The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

Activity Type Detection Of Random Forest Model Using UWB Radar And Indoor Environmental Measurement Sensor

UWB 레이더와 실내 환경 측정 센서를 이용한 랜덤 포레스트 모델의 재실활동 유형 감지

  • 박진수 (한국전자기술연구원 스마트가전혁신지원센터) ;
  • 정지성 (한국전자기술연구원 스마트가전혁신지원센터) ;
  • 양철승 (한국전자기술연구원 스마트가전혁신지원센터) ;
  • 이정기 (한국전자기술연구원 스마트가전혁신지원센터)
  • Received : 2022.10.21
  • Accepted : 2022.11.08
  • Published : 2022.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

As the world becomes an aging society due to a decrease in the birth rate and an increase in life expectancy, a system for health management of the elderly population is needed. Among them, various studies on occupancy and activity types are being conducted for smart home care services for indoor health management. In this paper, we propose a random forest model that classifies activity type as well as occupancy status through indoor temperature and humidity, CO2, fine dust values and UWB radar positioning for smart home care service. The experiment measures indoor environment and occupant positioning data at 2-second intervals using three sensors that measure indoor temperature and humidity, CO2, and fine dust and two UWB radars. The measured data is divided into 80% training set data and 20% test set data after correcting outliers and missing values, and the random forest model is applied to evaluate the list of important variables, accuracy, sensitivity, and specificity.

본 세계적으로 출생률이 줄고 기대 수명이 늘어나 고령화 사회가 되어감에 따라 고령 인구의 건강 관리를 위한 시스템이 필요하다. 그 중 실내 건강 관리를 위한 스마트 홈 캐어 서비스를 위해서는 재실 여부 및 활동 유형에 관한 다양한 연구가 수행되고 있다. 본 논문에서는 스마트 홈 캐어 서비스를 위해 실내 온습도, CO2, 미세먼지 값과UWB 레이더 측위를 통해 재실 여부 뿐만 아니라 활동 유형을 분류하는 랜덤 포레스트 모델을 제안한다. 실험은 실내 온습도, CO2, 미세먼지를 측정하는 센서 3개와 UWB Radar 2개를 사용하여 2초 간격으로 실내 환경 및 재실자의 측위 데이터를 측정한다. 측정된 데이터는 이상치와 결측치를 보정 처리한 후 80%의 트레이닝 셋 데이터와 20%의 테스트 셋 데이터로 이분하며 랜덤 포레스트 모델을 적용하여 중요도 상위 변수 목록, 정확도, 민감도, 특이도, T1 스코어를 평가한다.

Keywords

Acknowledgement

본 연구는 국토교통부의 국토교통기술사업화지원사업의 연구비지원에 의해 수행되었음 [과제명 : 비접촉 생체정보 측정기능이 포함된 스마트 디퓨저 기반 거주자 맞춤형 Home-HAS(Health, Air, Safety) 서비스 개발] [과제번호 : 21TBIP-C161696-01].

References

  1. Hwang, Jung-Hyun..An Analysis of the Research and Policy on the Smart Home Design for the Elderly based on the U-Healthcare.JOURNAL OF THE ARCHITECTURAL INSTITUTE OF KOREA Planning & Design,31(4),53-60, 2015. DOI:10.5659/JAIK_PD.2015.31.4.53
  2. Weon, Dal Soo, Lee, Sang San, and Jung, Yong Gyu, "Global Convergence for Healthcare ICT Services," The journal of the convergence on culture technology, vol. 2, no. 2, pp. 45-49, May 2016. DOI:10.17703/JCCT.2016.2.2.45
  3. MARTIN, Suzanne, et al. Smart home technologies for health and social care support. Cochrane database of systematic reviews, 2008, 4. DOI: 10.1002/14651858.CD006412.pub2
  4. Sung Hoon Yoon and Kil Soo Lee "Indoor Surveillance Camera based Human Centric Lighting Control for Smart Building Lighting Management," The International Journal of Advanced Culture Technology (IJACT), Vol.8 No.1 pp. 207-212, 2020. DOI:10.17703/IJACT.2020.8.1.207
  5. F. Wahl, M. Milenkovic, and O. Amft, "Adistributed PIR-based approach for estimating people count in office environments", IEEE 15th International Conference on Computational Science and Engineering, pp. 640-647, 2012.DOI: 10.1109/ICCSE.2012.92
  6. SLOBOGIN, Christopher. Public privacy: camera surveillance of public places and the right to anonymity. Miss. lJ, 2002, 72: 213. DOI:10.2139/ssrn.364600
  7. S. S. Leea, C. Choia, and M. Kim, "CNN-based People Recognition for Vision Occupancy Sensors". Journal of Broadcast Engineering, Vol. 23, no. 2, pp. 274-282, 2018. DOI:10.5909/JBE.2018.23.2.274
  8. BIAU, Gerard; SCORNET, Erwan. A randomforest guided tour. Test, 2016, 25.2: 197-227. DOI:10.48550/arXiv.1511.05741
  9. J. D. Suh, "Foreign Exchange Rate Forecasting Using the GARCH extended Random Forest Model", Journal of Industrial Economics and Business, Vol. 29, no. 5, pp. 1607-1628, 2016.
  10. A. M. Prasad, L. R. Iverson, and A. Liaw, "Newer classification and regression tree techniques: bagging and random forests for ecological prediction," Ecosystems, Vol. 9, pp. 181-199, 2006. DOI:10.1007/s10021-005-0054-1
  11. YU, Yong, et al. A review of recurrent neural networks: LSTM cells and network architectures. Neural computation, 2019, 31.7: 1235-1270. DOI:10.1162/neco_a_01199
  12. DEY, Rahul; SALEM, Fathi M. Gate-variants of gated recurrent unit (GRU) neural networks. In: 2017 IEEE 60th international midwest symposium on circuits and systems (MWSCAS). IEEE, 2017. p. 1597-1600. DOI:10.1109/MWSCAS.2017.8053243
  13. TEBALDI, Claudia; KNUTTI, Reto. The use of the multi-model ensemble in probabilistic climate projections. Philosophical transactions of the royal society A: mathematical, physical and engineering sciences, 2007, 365.1857: 2053-2075. DOI:10.1098/rsta.2007.2076