The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Development of Incident Detection Algorithm Using Naive Bayes Classification

나이브 베이즈 분류기를 이용한 돌발상황 검지 알고리즘 개발

  • 강성관 (한국도로공사 건설처) ;
  • 권봉경 (한국도로공사 해외사업처) ;
  • 권철우 (아주대학교 건설교통공학과) ;
  • 박상민 (아주대학교 건설교통공학과) ;
  • 윤일수 (아주대학교 교통시스템공학과)
  • Received : 2018.08.28
  • Accepted : 2018.11.07
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study is to develop an efficient incident detection algorithm by applying machine learning, which is being widely used in the transport sector. As a first step, network of the target site was constructed with micro-simulation model. Secondly, data has been collected under various incident scenarios produced with combination of variables that are expected to affect the incident situation. And, detection results from both McMaster algorithm, a well known incident detection algorithm, and the Naive Bayes algorithm, developed in this study, were compared. As a result of comparison, Naive Bayes algorithm showed less negative effect and better detect rate (DR) than the McMaster algorithm. However, as DR increases, so did false alarm rate (FAR). Also, while McMaster algorithm detected in four cycles, Naive Bayes algorithm determine the situation with just one cycle, which increases DR but also seems to have increased FAR. Consequently it has been identified that the Naive Bayes algorithm has a great potential in traffic incident detection.

본 연구에서는 최근 활발하게 활용되고 있는 머신러닝 기법을 교통분야에 적용하여 효율적인 돌발상황 검지 알고리즘을 개발하는 것을 목적으로 하였다. 미시교통시뮬레이션 모형을 통하여 대상지의 네트워크를 구축하였고 돌발상황에 영향을 줄 것으로 예상되는 변수의 여러 조합을 통해 시나리오를 설정하여 가상의 돌발상황 데이터를 수집하였다. 다음으로 대표적인 돌발상황 검지 알고리즘인 McMaster 알고리즘과 본 연구에서 개발한 나이브 베이즈 분류기를 구현하여 비교 평가하였다. 비교 결과, 나이브 베이즈 분류기가 McMaster 알고리즘에 비해 돌발상황 검지 간격에 따른 부정적인 영향이 적었고 더 우수한 검지율을 보였다. 하지만 검지율이 증가하는 만큼 오검지율 또한 증가하는 것을 확인할 수 있었다. McMaster 알고리즘은 4주기를 통해 검지가 가능하지만 나이브 베이즈 분류기는 1주기(30초)만으로 돌발상황을 판단할 수 있다. 본 연구를 통해 개발한 나이브 베이즈 분류기가 효율적으로 돌발을 파악할 수 있다는 것을 확인할 수 있었다.

Keywords

References

  1. Cho S. J. and Kang S. H.(2016), "Industrial Applications of Machine Learning," Industrial Engineering Magazine, vol. 23, no. 2, pp.34-38.
  2. Cho Y. T.(2016), Development of an Estimating Method for the Parameters of Volume Delay Functions Using a Genetic Algorithm, Doctoral thesis, Ajou University.
  3. Gailbo, http://www.gailbo.com, 2018.07.21.
  4. Deniz O. and Celikoglu H. B.(2011), "Overview to some existing incident detection algorithms: a comparative evaluation," Procedia-Social and Behavioral Sciences, vol. 2, pp.153-168.
  5. Hall F. L., Shi Y. and Atala G.(1991), "On-Line Testing of the McMaster Incident Detection Algorithm Under Recurrent Congestion," Transportation Research Record, no. 1394, pp.1-7.
  6. Jang M. S.(2018), Classifier Integration Model with Naive Bayes Classifier, Master thesis, Myongji University.
  7. Jeong H. R.(2018), Study on Prediction of Severities of Rental Car Traffic Accidents Using Ordinal Logit Model and Naive Bayes Classifier, Master thesis, Ajou University.
  8. Kim S. G. and Kim Y. C.(2006), "Development of Incident Detection Algorithm Using Speed-Occupancy Relationship," Seoul City Studies, vol. 7 no. 3, pp.235-249.
  9. Kim S. G., Kim C. H. and Kim Y. C.(2008), "A Sensitivity Test of McMaster Algorithm Depending on the Changes in Parameter Values," Seoul City Studies, vol. 9, no. 2, pp.121-131.
  10. Kim S. H.(1999), "A Development of Neural Networks-based Incident Detection Model," Journal of Engineering & Technology, Hanyang University, vol. 8, no. 1, pp.187-196.
  11. Kim S. H., Kim J. H., Doo M. S., Byun W. H., Sin A. G., Yun Y. H., Lee Y. T., Lee J. B. and Chun S. H.(2016), Road Traffic ITS Theory and Design, Cheongmoongak, pp.108-109.
  12. Ko S. G., Kwon C. W., Kim T. S., Cho W. S. and Yun I. S.(2017), "Study on Performance Evaluation of Magnetometer Detectors," Journal of The Korea Institute of Intelligent Transport Systems, vol. 2017, no. 10, pp.63-67.
  13. Korea Road Traffic Authority(2018), Traffic accident statistics.
  14. Korea Transport Institute(2010), Study on the Collection and Provision of Traffic Information on Highway.
  15. KOROAD(2014), "Central Traffic Information Center Traffic Information," KOROAD Traffic Science Institute, pp.8-17.
  16. Lee D. H.(2017), A study on Hotspot Identification using Machine Learning, Master thesis, University of Seoul.
  17. Lee J., Kim B. K. and Kim S. H.(2000), "A Study on the Application of the Interrupted Traffic Flow Incident Detection Algorithm using Fixed Detector," Journal of Korean society of Transportation, vol. 4, pp.33-36.
  18. Lee S. H. and Kang H. C.(2003), "Development and Evaluation of New Incident Detection Algorithm," Journal of Korean society of Transportation, vol. 44, pp.1-6.
  19. Mak C. L. and Fan H. S.(2005), "Transferability of expressway incident detection algorithms to Singapore and Melbourne," Journal of transportation engineering, vol. 131, no. 2, pp.101-111. https://doi.org/10.1061/(ASCE)0733-947X(2005)131:2(101)
  20. Philip H. M., Joseph K. L. and Kam W.(1991), "Incident Detection Algorithms for COMPASS An Advanced Traffic Management System," Vehicle Navigation and Information Systems Conference, vol. 2, pp.295-310.
  21. Rakha H., Hellinga B. and Van Aerde M.(1999), "Testbed for Evaluating Automatic Incident Detection Algorithms," In Intelligent Transportation System Safety and Security Conference.
  22. Sun D., Zhang C., Zhao M., Zheng L., Liu W.(2017), "Traffic Congestion Pattern Detection Using an Improved McMaster Algorithm," 2017 29th Chinese Control And Decision Conference, pp.2814-2819.
  23. Yang C., Miao Z. and Dongyuan Y.(2015), "Automatic Incident Detection for Urban Expressways Based on Segment Traffic Flow Density," Journal of Intelligent Transportation Systems, vol. 19, pp.205-213. https://doi.org/10.1080/15472450.2014.977046
  24. Yun I. S., Han E., Lee C. K., Rho J. H., Lee S. J. and Kim S. B.(2013), "Mobility and Safety Evaluation Methodology for the Locations of Hi-PASS Lanes Using a Microscopic Traffic Simulation Tool," The Journal of the Korea Institute of Intelligent Transport Systems, vol. 12, no. 1, pp.98-108. https://doi.org/10.12815/kits.2013.12.1.098

Cited by

  1. Automatic Classification Model of Electronic Documents Based on Machine Learning for Job Analysis vol.17, pp.7, 2018, https://doi.org/10.14801/jkiit.2019.17.7.23
  2. SNS 기반 여론 감성 분석 vol.6, pp.1, 2018, https://doi.org/10.17703/jcct.2020.6.1.111
  3. IDM을 이용한 자율주행자동차 시장점유율 변화가 고속도로 교통류에 미치는 영향 분석 vol.20, pp.4, 2018, https://doi.org/10.12815/kits.2021.20.4.13