Acceleration Feature Extraction of Human Body Based on Wearable Devices

Wearable devices used for human body monitoring has broad applications in smart home, sports, security and other fields. provide an extremely convenient way to collect a large amount of motion data. In this paper, the acceleration feature extraction method based on wearable is studied. Firstly, Butterworth filter Then, order ensure extracted value more accurately, it necessary remove abnormal data source. This paper combines Kalman algorithm with genetic use code parameters algorithm. We Standard Deviation (SD), Interval Peaks (IoP) Difference between Adjacent Troughs (DAPT) analyze seven kinds acceleration. At last, SisFall set, which globally available set study experiments, experiments verify effectiveness our method. Based simulation results, we can conclude that distinguish different activity clearly.