Xiangxin Li

TL;DR: Three new time- domain features are proposed to improve the performance of EMG-PR based strategy in arm movement classification and could achieved an average classification accuracy of 92.00% ± 3.11% which was 6.49% higher than that of the commonly used time-domain features.

TL;DR: The feasibility of fusing sEMG and EEG signals towards improving motion classification accuracy for above-elbow amputees is demonstrated, which might enhance the control performances of multifunctional myoelectric prostheses in clinical application.

TL;DR: The effect of mobility on the performance of EMG-PR motion classifier was investigated based on myoelectric and accelerometer signals acquired from six upper-limb amputees across four scenarios and three methods were proposed to mitigate such effect.

TL;DR: Findings suggest that optimal feature set combination would yield a relatively high decoding accuracy that may improve the clinical robustness of MDoF neuroprosthesis.

TL;DR: In this paper, a force myography (FMG) recording system based on piezoelectret sensors was presented. And the FMG patterns were evaluated and identified by means of linear discriminant analysis and artificial neural network algorithms, and average motion classification accuracies of 96.1% and 94.8% were obtained.