Recognition of Lower Limb Muscle EMG Patterns by using Neural Networks during the Postural Balance Control

The purpose of the study was to recognize EMG signal patterns of lower limb muscles by using neural networks during the recovery of postural balance of human body. Surface electrodes were attached to several lower limb muscles. EMG signals were collected during the postural balance recovery process after a perturbation without permitting compensatory stepping. A waist pulling system was used to apply transient perturbations in five horizontal directions. The EMG signals of fifty repetitions of five motions were analyzed for 10 subjects. Twenty features were extracted from EMG signals of one event. By using neural networks, EMG signals were classified into five categories, such as forward perturbation, backward perturbation, lateral perturbation and two oblique perturbations. As results, motions were recognized with mean success rates of 75 percent. With the neural network classifier of this study, the EMG patterns of lower limb muscles during the recovery of postural balance could be classified with high accuracy of recognition.