본문 바로가기
  • Home

Abnormal Situation Detection Algorithm via Sensors Fusion from One Person Households

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2022, 27(4), pp.111-118
  • DOI : 10.9708/jksci.2022.27.04.111
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science
  • Received : March 24, 2022
  • Accepted : April 21, 2022
  • Published : April 29, 2022

Da-hyeon Kim 1 Jun-ho Ahn 1

1한국교통대학교

Accredited

ABSTRACT

In recent years, the number of single-person elderly households has increased, but when an emergency situation occurs inside the house in the case of single-person households, it is difficult to inform the outside world. Various smart home solutions have been proposed to detect emergency situations in single-person households, but it is difficult to use video media such as home CCTV, which has problems in the privacy area. Furthermore, if only a single sensor is used to analyze the abnormal situation of the elderly in the house, accurate situational analysis is limited due to the constraint of data amount. In this paper, therefore, we propose an algorithm of abnormal situation detection fusion inside the house by fusing 2DLiDAR, dust, and voice sensors, which are closely related to everyday life while protecting privacy, based on their correlations. Moreover, this paper proves the algorithm’s reliability through data collected in a real-world environment. Adnormal situations that are detectable and undetectable by the proposed algorithm are presented. This study focuses on the detection of adnormal situations in the house and will be helpful in the lives of single-household users.

Citation status

* References for papers published after 2023 are currently being built.

This paper was written with support from the National Research Foundation of Korea.