Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Deep learning based optimal evacuation route guidance system in case of structure fire disaster

딥러닝 기반의 구조물 화재 재난 시 최적 대피로 안내 시스템

  • Lim, Jae Don (Department of Computer Engineering, Paichai University) ;
  • Kim, Jung Jip (Department of Computer Engineering, Paichai University) ;
  • Hong, Dueui (Department of Computer Engineering, Paichai University) ;
  • Jung, Hoekyung (Department of Computer Engineering, Paichai University)
  • Received : 2019.08.31
  • Accepted : 2019.09.20
  • Published : 2019.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

In case of fire in a structure, it is difficult to suppress fire because it can not accurately grasp the location of fire in case of fire. In this paper, we propose a system algorithm that can guide the optimal evacuation route in case of deep learning-based (RNN) structure disaster. The present invention provides a service to transmit data detected by sensors to a server in real time by using installed sensor, to transmit and analyze information such as temperature, heat, smoke, toxic gas around the sensor, to identify the safest moving path within a set threshold, to transmit information to LED guide lights and direction indicators in a structure in real time to avoid risk factors. This is because the information of temperature, heat, smoke, and toxic gas in each area of the structure can be grasped, and it is considered that the optimal evacuation route can be guided in case of structure disaster.

구조물에서 화재 발생 시 화재의 발생 위치를 정확하게 파악하지 못해 화재 진압이 용이하지 못하는 문제, 연기나 유독가스로 시야 확보가 어려운 상태에서 비상구 및 탈출로에 대한 정보를 방향지시기와 LED 유도등에 의존하여 위험에 빠지는 문제가 빈번히 발생하고 있다. 이에 본 논문에서는 딥러닝 기반(RNN) 구조물 재난 시 최적의 대피로를 안내할 수 있는 시스템 알고리즘을 제시한다. 설치되어 있는 감지 센서를 이용하고, 센서별 검출된 데이터를 서버로 실시간 전송되며, 감지 센서 주변의 온도, 열, 연기, 유독가스 등의 정보가 전달된다. 그리고 이를 분석하고, 설정된 임계치 범위 내에 있는 가장 안전한 이동 경로를 파한다. 이때 구조물 내에 있는 LED 유도등과 방향지시기에 실시간으로 정보를 전달하여 위험 요소를 피할 수 있는 서비스를 제공해 준다. 이는 구조물의 각 구역별 온도, 열, 연기, 유독가스의 정보를 파악할 수 있어, 구조물 재난 시 최적의 대피로를 안내받을 수 있을 것이라고 사료된다.

Keywords

Acknowledgement

This work(Grants No. S2651789) was supported by project for Cooperative R&D between Industry, Academy, and Research Institute funded Korea Ministry of SMEs and Startups in 2018.

References

  1. Y.H. Shin, J.S. Yun, S.H. Seo, and J.M. Chung "Deployment of Network Resources for Enhancement of Disaster Response Capabilities with Deep Learning and Augmented Reality," Journal of Internet Computing and Services, vol.18, no.5, pp. 69-77, 2017. https://doi.org/10.7472/jksii.2017.18.5.69
  2. H.J. Jang, E.S. Kim, and J.Y. Park. "Development and Evaluation of Portable Multiple Gas Meter," The Korea Academia-Industrial cooperation Society, vol. 20, no. 3, pp. 483-490, 2019.
  3. H.S. Lee, and G .H. Shin, "Fire Prevention and Status for the People Safety," Korean Journal of Security Convergence Management, vol. 4 no. 1, pp. 59-72, Jun. 2015. https://doi.org/10.24826/KOSSCOM.4.1.4
  4. Y.J. Kim, and E.K. Kim, "Real-time fire detection based on CNN and Grad-CAM," The Korea Institute of Information and Communication Engineering, vol. 22, no. 12, pp. 1596-1603, 2018.
  5. N. M. Dung, and S.H. RO, "Smoke Detection Algorithm Using Deep Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 42, no.7, pp. 1370-1379, 2017. https://doi.org/10.7840/kics.2017.42.7.1370
  6. J.D. Lim, J.J. Kim, D.E. Hong, and H.K. Jung, "Safety Monitoring System of Structures using MEMS Sensor," Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 10, pp.1307-1313, 2018. https://doi.org/10.6109/JKIICE.2018.22.10.1307
  7. H.T. Cho, S.A, Lee, and S.W. Kang, "A Code Recommendation Method Using RNN Based on Interaction History," Korea Information Processing Society, vol.7, no.12, pp. 461-468, 2018.
  8. X. Yang, J. S. Lee, and H. K. Jung, "Fault diagnosis Management Model using Machine Learning," Journal of information and communication convergence engineering, vol. 17. no. 2, pp. 128-134, 2019. https://doi.org/10.6109/JICCE.2019.17.2.128