Feasibility study on extraction finger joint angle information from sEMG signal

In this paper, three experiments were conducted about the extension/flexion movements of the index finger at two speeds 0.4Hz and 0.8Hz of the 10 subjects. AR coefficients of sEMG signals were used as the feature parameters fed into the fuzzy neural network. The motion direction identification, fixed finger joint angle recognition and trajectory forecast are implemented in this study. The experimental results are generally satisfactory: the accuracy rate of motion direction identification is 100% (0.4Hz) and 92.5% (0.8Hz); the accuracy rates of fixed finger joint angle recognition all reached 100% in 0.4Hz and 0.8Hz experiments; joint angle forecast achieved a good trajectory tracking. The results of this study show the feasibility of extraction finger joint angle information from sEMG.