J Shanghai Jiaotong Univ Sci

Journal of Shanghai Jiaotong University(Science) >

2021 , Vol. 26 >Issue 1: 84 - 92

DOI: https://doi.org/10.1007/s12204-020-2249-1

Medicine-Engineering Interdisciplinary Research

Prosthetic Leg Locomotion-Mode Identification Based on High-Order Zero-Crossing Analysis Surface Electromyography

Expand
  • (1. College of Building Environment Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China;
    2. College of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin 300130, China)

Online published: 2021-01-19

Fold

Abstract

The research purpose was to improve the accuracy in identifying the prosthetic leg locomotion mode. Surface electromyography (sEMG) combined with high-order zero-crossing was used to identify the prosthetic leg locomotion modes. sEMG signals recorded from residual thigh muscles were chosen as inputs to pattern classifier for locomotion-mode identification. High-order zero-crossing were computed as the sEMG features regarding locomotion modes. Relevance vector machine (RVM) classifier was investigated. Bat algorithm (BA) was used to compute the RVM classifier kernel function parameters. The classification performance of the particle swarm optimization-relevance vector machine (PSO-RVM) and RVM classifiers was compared. The BA-RVM produced lower classification error in sEMG pattern recognition for the transtibial amputees over a variety of locomotion modes: upslope, downgrade, level-ground walking and stair ascent/descent.

Key words： intelligent prosthesis; surface electromyography (sEMG); relevance vector machine(RVM); high-order
zero-crossing; bat algorithm (BA); locomotion-mode identification

Cite this article

LIU Lei (刘磊), YANG Peng (杨鹏), LIU Zuojun (刘作军), SONG Yinmao (宋寅卯) . Prosthetic Leg Locomotion-Mode Identification Based on High-Order Zero-Crossing Analysis Surface Electromyography[J]. Journal of Shanghai Jiaotong University(Science), 2021 , 26(1) : 84 -92 . DOI: 10.1007/s12204-020-2249-1

References

[1] YOUNG A J, SIMON A M, FEY N P, et al. Intentrecognition in a powered lower limb prosthesis usingtime history information [J]. Annals of Biomedical Engineering,2014, 42(3): 631-641.
[2] SUN J M, VOGLEWEDE P A. Powered transtibialprosthetic device control system design, implementation,and bench testing [J]. Journal of Medical Devices,2014, 8(1): 011004.
[3] LIU Z J, LIN W, GENG Y L, et al. Intent patternrecognition of lower-limb motion based on mechanicalsensors [J]. IEEE/CAA Journal of Automatica Sinica,2017, 4(4): 651-660.
[4] ZHENG E H, WANG Q N. Noncontact capacitivesensing-based locomotion transition recognition foramputees with robotic transtibial prostheses [J]. IEEETransactions on Neural Systems and RehabilitationEngineering, 2017, 25(2): 161-170.
[5] SHENG M, LIU S Q, WANG J, et al. Motion intentrecognition of intelligent lower limb prosthesis basedon GMM-HMM [J]. Chinese Journal of Scientific Instrument,2019, 40(5): 169-178 (in Chinese).
[6] WANG Y X, CHEN H, YIN Z, et al. Human action androad condition recognition based on the inertial information[J]. Journal of Biomedical Engineering, 2018,35(4): 621-630 (in Chinese).
[7] HUANG S, FERRIS D P. Muscle activation patternsduring walking from transtibial amputees recordedwithin the residual limb-prosthetic interface [J]. Journalof Neuroengineering and Rehabilitation, 2012, 9:55.
[8] HARGROVE L J, SIMON A M, YOUNG A J, et al.Robotic leg control with EMG decoding in an amputeewith nerve transfers [J]. The New England Journal ofMedicine, 2013, 369(13): 1237-1242.
[9] ZHAO X D, LIU Z J, CHEN L L, et al. Approach ofrunning gait recognition for lower limb amputees [J].Journal of Zhejiang University (Engineering Science),2018, 52(10): 1980-1988 (in Chinese).
[10] SIMON A M, INGRAHAM K A, SPANIAS J A, etal. Delaying ambulation mode transition decisions improvesaccuracy of a flexible control system for poweredknee-ankle prosthesis [J]. IEEE Transactions onNeural Systems and Rehabilitation Engineering, 2017,25(8): 1164-1171.
[11] KIM D H, CHO C Y, RYU J. Real-time locomotionmode recognition employing correlation feature analysisusing EMG pattern [J]. ETRI Journal, 2014, 36(1):99-105.
[12] MILLER J D, BEAZER M S, HAHNM E. Myoelectricwalking mode classification for transtibial amputees[J]. IEEE Transactions on Biomedical Engineering,2013, 60(10): 2745-2750.
[13] YOUNG A J, HARGROVE L J, KUIKEN T A.Improving myoelectric pattern recognition robustnessto electrode shift by changing interelectrode distanceand electrode configuration [J]. IEEE Transactions onBiomedical Engineering, 2012, 59(3): 645-652.
[14] WANG H T, LI T, HUANG H, et al. A motor imageryanalysis algorithm based on spatio-temporal-frequencyjoint selection and relevance vector machine [J]. ControlTheory & Applications, 2017, 34(10): 1403-1408(in Chinese).
[15] ZHU B L, ZHU W Y, ZHU Z Q, et al. Applicationof bat algorithm based on statistical characteristicsin spectrum allocation of cognitive radio [J]. SystemsEngineering and Electronics, 2018, 40(2): 441-446 (in Chinese).
[16] WANG J H, ZHANG L, SHI C, et al. Task allocationmodeling and solving algorithm for equipmentsupport using DLS-BCIWBA [J]. Systems Engineeringand Electronics, 2018, 40(9): 1979-1985 (in Chinese).
[17] GUO X,WANG L, XUAN B K, et al. Gait recognitionbased on supervised Kohonen neural network [J]. ActaAutomatica Sinica, 2017, 43(3): 430-438 (in Chinese).
[18] CHENG J, CHEN X, PENG H. An onset detectionmethod for action surface electromyography basedon sample entropy [J]. Acta Electronica Sinica, 2016,44(2): 479-484 (in Chinese).
[19] LIU L, YANG P, LIU Z J. Lower limb locomotionmode identification based on multi-source informationand particle swarm optimization algorithm [J]. Journalof Zhejiang University (Engineering Science), 2015,49(3): 439-447 (in Chinese).

Options
Outlines

/

〈 〉