Search

Design of Anti-fall Alarm for the Elderly Based on Three-axis Acceleration Sensor

Author(s)

Ma Dongling

Affiliation(s)

Higher Vocational and Technical College, Shanghai University of Engineering Science, Shanghai, China

Abstract

The safety of the elderly is a big problem in the aging society. The design of the elderly anti-fall alarm can effectively improve the safety of the elderly. For how to judge whether the elderly is falling or not, this design uses the method of nonlinear dynamics to analyze the acceleration data of the action. Nonlinear dynamics studies the qualitative and quantitative variation of various motion states of nonlinear dynamic systems, especially the complexity of the long-term evolution behavior of the system. Due to the influence of various nonlinear factors, the signal generated by the fall process is generally non-stationary, non-linear and non-Gaussian random signal. Aiming at the research purpose of this topic, this paper adopts the analysis method of symbol entropy to realize the accurate judgment of the threshold.

Keywords

Nonlinear Dynamics; Symbol Entropy; Threshold

References

[1] Kim H-G, Kim G Y, Kim J Y. Music Recommendation System Using Human Activity Recognition from Accelerometer Data [J]. IEEE Transactions on Consumer Electronics, 2019, 65(3):349-358. [2] Li H, Shrestha A, Heidari H, et al. A multisensory approach for remote health monitoring of older people [J]. IEEE Journal of Electromagnetics, RFand Microwaves in Medicine and Biology, 2018, 2(2):102-108. [3] Nguyen T D, Huh E-N, Park JH, et al. Performance analysis of data parallelism technique in machine learning for human activity recognition using LSTM [C]. Proceedings of the 11th IEEE International Conference on Cloud Computing Technology and Science, 2019:387-391. [4] He J, Zhang Z, Wang X, et al. A low power fall sensing technology based on FD-CNN [J]. IEEE Sensors Journal, 2019, 19(13):5110-5118.