Journal of Korean Society of Transportation (대한교통학회지)

Korean Society of Transportation (대한교통학회)
권호 표지

Development of a Fuzzy-Genetic Algorithm-based Incident Detection Model with Self-adaptation Capability

Fuzzy-Genetic Algorithm기반의 자가적응형 돌발상황 검지모형 개발 연구

  • 이시복 (영산대학교 교통물류시스템학과) ;
  • 김영호 (영산대학교 교통물류시스템학과)
  • Published : 2004.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study utilizes the fuzzy logic and genetic algorithm to improve the existing incident detection models by addressing the problems associated with "crisp" thresholds and model transferability (applicability). The model's major components were designed to be a set of the fuzzy inference engines, and for the self-adaptation capability the genetic algorithm was introduced in optimization(or training) of the fuzzy membership functions. This approach is often called "the hybrid of fuzzy-genetic algorithm" The model performance was tested and found to be compatible with that of the existing well-recognized models in terms of performance measures such as detection rate, false alarm rate, and detection time. This study was not an effort for simple improvement of the model performance, but an experimental attempt to incorporate new characteristics essential for the incident detection model to be universally applicable for various roadway and traffic conditions. The study results prove that the initial objective of the study was satisfied, and suggest a direction that the future research work in this area must follow.

본 연구에서는 기존의 돌발상황 검지모형의 단점인 crisp한 임계값 설정과 타 대상도로에 이식이 어려운 문제점을 보완하는 방법으로 퍼지추론모형과 유전자 알고리즘을 활용하였다. 퍼지추론모형을 이용하여 유고검지 알고리즘의 주요 구성요소들을 설계하였으며, 돌발상황 검지모형 스스로의 적응력(자가적응)과 현장 이식성(移植性)을 극대화하기 위하여 퍼지추론모형의 퍼지소속함수 최적화에 유전자 알고리즘을 적용함으로써 hybrid fuzzy-genetic 형태의 유고검지모형을 개발하였다. 개발된 돌발상황검지모형의 성능은 유전자 알고리즘의 특성상 적응이력과 비례하여 향상될 것이므로 본 연구의 결과만을 가지고 확정적 결론을 내릴 수는 없으나, 잠정적으로 검지율, 오보율, 검지시간 등의 척도에서 기존 성능우수 모형과 대등한 성능을 나타내었다. 본 연구의 초점이 기존 모형의 성능지표 자체의 향상보다는 다양한 도로유형에 공히 적용 가능한 동시에 자가 적응력을 갖도록 하는 실험적 시도에 있었던 만큼 연구는 소기의 성과를 거두었다고 판단되며, 향후 이 분야 연구가 지향해야 할 중요한 방향성 하나를 제시하였다고 판단된다.

Keywords

References

  1. Ahmed, S.A. and A.R. Cook(1982). 'Discrete Dynamic Models for Freeway Incident Detection Systems'. Transportation Planning and Technology, Vol.7, pp.231-242 https://doi.org/10.1080/03081068208717226
  2. Bell, M. G. H., and B 'Thancanamootoo(1988) Automatic Incident Detection Within Urban Traffic Control Systems. Proceedings of International Road and Traffic Conference Roads and Traffic 2000, Vol.4:2, pp.35-38
  3. Chen , C.-H., and G.-L. Chang(1993). 'A Dynamic Real-Time Incident Detection System For Urban Arterials: System Architecture and Preliminary Results'. Proceedings of Pacific Rim TransTech Conference , Vol. 1, Seattle, Washington. pp.98-104
  4. Cheu, R.L., S.G. Ritchie, W.W. Recker, and B. Bavrian(1991). 'Investigation of Neural Network Model for Freeway Incident Detection' Program on Advanced Technology for the Highway, Institute of Transportation Studies, University of California, Berkeley, California
  5. Elie Sanchez. Takanori Shibata, and Lotfi A. Zadeh (1997), 'Genetic Algorithms and Fuzzy Logic Systems', World Scientific
  6. Hall, F.L., Y. Shi, and G. Atala(1993). 'On-Line Testing of the McMaster Incident Detection Algorithm Under Recurrent Congestion'. Transportation Research Record 1394, TRB. National Research Council, Washington, D.C., pp.1-7
  7. Han, L.D.. and A. D. May(1989). 'Artificial Intelligence Approaches for Urban Network Incident Detection And Control'. Institute of Transportation Studies. University of California, Berkeley, California
  8. Hoose, N., M.-A. Vicencio, and X. Zhang (1992). 'Incident Detection in Urban Roads Using Computer Image Processing'. Traffic Engineering & Control. Vol.33, No.4, pp.236-244
  9. Ivan, J.N., J.L. Schofer, C.R. Bhat, P.-C. Liu, F.S. Koppelman, and A. Rodriguez (1993). 'Arterial Street Incident Detection Using Multiple Data Sources: Plans for ADVANCE'. Proceedings of Pacific Rim TransTech Conference. Vol.1. Seattle, Washington, pp.429-435
  10. Kaan Ozbay, and Pushkin Kachroo(1999), 'Incident Management in Intelligent Transportation Systems', Artech House
  11. Kevin N. Balke, P. E(1993), 'An Evaluation of Existing Incident Detection Algorithms', Research report 1232-20, Texas Transportation Institute
  12. Khan, S.I., and S.G. Ritchie(May 1994). 'Incident Detection on Surface Streets Using Artificial Neural Networks'. Proceedings of the Intl Conference on Advanced Technologies in Transportation and Traffic Management, Singapore, pp.261-268
  13. Levin, M. and G.M. Krause(1978). 'Incident Detection : A Bayesian Approach'. Transportation Research Record 682. TRB, National Research Council, Washington, D.C., pp.52-58
  14. Sellam, S., A. Boulmakoul, and J.C. Pierrelee (1991). 'A Distributed Real Time Knowledge-Based System Using Video Image Processing for Junctions Automatic Incident Detection'. Proceedings of the Second International Conference on Applications of Advanced Technologies in Transportation Engineering, American Society of Civil Engineers, New York, New York, pp.351-356
  15. Stephanedes. Y.J., and A. P. Chassiakos (1993). 'Smoothing Algorithms for Incident Detection'. Transportation Research Record 1394, TRB, National Research Council, Washington, D.C., pp.8-16
  16. Stephanedes, Y.J., and G. Vassilakis(1994). 'Intersection Incident Detection for IVHS' Paper submitted to 74th Annual Meeting of the Transportation Research Board, Washington, D.C.
  17. Zbigniew Michalewicz (1996), 'Genetic Algorithms + Data Structures = Evolution Programs', Springer
  18. 데이터사이언스(주)홈페이지 (http://datascience.co.kr/mining_how_gen.htm)
  19. Sibok Lee (1995), Fuzzy Logic Based Incident Detection for Paired Intersections. A doctoral dissertation, Texas A&M University
  20. 채석 . 오영석(1997), '퍼지이론과 제어', 청문각
  21. 장세봉(1997), '인공신경망을 이용한 고속도로 자동유고감지 모형의 개발', 박사학위논문, 서울대학교
  22. 이영인 . 황준환 (2001), '간선도로 돌발상황 검지기법 개발연구', 대한교통학회지, 제19권 제2호, 대한교통학회, pp.73-87
  23. 강진기(1994), '검지기 간격에 따른 돌발상황검지 알고리즘의 돌발상황겸지시간 분석에 관한 연구', 석사학위논문, 서울대학교
  24. 김영찬 . 엄성만(2004), '도시고속도로 비혼잡상황에서의 자동 돌발상황 감지 알고리즘 개발', 대한토목학회지, 제24권 제2D호, 대한토목학회, pp.167-173