Fatigue Recognition using EMG Signals and Stochastic Switched ARX Model

The man-machine cooperative system is attracting great attention in many fields, such as industry, welfare and so on. The assisting system must be designed so as to accommodate the operator’s skill, which might be strongly affected by the fatigue. This paper presents a new fatigue recognizer based on the Electro MyoGram (EMG) signals and the Stochastic Switched ARX (SS-ARX) model which is one of the extended model of the standard Hidden Markov Model (HMM). Since the SS-ARX model can represent complex dynamical relationship which involves switching and stochastic variance, it is expected to show higher performance as the fatigue recognizer than using simple statistical characteristics of the EMG signal and/or standard HMM. The usefulness of the proposed strategy is demonstrated by applying to a peg-in-hole task.