Academy & Industry Research Collaboration Center (AIRCC)

Volume 9, Number 6, May 2019

Research on gait prediction based on LSTM

  Authors

Bofan Liang1 and Qili Chen1,2,3, 1Beijing Information Science and Technology University, China, 2Beijing University of Technology, China and 3Beijing Key Laboratory of Computational Intelligence and Intelligent System, China

  Abstract

With an aging population that continues to grow, the protection and assistance of the older persons has become a very important issue. Falls are the main safety problems of the elderly people, so it is very important to predict the falls. In this paper, a gait prediction method is proposed. Firstly, the lumbar posture of the human body is measured by the acceleration gyroscope as the gait feature, and then the gait is predicted by the LSTM network. The experimental results show that the RMSE between the gait trend predicted by the method and the actual gait trend can be reached a level of 0.06 ± 0.01. The proposed method can predict the gait trend well.

  Keywords

Elderly people fall, Acceleration gyro, Lumbar posture, Gait prediction, LSTM