Estimation of Lower Limb Kinematics during Squat Task in Different Loading Using sEMG Activity and Deep Recurrent Neural Networks.

Alireza Rezaie Zangene,Ali Abbasi,Kianoush Nazarpour

doi:10.3390/s21237773

Alireza Rezaie Zangene, Ali Abbasi + Show 1 more

Open Access

https://doi.org/10.3390/s21237773

Copy DOI

Abstract

The aim of the present study was to predict the kinematics of the knee and the ankle joints during a squat training task of different intensities. Lower limb surface electromyographic (sEMG) signals and the 3-D kinematics of lower extremity joints were recorded from 19 body builders during squat training at four loading conditions. A long-short term memory (LSTM) was used to estimate the kinematics of the knee and the ankle joints. The accuracy, in terms root-mean-square error (RMSE) metric, of the LSTM network for the knee and ankle joints were 6.774 ± 1.197 and 6.961 ± 1.200, respectively. The LSTM network with inputs processed by cross-correlation (CC) method showed 3.8% and 4.7% better performance in the knee and ankle joints, respectively, compared to when the CC method was not used. Our results showed that in the prediction, regardless of the intensity of movement and inter-subject variability, an off-the-shelf LSTM decoder outperforms conventional fully connected neural networks.

Highlights

Amputation, that is a removal of a limb, can be because of a trauma or medical illness.In the United States about 1.6 million people were amputated in 2005 and it is expected to grow to than 3.5 million by 2050 [1]
Our results showed that in the prediction, regardless of the intensity of movement and inter-subject variability, an off-the-shelf long-short term memory (LSTM) decoder outperforms conventional fully connected neural networks
The surface electromyographic (sEMG) signals of vastus medialis (VM), rectus femoris (RF), biceps femoris (BF), tibialis anterior (TA), and medial gastrocnemius (MG) muscles of right leg were recorded with a wireless sEMG collection device at the sampling rate of 1500 Hz which they are the most muscles move the knee and ankle in the sagittal plane [39]

Summary

Introduction

Amputation, that is a removal of a limb, can be because of a trauma or medical illness.In the United States about 1.6 million people were amputated in 2005 and it is expected to grow to than 3.5 million by 2050 [1]. The symmetrical function of the lower limbs depends on the kinematics similarity of the prosthesis to their biological counterparts. The symmetry between the two limbs can be improved through the kinematic adjustments of the prosthesis. It is expected that active prostheses improve gait symmetry and walking stability [9], reduce metabolic cost [10], and enhance similarity of ground reaction forces to intact limb [11]. Even in the active type of prosthesis, lack of connection between prosthesis and human nervous system, can lead to some degree of asymmetry in unilateral lower limb amputee and there must be some kind of interaction between prosthesis and the user

Objectives

Methods

Results

Discussion

Conclusion