Citation

Taghvaei S, Jahanandish MH, Kosuge K. Assist. Technol. 2016; 29(1): 19-27.

Copyright

(Copyright © 2016, Rehabilitation Engineering and Assistive Technology Society of North America, Publisher Informa - Taylor and Francis Group)

DOI

10.1080/10400435.2016.1174178

PMID

27450279

Abstract

Population aging of the societies requires providing the elderly with safe and dependable assistive technologies in daily life activities. Improving the fall detection algorithms can play a major role in achieving this goal. This paper proposes a real-time fall prediction algorithm based on the acquired visual data of a user with walking assistive system from a depth sensor. In the lack of a coupled dynamic model of the human and the assistive walker a hybrid "system identification-machine learning" approach is used. An auto regressive moving average (ARMA) model is fitted on the time-series walking data to forecast the upcoming states, and a hidden Markov model (HMM)-based classifier is built on the top of the ARMA model to predict falling in the upcoming time frames. The performance of the algorithm is evaluated through experiments with four subjects including an experienced physiotherapist while using a walker robot in five different falling scenarios; namely, fall forward, fall down, fall back, fall left, and fall right. The algorithm successfully predicts the fall with a rate of 84.72%.

Language: en