Estimation and Correlation Analysis of Lower Limb Joint Angles Based on Surface Electromyography

Abstract

Many people lose their motor function because of spinal cord injury or stroke. This work studies the patient’s continuous movement intention of joint angles based on surface electromyography (sEMG), which will be used for rehabilitation. In this study, we introduced a new sEMG feature extraction method based on wavelet packet decomposition, built a prediction model based on the extreme learning machine (ELM) and analyzed the correlation between sEMG signals and joint angles based on the detrended cross-correlation analysis. Twelve individuals participated in rehabilitation tasks, to test the performance of the proposed method. Five channels of sEMG signals were recorded, and denoised by the empirical mode decomposition. The prediction accuracy of the wavelet packet feature-based ELM prediction model was found to be 96.23% ± 2.36%. The experimental results clearly indicate that the wavelet packet feature and ELM is a better combination to build a prediction model.

Continuous Myoelectric Prediction of Future Ankle Angle and Moment Across Ambulation Conditions and Their Transitions

“…While effective, it requires constant and time consuming (e.g., 30 min; Meyer et al, 2017) re-calibration of model parameters that are sensitive to changes in muscle-tendon geometry which may not be well characterized for amputees or orthopedic impaired individuals (Shao et al, 2009;Meyer et al, 2017), and consequently, not suitable for real-time applications. Limb joint mechanics and kinematics have been continuously estimated from electromyography (EMG) signals (Sepulveda et al, 1993;Lee and Lee, 2005;Shao et al, 2009;Prasertsakul et al, 2012;Zhang et al, 2012;Chen et al, 2013Chen et al, , 2018Ardestani et al, 2014;Farmer et al, 2014;Ngeo et al, 2014;Li et al, 2015;Liu et al, 2017aLiu et al, , 2020Meyer et al, 2017;Huihui et al, 2018;Baby Jephil et al, 2020;Gupta et al, 2020;Keleş and Yucesoy, 2020;Wang et al, 2020), hip joint dynamics (Embry et al, 2018;Dey et al, 2019;Eslamy and Alipour, 2019), knee joint dynamics (Joshi et al, 2011;Embry et al, 2018;Eslamy and Alipour, 2019), force myography (Kumar et al, 2021), and ground reaction forces (GRF) (Liu et al, 2009;Jacobs and Ferris, 2015), among others. Support vector regression (SVR) and Gaussian process regression have been used to continuously estimate ankle angle and ankle moment simultaneously using hip and knee joint kinematics (Dey et al, 2019) and shank kinematics (Eslamy and Alipour, 2019), respectively.…”

“…Classification algorithms have been used together with surface EMG to distinguish among discrete locomotion modes (Huang et al, 2009;Young et al, 2014;Gupta and Agarwal, 2017;Liu et al, 2017b) while other approaches continuously estimate ankle joint kinematics (Sepulveda et al, 1993;Prasertsakul et al, 2012;Zhang et al, 2012;Farmer et al, 2014;Chen et al, 2018;Huihui et al, 2018;Baby Jephil et al, 2020;Gupta et al, 2020;Keleş and Yucesoy, 2020;Wang et al, 2020) and kinetics (Sepulveda et al, 1993;Ardestani et al, 2014;Baby Jephil et al, 2020;Keleş and Yucesoy, 2020) using EMG signals. Most approaches characterize performance during a single type of terrain (e.g., level walking) (Prasertsakul et al, 2012;Zhang et al, 2012;Ardestani et al, 2014;Farmer et al, 2014;Chen et al, 2018;Gupta et al, 2020;Keleş and Yucesoy, 2020;Wang et al, 2020) or ankle motion while sitting (Zhang et al, 2012;Huihui et al, 2018;Baby Jephil et al, 2020). Models that estimate ankle angle or ankle moment during more than one condition (e.g., speeds) have begun to emerge.…”

Pulmonary Vein Activity Organization to Determine Atrial Fibrillation Recurrence: Preliminary Data from a Pilot Study

“…After the preprocessing step, cross-correlation measurements were carried out in order to quantify the synchronization of the local activation time series between different sites. This analysis has been previously applied to different types of signals, from biomedical to meteorological signals [22][23][24]. Mathematics can be helpful for a better understanding of wave propagation in these cardiac models to gain a clear picture of the correlation as a snapshot measure of global synchrony.…”

Gesture Recognition Based on Multiscale Singular Value Entropy and Deep Belief Network

“…Surface electromyography (sEMG) is a kind of bioelectrical signal [3][4][5] that reflects the neuromuscular system activity collected from the muscle surface and contains abundant information related to gesture action. As sEMG signal acquisition is simple and noninvasive, gesture recognition based on sEMG [6,7] is favored by an increasing number of researchers at home and abroad.…”

“…4) where U and V are orthogonal matrices of m m  and n n  order, respectively, diagonal matrix. Its diagonal elements are singular values of matrix A which arranged in descending order.…”