Towards semi-supervised myoelectric finger motion recognition based on spatial motor units activation

It is vital to recognize the intention of finger motions for human-machine interaction (HMI). The latest research focuses on fine myoelectric control through the decoding of neural motor unit action potential trains (MUAPt) from high-density surface electromyographic (sEMG) signals. However, the existing EMG decoding algorithms rarely obtain the spatial matching relationship between decoded motion units (MU) and designated muscles, and the control interface can only recognize the trained hand gestures. In this study, a semi-supervised HMI based on MU-muscle matching (MMM) is proposed to recognize individual finger motions and even the untrained combined multi-finger actions Through automatic channel selection from high-density sEMG signals, the optimal spatial positions to monitor the MU activation of finger muscles are determined. Finger tapping experiment is carried out on ten subjects, and the experimental results show that the proposed sEMG decomposition algorithm based on MMM can accurately identify single finger motions with an accuracy of 93.1%+/- 1.4%, which is comparable to that of state-of-the-art pattern recognition methods. Furthermore, the MMM allows unsupervised recognizing the untrained combined multi-finger motions with an accuracy of 73%+/- 3.8%. The outcomes of this study benefit the practical applications of HMI, such as controlling prosthetic hand and virtual keyboard.

Automated summary

A semi-supervised HMI based on MU-muscle matching (MMM) was proposed to recognize individual finger motions and even untrained combined multi-finger actions. Automatic channel selection helped determine the optimal spatial positions to monitor the MU activation of finger muscles. Experimental results showed that the proposed method accurately identified single finger motions and even untrained combined multi-finger actions.