Journal of Platform Technology

ICT Platform Society (ICT플랫폼학회)
권호 표지

Emergency vehicle priority signal system based on deep learning using acoustic data

음향 데이터를 활용한 딥러닝 기반 긴급차량 우선 신호 시스템

  • 이소연 (순천향대학교 일반대학원 소프트웨어융합학과) ;
  • 장재원 (대구가톨릭대학교 모바일소프트웨어전공) ;
  • 김대영 (순천향대학교 컴퓨터소프트웨어공학과)
  • Received : 2021.09.09
  • Accepted : 2021.09.27
  • Published : 2021.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In general, golden time refers to the most important time in the initial response to accidents such as saving lives or extinguishing fires. The golden time varies from disaster to disaster, but is aimed at five minutes in terms of fire and first aid. However, for the actual site, the average dispatch time for ambulances is 9 minutes and the average transfer time is 17.6 minutes, which is quite large compared to the golden time. There are various causes for this delay, but the main cause is traffic jams. In order to solve the problem, the government has established emergency car concession obligations and secured golden time to prioritize ambulances in places with the highest accident rate, but it is not a solution in rush hour when traffic is increasing rapidly. Therefore, this paper proposed a deep learning-based emergency vehicle priority signal system using collected sound data by installing sound sensors on traffic lights and conducted an experiment to classify frequency signals that differ depending on the distance of the emergency vehicle.

일반적으로 골든 타임은 인명 구조나 화재 진압 등의 사고 초기대응에 있어서 가장 중요한 시간을 의미한다. 골든 타임은 재난 상황별로 다르지만 화재나 구급에 있어서는 5분을 목표로 하고 있다. 하지만 실제 현장의 경우 구급차의 평균 출동 시간은 9분, 평균 이송 시간은 17.6분으로 골든 타임과 비교하여 상당히 큰 지연시간이 존재한다. 이러한 지연시간에는 다양한 원인이 존재하지만 가장 큰 원인은 교통체증이다. 해당 문제를 해결하기 위해 정부에서는 긴급 자동차 양보의무법 제정, 사고 발생률이 가장 높은 장소에 구급차 우선 배치 등을 골든 타임을 확보하고 있지만, 교통량이 빠른 속도로 증가하는 출퇴근 상황에서는 해결책이 되지 못하고 있다. 따라서 본 논문에서는 신호등에 사운드 센서를 설치하여 수집된 소리 데이터를 활용한 딥러닝 기반 긴급차량 우선 신호 시스템을 제안하고 긴급차량의 주파수 대역을 추출하고 거리에 따라 다르게 나타나는 진폭 신호를 분류하는 실험을 진행하였다.

Keywords

Acknowledgement

본 연구는 산업통상자원부와 한국산업기술진흥원이 지원하는 혁신조달 연계형 신기술사업화 사업으로 수행된 연구결과입니다(No. P0014176). 또한, 본 연구는 한국연구재단 4 단계 두뇌한국 21 사업(4 단계 BK21 사업)의 지원을 받아 작성되었습니다(No. 5199990914048).

References

  1. Eunjeong Ko, Junhan Cho, LEE. Jooyoung. " Study on Improving Operational Criteria of Preemption/Priority Signal Control for Emergency Vehicles." Journal of Korean Society of Transportation, Vol. 39, No. 3, pp. 299-311, 2021 https://doi.org/10.7470/jkst.2021.39.3.299
  2. Kyung-Hee Kang, Jin-Ok Han. "Analysis of response time for patient non-transport by 119 ambulance services." The Korean Journal of Emergency Medical Services, Vol. 22, No. 3, pp. 177-187, 2018 https://doi.org/10.14408/KJEMS.2018.22.3.177
  3. Juyoung Hwang, Nayoung Kim, Jinil Ha. "A Case Study of the Optimization of Ambulance Deployment and Relocation to Improve the Arrival Rate of Ambulances within Emergency Patients' Golden Time." Journal of The Korean Operations Research and Management Science Society, Vol. 37, No. 3, pp. 63-76, 2020
  4. DongHyeop Kim, JinTae Kim. "A Study of Current Status and Development Direction of Emergency Vehicle Preemption." Proc. of the KOR-KST Conference, Vol. 81, pp. 345-346, 2019
  5. Seungchun Han, Yonghyun Lee, Wongil Kim, Jeungshik Kangh, Gwanho Park, Taewoo Hwang. " A study on the effect evaluation of the centrally controlled emergency vehicle priority signal control system to secure the golden time," Proc. of the KOR-KST Conference, pp. 341-346, 2018.
  6. Son Ho Jun(2021). "Inspection system for arc welding defects by using audio data based on deep learning." Unpublished master's thesis, Pusan National University, Pusan.
  7. Sang Hoon Kang(2019). "A study on Deep-Learning based Hazardous Sound Detection System using Modified MFCC Robust to Noise and Background Sounds", Unpublished master's thesis, Hongik University, Seoul.
  8. SungHyun Park, Byeongyeon Lim, Hoekyung Jung, "CNN-Based Toxic Plant Identification System.", Journal of the Korea Institute of Information and Communication Engineering, Vol. 24, No. 8, pp. 993-998, 2020 https://doi.org/10.6109/JKIICE.2020.24.8.993
  9. Lee Jae-hyung, Sung-Tae Jeon, Eun-Young Choi, Min-YoungChoi, Seo-hyunJo, Se-woon Choe, "A Study on Cell Image Classification Algorithm with CNN", The Korea Institute of Information and Communication Engineering, Vol. 24, No. 2, pp. 228-230, 2020