Frequency analysis of fall detection based on Android system

Siwei Li, Ruirui Yin, Jiang Yu, Yanchao Qiu, Hai Li

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

In order to solve a hot issue about the elderly fall, this paper designs a software algorithm system based on the frequency analysis. This software can judge whether the elderly fall down, so as to take subsequent rescue measures. The paper carries on the analysis from the frequency domain. By using the acceleration sensor to get the information of human body state continuously and with the aid of subsection processing, the software can determine whether the body is in a state of fall. The core of the frequency domain analysis method is to add window to data and use STFT. Because of the particularity of acceleration frequency in the process of the fall, the algorithm can be more accurate to judge whether the elderly fall down.

Original languageEnglish
Title of host publicationICEIEC 2016 - Proceedings of 2016 IEEE 6th International Conference on Electronics Information and Emergency Communication
EditorsVincent Tam, Li Wenzheng
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages186-189
Number of pages4
ISBN (Electronic)9781509019960
DOIs
Publication statusPublished - 12 Oct 2016
Event6th IEEE International Conference on Electronics Information and Emergency Communication, ICEIEC 2016 - Beijing, China
Duration: 17 Jun 201619 Jun 2016

Publication series

NameICEIEC 2016 - Proceedings of 2016 IEEE 6th International Conference on Electronics Information and Emergency Communication

Conference

Conference6th IEEE International Conference on Electronics Information and Emergency Communication, ICEIEC 2016
Country/TerritoryChina
CityBeijing
Period17/06/1619/06/16

Keywords

  • STFT
  • fall detection
  • the frequency analysis

Fingerprint

Dive into the research topics of 'Frequency analysis of fall detection based on Android system'. Together they form a unique fingerprint.

Cite this