1인가구에서 센서융합을 통한 이상상황탐지 알고리즘
Abnormal Situation Detection Algorithm via Sensors Fusion from One Person Households
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
최근 1인 고령 가구가 증가하고 있지만 1인 가구의 경우 집 안에서 위험 상황이 발생했을 때, 이를 외부에 알리기 힘들다. 이와 같은 1인 가구의 위험 상황을 탐지하기 위해 다양한 스마트홈솔루션이 제안되고 있지만, 프라이버시 영역에 문제가 있는 홈 CCTV와 같은 영상 매체는 활용어렵다. 그리고 단일 센서만을 활용하여 집안 내 고령자의 위험 상황을 분석할 경우, 데이터양의한계로 정확한 상황해석이 제한 된다. 따라서 본 논문에서는 프라이버시를 지킬 수 있으며 실생활에 밀접한 2DLiDAR, 먼지, 음성 센서 간의 상관관계 따른 융합을 통한 집 내부의 위험 상황 탐지 융합 알고리즘을 제안한다. 또한, 본 논문은 실제 환경에서 수집한 데이터를 통해 알고리즘의신뢰성을 증명한다. 제안하는 알고리즘이 탐지 가능한 위험 상황과 불가능한 상황을 제시한다. 본논문은 집 안에서 위험 상황을 탐지하는 연구로써 1인 가구 사용자의 생활에 도움이 될 것이다.
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.
참고문헌 (19)
- "2020 Population Housing Survey Sample Results Furniture and Housing Characteristics Item Press Release"[URL]
- "Smartly Prevent Lonely Deaths from Living Alone"[URL]
- "Check with Smart Sensor for Elderly Living Alone"[URL]
- "Status of Support for Elderly People Using ICT Technology in Major Foreign Countries"[URL]
- G. M. Youngblood, "Data Mining for Hierarchical Model Creation", IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 37(4), pp.561~572 (2007)[DOI]
- M. Skubic, "A smart home application to eldercare: current status and lessons learned", IOS Press on Technology and Health Care, 17(3), pp.183~201 (2009)[DOI]
- M. Yu, "A Posture Recognition-Based Fall Detection System for Monitoring an Elderly Person in a Smart Home Environment", IEEE Transactions on Information Technology in Biomedicine, 16(6), pp.1274~1286 (2012)[DOI]
- H. Medjahed, "A pervasive multi-sensor data fusion for smart home healthcare monitoring", 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011), pp.1466~1473 (2011)
- L. Hyunsoo, "Scenario-Based Smart Services for Single-Person Households", Indoor and Built Environment, 22(1), pp.309~318 (2012)[DOI]
- K. Jinwoo, "Occupant behavior monitoring and emergency event detection in single-person households using deep learning-based sound recognition", Building and Environment, 181, pp.107092~ (2020)[DOI]
- A. Junho, "myBlackBox: Blackbox Mobile Cloud Systems for Personalized Unusual Event Detection", Sensors, 16(5), pp.753~ (2016)[DOI]
- H. F. Nweke, "Data fusion and multiple classifier systems for human activity detection and health monitoring: Review and open research directions", Information Fusion, 46, pp.147~170 (2019)[DOI]
- 김다현, "스마트 홈 사용자를 위한 라이다, 영상, 오디오 센서를 이용한 인공지능 이상징후 탐지 알고리즘", 인터넷정보학회논문지, 22(3), pp.17~26 (2021), 한국인터넷정보학회
- G. Anitha, "Posture based health monitoring and unusual behavior recognition system for elderly using dynamic Bayesian network", Cluster Computing, pp.1~8 (2018)[DOI]
- S. Kohlbrecher, "A flexible and scalable SLAM system with full 3D motion estimation", 2011IEEE International Symposium on Safety, Security, and Rescue Robotics, pp.155~160 (2011)
- "Librosa"[URL]
- "YDLiDAR"[URL]
- "Emergency Voice and Sound Introduction"[URL]
- "The Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS)"[URL]