Recognition of locomotion patterns based on BP neural network during different walking speeds

Pattern recognition based on myoelectric speed control is critical for neural-controlled powered lower limb prostheses. We preliminarily investigated the performance of surface electromyography signals used to identify movement modes with different speeds. The pattern recognition was tested on electromyography data collected from five muscles of sixteen able-bodied subjects. The BP neural network was used to identify level-ground walking modes with three different speeds: slow speed (0.5m/s), median speed (1m/s) and fast speed (1.5m/s). The results showed that the comprehensive recognition rate reached 90.48%, which would aid the future development of neural-controlled artificial legs and assist lower limb amputees with level ground walking.

[1]  Yang Peng,et al.  Leg amputees motion pattern recognition based on principal component analysis and BP network , 2013, 2013 25th Chinese Control and Decision Conference (CCDC).

[2]  Haibo He,et al.  Improving the performance of a neural-machine interface for prosthetic legs using adaptive pattern classifiers , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[3]  He Huang,et al.  Musculoskeletal model predicts multi-joint wrist and hand movement from limited EMG control signals , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[4]  Michelle M. Lusardi,et al.  Orthotics & prosthetics in rehabilitation , 2013 .

[5]  J Duchêne,et al.  Surface electromyogram during voluntary contraction: processing tools and relation to physiological events. , 1993, Critical reviews in biomedical engineering.

[6]  Fan Zhang,et al.  On Design and Implementation of Neural-Machine Interface for Artificial Legs , 2012, IEEE Transactions on Industrial Informatics.

[7]  陈亮,et al.  Effect of Upper-Limb Positions on Motion Pattern Recognition Using Electromyography , 2011 .

[8]  Shengxin Wang,et al.  Research on musculoskeletal model of elbow joint for evaluating the feasibility of FES. , 2015, Bio-medical materials and engineering.

[9]  Richard A. Brand,et al.  The biomechanics and motor control of human gait: Normal, elderly, and pathological , 1992 .

[10]  Dario Farina,et al.  EMG-Driven Forward-Dynamic Estimation of Muscle Force and Joint Moment about Multiple Degrees of Freedom in the Human Lower Extremity , 2012, PloS one.

[11]  Dustin L Crouch,et al.  Musculoskeletal model-based control interface mimics physiologic hand dynamics during path tracing task. , 2017, Journal of neural engineering.

[12]  Hugh Herr,et al.  User-adaptive control of a magnetorheological prosthetic knee , 2003, Ind. Robot.

[13]  Angkoon Phinyomark,et al.  EMG feature evaluation for improving myoelectric pattern recognition robustness , 2013, Expert Syst. Appl..

[14]  He Huang,et al.  A Strategy for Identifying Locomotion Modes Using Surface Electromyography , 2009, IEEE Transactions on Biomedical Engineering.

[15]  R. Brand,et al.  The biomechanics and motor control of human gait: Normal, elderly, and pathological , 1992 .

[16]  Feng Zhang,et al.  sEMG-based continuous estimation of joint angles of human legs by using BP neural network , 2012, Neurocomputing.

[17]  Jongsang Son,et al.  Determination of the dynamic knee joint range of motion during leg extension exercise using an EMG-driven model , 2012 .

[18]  Levi J. Hargrove,et al.  Detection of and Compensation for EMG Disturbances for Powered Lower Limb Prosthesis Control , 2016, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[19]  Wei Li,et al.  sEMG-Based Identification of Hand Motion Commands Using Wavelet Neural Network Combined With Discrete Wavelet Transform , 2016, IEEE Transactions on Industrial Electronics.

[20]  Huosheng Hu,et al.  Myoelectric control systems - A survey , 2007, Biomed. Signal Process. Control..