Lower Limb Movement Recognition Using EMG Signals

This paper presents an enhanced extraction feature for lower limb movement recognition application using surface EMG signals. Public SEMG database is used for system evaluation, where subjects, depending on knee normality, are divided into normal and abnormal groups. The spectogram of input EMG signals are calculated in time-frequency domain, and then processed with standard deviation texture. Experimental results show that EMG data of Semitendinosus (ST) muscle with Convolutional Neural Network (CNN) classifier provide the highest accuracy of 92% for classifying up to three movements (gait, leg extension, leg flexion) in normal group, and 95% for classifying two movements (gait, leg flexion) in abnormal group.