SEMG-Based Human In-Hand Motion Recognition Using Nonlinear Time Series Analysis and Random Forest

As a novel and non-invasive sensing technology, surface electromyography (SEMG) can record the bioelectrical signals on the skin surface quickly and effectively, and thus has been widely used in human motion assessment in fields like medical rehabilitation and human-computer interaction. In this paper, an SEMG-based in-hand motion recognition system is proposed to recognize ten kinds of popular hand motions. According to the human common movements in performing in-hand object manipulations, ten sets of in-hand motions, including translation, transfer, and rotation, are designed, and then a nonlinear time series analysis method of SEMG signal processing is proposed to better capture the nonlinearity of these motions. The detailed analysis method of the nonlinear data is presented, and the experimental results, including human in-hand motion recognition result, motion recognition results of different subjects, and comparison results of different algorithms performance, are analyzed and discussed in detail. Experimental results illustrate that the human in-hand motion recognition system proposed in this paper can effectively recognize these different in-hand movements with a better performance than other popular methods.