T. and Morimoto, J., “Bilinear modeling of EMG signals to extract user-independent features for multiuser myoelectric interface,” IEEE Trans. Biomed. Eng. 60(8), 2205–2213 (2013).CrossRefGoogle ScholarPubMed
Cote-Allard, U., Fall, C. L., Campeau-Lecours, A., Gosselin, C., Laviolette, F. and Gosselin, B., “Transfer Learning for sEMG Hand Gestures Recognition Using Convolutional Neural Networks,” In: Proceedings of the 2017 IEEE International Conference on Systems, Man, and Cybernetics (IEEE, Banff, 2017) pp. 1663–1668.Google Scholar
Kalani, H., Moghimi, S. and Akbarzadeh, A., “Toward a bio-inspired rehabilitation aid: SEMG-CPG approach for online generation of jaw trajectories for a chewing robot,” Biomed. Signal Process. Control 51, 285–295 (2019).10.1016/j.bspc.2019.02.022CrossRefGoogle Scholar
Zhang, Y., Xu, X.-L. and Luo, Y., “Adaptive myoelectric human-machine interface systems using online support vector machines,” J. Huazhong Univ. Sci. Technol. (Nat. Sci. Ed.) 41(4), 75–79 (2013).Google Scholar
Sun, B.-X., Cheng, G., Dai, Q., Chen, T., Liu, W. and Xu, X., “Human motion intention recognition based on EMG signal and angle signal,” Cogn. Comput. Syst. 3(1), 37–47 (2021).CrossRefGoogle Scholar
Chen, X. and Wang, Z.-J., “Pattern recognition of number gestures based on a wireless surface EMG system,” Biomed. Signal Process. Control 8(2), 184–192 (2013).CrossRefGoogle Scholar
Zhou, C.-C., Yang, L., Liao, H., Liang, B. and Ye, X., “Ankle foot motion recognition based on wireless wearable sEMG and acceleration sensors for smart AFO,” Sens. Actuators A Phys. 331, 113025 (2021).CrossRefGoogle Scholar
Li, X.-O., Zhou, Z., Liu, W. and Ji, M., “Wireless sEMG-based identification in a virtual reality environment,” Microelectron. Reliab. 98, 78–85 (2019).CrossRefGoogle Scholar
Bai, J.-X., Liu, Y.-P., Liu, X., Cui, R., Cao, H.-L., Shan, Y.-H., Yu, F., Yuan, Y.-H. and Wang, R.-X., “Design of electromyography wireless acquisition system based on flexible dry electrodes,” Micronanoelectron. Technol. 56(7), 556–563 (2019).Google Scholar
Wang, B.-Z., Ou, C.-W., Xie, N.-G., Wang, L., Yu, T.-T., Fan, G.-H. and Chu, J.-F., “Lower limb motion recognition based on surface electromyography signals and its experimental verification on a novel multi-posture lower limb rehabilitation robots,” Comput. Electr. Eng. 101, 108067 (2022).CrossRefGoogle Scholar
Narayan, Y., “SEMG signal classification using KNN classifier with FD and TFD features,” Mater. Today Proc. 37, 3219–3225 (2021).10.1016/j.matpr.2020.09.089CrossRefGoogle Scholar
Zhang, S., Li, X., Zong, M., Zhu, X. and Cheng, D., “Learning k for kNN classification,” ACM Trans. Intell. Syst. Technol. 8(3), 1–19 (2017).Google Scholar
Huang, G.-B., Zhu, Q.-Y. and Siew, C.-K., “Extreme learning machine: Theory and applications,” Neurocompting 1(2/3), 489–501 (2006).CrossRefGoogle Scholar
Wang, D., Tan, D. and Liu, L., “Particle swarm optimization algorithm: An overview,” Soft Comput. 22(2), 387–408 (2018).CrossRefGoogle Scholar
Pano, V. and Ouyang, P. R., “Gain tuning of position domain PID control using particle swarm optimization,” Robotica 34(6), 1351–1366 (2016).CrossRefGoogle Scholar
Pancholi, S. and Joshi, A. M., “Time derivative moments based feature extraction approach for recognition of upper limb motions using emg,” IEEE Sens. Lett. 3(4), 5084–5087 (2019).CrossRefGoogle Scholar
Delgado-Bonal, A. and Marshak, A., “Approximate entropy and sample entropy: A comprehensive tutorial,” Entropy 21(6), 541 (2019).10.3390/e21060541CrossRefGoogle ScholarPubMed
Fan, G.-H., Movement Pattern Recognition and Fatigue Analysis Based on Surface Electromyography Signals of Human Lower Limbs (Anhui University of Technology, Ma’anshan, 2020).Google Scholar
Liu, H. and Yu, L., “Toward integrating feature selection algorithms for classification and clustering,” IEEE Trans. Knowl. Data Eng. 17(4), 491–502 (2005).Google Scholar
Chow, C.-K. and Liu, C.-N., “Approximating discrete probability distributions with dependence trees,” IEEE Trans. Inf. Theory 14(3), 462–467 (1968).10.1109/TIT.1968.1054142CrossRefGoogle Scholar
Xue, B., Zhang, M., Browne, W. N. and Yao, X., “A survey on evolutionary computation approaches to feature selection,” IEEE Trans. Evol. Comput. 20(4), 606–626 (2016).10.1109/TEVC.2015.2504420CrossRefGoogle Scholar