Fire Science and Engineering (한국화재소방학회논문지)

Korean Institute of Fire Science and Engineering (한국화재소방학회)
권호 표지
DOI QR코드

DOI QR Code

Fire Risk Assessment Based on Weather Information Using Data Mining

데이터마이닝을 이용한 기상정보에 따른 화재 위험 평가

  • 류정우 ((주)세이프티아 기술연구소) ;
  • 권성필 (한국소방산업기술원 미래소방기술연구소)
  • Received : 2015.08.11
  • Accepted : 2015.08.24
  • Published : 2015.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

We propose a weather-related service for fire risk assessment in order to increase fire safety awareness in everyday life. The proposed service offers a fire risk assessment level according to weather forecasts and a degree of fire risk according to fire factors under certain weather conditions. In order to estimate the fire risk, we produced a risk matrix through data mining with a decision tree using investigation data and weather data. Through the proposed service, residents can calculate the degree of fire risk under certain weather conditions using the fire factors around them. In addition, they can choose from various solutions to reduce fire risk. In order to demonstrate the feasibility of the proposed services, we developed a system that offers the services. Whenever weather forecasting is carried out by the Korea Meteorological Administration, the system produces the fire risk assessment levels for seven major cities and nine provinces of South Korea in an online process, as well as the fire risk according to fire factors for the weather conditions in each region.

본 논문에서는 일상생활에서 화재에 대한 주민들의 경각심을 고취시킬 수 있도록 기상조건에 따른 화재위험을 평가할 수 있는 날씨 관련 서비스를 제안한다. 제안된 서비스는 기상예보에 따른 화재위험평가등급과 특정 기상조건에서 화재요인에 따른 화재위험도를 제공한다. 제안한 서비스에서는 데이터마이닝 기법인 의사결정트리를 이용하여 화재조사데이터와 관측된 기상데이터로부터 화재위험평가등급을 산출할 수 있는 화재 위험도 매트릭스를 생성한다. 주민들은 제안한 서비스를 통해 특정 기상조건에서 화재요인에 따라 화재위험도를 직접 평가할 수 있고, 화재위험도를 저감시킬 수 있는 예방책을 사용자가 선택할 수 있다. 제안한 서비스를 시스템화하여 서비스의 현실성을 확인하였다. 시스템은 온라인상에서 기상청의 기상예보가 갱신될 때마다 시도별로 기상예보에 따른 화재위험평가등급을 표시하고, 각 시도별로 해당 기상조건에서 화재요인에 따라 화재위험도를 평가할 수 있다.

Keywords

References

  1. Korea Meteorological Administration's Website, "http://kma.go.kr/HELP/basic/help_01_03.jsp" (2015).
  2. D. W. Song, K. S. Kim and S. K. Lee, "An Relational Analysis between Humidity, Temperature and Fire Occurrence using Public Data", Journal of Fire Science and Engineering, Vol. 28, No. 2, pp. 82-90 (2014).
  3. H. Tanskanen and A. Venӓlӓinen, "The Relationship between Fire Activity and Fire Weather Indices at Different Stages of the Growing Season in Finland", Boreal Environment Research, Vol. 13, No. 4, pp. 285-302 (2008).
  4. A. C. Carvalho, A. Carvlho, H. Martins, C. Marques, A. Rocha, C. Borrego and D. X. Viegas, "Fire Weather Risk Assessment Under Climate Change Using a Dynamical Downscaling Approach", Environmental Modelling & Software, Vol. 26, Issue 9, pp. 1123-1133 (2011). https://doi.org/10.1016/j.envsoft.2011.03.012
  5. L. K. C. Chau and R. T. Corlett, "Fire and Weather in Hong Kong", Proceeding of the 12th Conference on Fire and Forest Meteorology, pp. 442-452 (1993).
  6. M. Holmes, Y. Wang and I. Ziedins, "The Application of Data Mining and Statistical Techniques to Identify Patterns and Changes in Fire Events", Technical report, University of Auckland (2009).
  7. National Oceanic and Atmospheric Administration's Website, "http://www.srh.noaa.gov/ridge2/fire/" (2015).
  8. Ministry of Public Safety and Security, National Fire Data System's Website, "http://www.nfds.go.kr/index.jsf" (2015).
  9. X. Wu, V. Kumar, J. R. Quinlan, J. Ghosh, Q. Yang, H. Motoda, G. J. McLachlan, A. Ng, B. Liu, P. S. Yu, Z.-H. Zhou, M. Steinbach, D. J. Hand and D. Steinberg, "Top 10 Algorithms in Data Mining", Knowledge Information System, Vol. 14, Issue 1, pp. 1-37 (2008). https://doi.org/10.1007/s10115-007-0114-2
  10. J. R. Quinlan, "Generating Production Rules From Decision Tree", Proceedings of the 10th International Joint Conference on Artificial Intelligence, Vol. 1, pp. 304-307 (1987).
  11. J. W. Ryu, Y. J. Kim, E. J. Kim and M. W. Kim, "A Generation Method of a Fire Probability Prediction Model Based on Weather Forecast", Journal of KIISE: Computing Practices and Letters, Vol. 20, No. 2, pp. 68-79 (2014).
  12. Y. J. Kim, J. W. Ryu, W. M. Song and M. W. Kim, "Fire Probability Prediction Based on Weather Information Using Decision Tree", Journal of KIISE: Software and Applications, Vol. 40, No. 11, pp. 705-715 (2013).
  13. Korea Occupational Safety and Health Agency, "Accident Frequency Analysis (FTA ETA)", Occupational Safety and Health Training Institute, pp. 3-6 (2013).
  14. Y.-S. Kim, "The Study of Risk Matrix Development for Urban Metro EMU", Journal of the KOSOS, Vol. 26, No. 6, pp. 111-117 (2011).