Trust sensor interface for improving reliability of EMG-based user intent recognition

To achieve natural and smooth control of prostheses, Electromyographic (EMG) signals have been investigated for decoding user intent. However, EMG signals can be easily contaminated by diverse disturbances, leading to errors in user intent recognition and threatening the safety of prostheses users. To address this problem, we propose a trust sensor interface (TSI) that contains 2 modules: (1) abnormality detector that detects diverse disturbances with high accuracy and low latency and (2) trust evaluation that dynamically evaluates the reliability of EMG sensors. Based on the output of the TSI, the user intention recognition (UIR) algorithm is able to dynamically adjust their operations or decisions. Our experiments on an able-bodied subject have demonstrated that the proposed TSI can effectively detect two types of disturbances (i.e. motion artifacts and baseline shifts) and improve the reliability of the UIR.