A Gait phase classification method for Stair walking using Feature Extraction and Muscle selection based on EMG Signals

摘要

The present invention relates to a method of classifying a walking step of a step based on an EMG signal, the method comprising the steps of: (a) extracting a training signal of an EMG signal of a plurality of muscles measured during an uphill and downhill walking, Generating a classifier for classifying the gait steps of the gait according to the characteristics; (b) receiving a test signal for an EMG signal of the muscle, testing the classifier to obtain a recognition rate, selecting a classifier according to the recognition rate, and selecting a classifier for each of the uphill and downhill walking; And (c) recognizing a walking step of the uphill or downhill walk with the selected classifier. By using the above-described method, the step-walks step can be more accurately classified by using the features and the muscles that have a high recognition rate for each of the walking steps and the downward walking steps, respectively.