Adaptive Hybrid Classifier for Myoelectric Pattern Recognition Against the Interferences of Outlier Motion, Muscle Fatigue, and Electrode Doffing

Abstract

Traditional myoelectric prostheses that employ a static pattern recognition model to identify human movement intention from surface electromyography (sEMG) signals hardly adapt to the changes in the sEMG characteristics caused by interferences from daily activities, which hinders the clinical applications of such prostheses. In this paper, we focus on methods to reduce or eliminate the impacts of three types of daily interferences on myoelectric pattern recognition (MPR), i.e., outlier motion, muscle fatigue, and electrode doffing/donning. We constructed an adaptive incremental hybrid classifier (AIHC) by combining one-class support vector data description and multiclass linear discriminant analysis in conjunction with two specific update schemes. We developed an AIHCbased MPR strategy to improve the robustness of MPR against the three interferences. Extensive experiments on hand-motion recognition were conducted to demonstrate the performance of the proposed method. Experimental results show that the AIHC has significant advantages over non-adaptive classifiers under various interferences, with improvements in the classification accuracy ranging from 7.1% to 39% (p < 0.01). The additional evaluations on data deviations demonstrate that the AIHC can accommodate large-scale changes in the sEMG characteristics, revealing the potential of the AIHC-based MPR strategy in the development of clinical myoelectric prostheses. Index Terms-Surface electromyography (sEMG), myoelectric prosthesis, adaptive classifier, online update. I. INTRODUCTION M YOELECTRIC pattern recognition (MPR) that can decipher movement intention from electromyography signals, has been regarded as an outstanding way to realize

The Muscle Fatigue’s Effects on the sEMG-Based Gait Phase Classification: An Experimental Study and a Novel Training Strategy

“…For example, the study reported by [47] proposed a method to classify hand movements through the single-channel sEMG, which did not consider the fatigue situation, and the method can be improved by our strategy. Previous studies have proposed the methods of designing classifiers that are robust against fatigue, such as fuzzy neural networks and adaptive hybrid classifiers [23,24]. However, these methods may be accompanied by increasing the computation and the complexity of classifiers, while our strategy may be easier to use.…”

“…Pioneer studies also focused on improving the classifiers' robustness against muscle fatigue. Song et al [23] and Ding et al [24] have proposed EMG based gesture classifier, which is robust to fatigue by using a fuzzy neural network and an adaptive incremental hybrid classifier-based recognize strategy, respectively. Mainardi et al [25] developed a new double differential electrode that can compensate for the influence of muscle fatigue by modifying its gain.…”

State of the art in parallel ankle rehabilitation robot: a systematic review

“…There have been many studies involving sEMG for motion intention recognition in the application of rehabilitation robots [79][80][81], and the sEMG signal should be incorporated in the active exercise of the AJC to make the active exercise more real-time and comfortable even though the sEMG signals change due to a variety of factors, such as placement, fatigue and sweat.…”

A Classification and Calibration Procedure for Gesture Specific Home-Based Therapy Exercise in Young People With Cerebral Palsy

“…In addition to attention, out-of-laboratory myoelectricbased gesture recognition performance is known to be limited by interference including: electrode shift, muscle fatigue, unwanted motion and force variation [34]- [36]. To compensate for this, Ding et al (2019) circumvent the burden of frequent retraining by using an adaptive incremental hybrid classifier [37]. The proposed method retrains target gestures in a semiautomated process by separating classes through resting and active states [37].…”

“…To compensate for this, Ding et al (2019) circumvent the burden of frequent retraining by using an adaptive incremental hybrid classifier [37]. The proposed method retrains target gestures in a semiautomated process by separating classes through resting and active states [37]. While manual input is still required, adaptive classifiers like this and others ( [38]- [40]) may be a promising approach to address real-world EMG variability.…”