Walking Pattern Recognition by Feature Vector of EMG

摘要

In order to find a way to get locomotion movement class discrimination by EMGfeatures during different walking speed or walking conditions (walking on flat ground,slope assenting or slope descending), a set of experiments were carried out. The EMGfeature vector obtained from several different methods were used to recognize the walkingpattern. The weighted distance was employed as the index to assign a EMG pattern toclassified locomotion. The recognition results show that the prospect of application of thefeature vector is attractive.