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 an AIDA(Automatic Incident Detection Algorithm) for Uninterrupted Flow Based on the Concept of Short-term Displaced Flow

연속류도로 단기 적체 교통량 개념 기반 돌발상황 자동감지 알고리즘 개발

  • 이규순 ((주)동림TNS 교통계획부) ;
  • 신치현 (경기대학교 도시.교통공학과)
  • Received : 2015.10.30
  • Accepted : 2016.04.07
  • Published : 2016.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Many traffic centers are highly hesitant in employing existing Automatic Incident Detection Algorithms due to high false alarm rate, low detection rate, and enormous effort taken in maintaining algorithm parameters, together with complex algorithm structure and filtering/smoothing process. Concerns grow over the situation particularly in Freeway Incident Management Area This study proposes a new algorithm and introduces a novel concept, the Displaced Flow Index (DiFI) which is similar to a product of relative speed and relative occupancy for every execution period. The algorithm structure is very simple, also easy to understand with minimum parameters, and could use raw data without any additional pre-processing. To evaluate the performance of the DiFI algorithm, validation test on the algorithm has been conducted using detector data taken from Naebu Expressway in Seoul and following transferability tests with Gyeongbu Expressway detector data. Performance test has utilized many indices such as DR, FAR, MTTD (Mean Time To Detect), CR (Classification Rate), CI (Composite Index) and PI (Performance Index). It was found that the DR is up to 100%, the MTTD is a little over 1.0 minutes, and the FAR is as low as 2.99%. This newly designed algorithm seems promising and outperformed SAO and most popular AIDAs such as APID and DELOS, and showed the best performance in every category.

기존의 많은 돌발상황 자동감지 알고리즘은 복잡한 구조와 계산 과정, 수많은 매개변수, 그리고 필터링/평활화 같은 선 작업 때문에 지속적인 유지관리가 사실상 중단된 상태이고 오보율 또한 높아 많은 교통관리센터로부터 기피 대상이 되고 있는 등 돌발상황감지의 주력 수단으로서 자동 알고리즘의 지위가 위태해진 현실은 매우 우려할만하다. 본 연구에서는 상대 점유율과 속도 항을 활용하여 적체 교통량이라는 신 개념을 도입, 구조가 아주 간단하면서도 검측 원시자료의 보정이 거의 필요 없는 DiFI(Displaced Flow Index) 기반의 돌발상황 자동감지알고리즘을 개발하였다. DiFI 알고리즘의 성능평가는 2003년도 내부순환로 검지기자료를 활용하여 검증을 수행하였으며, 2011년도 경부고속도로 검지기 자료를 수집 정리하여 이식성 검사를 이행하였다. 성능평가는 검지율, 오보율, 평균검지시간, 기타 CR, CI, PI를 사용하였는데 100%의 검지율과 2.99%의 낮은 오보율, 1분을 약간 초과하는 평균검지시간을 보였다. 이는 SAO는 물론 국내 현장에 가장 많이 접목된 APID 및 DELOS 등과 비교해서도 모든 면에서 우월한 성능을 보이는 것이었다.

Keywords

References

  1. Seo J.(2003), A Comparative Study of ILDs and VIPs as Data Collection Methods for Freeway Congestion Management, Master's Thesis, Kyonggi University.
  2. Kim S.(2004), A Study of FAR Reduction Methods for AIDAs by Adjusting Data Discrepancy Between Video Image Detector Stations, Master's Thesis, Kyonggi University.
  3. Dudek C., Messer C. and Nuckles N.(1974), "Incident Detection on Urban Freeways," TRR-495, pp. 12-24.
  4. Payne H. and Tignor S.(1978), "Freeway Incident-Detection Algorithms Based on Decision Trees with States," TRR-682, pp. 30-37.
  5. Levin M. and Krause G.(1978), "Incident Detection: A Bayesian Approach," TRR-682, pp. 52-58.
  6. Cook A. and Cleveland D.(1974), "Detection of Freeway Capacity-Reducing Incidents by Traffic- Stream Measurements," TRR-495, pp 1-11.
  7. Chow E. et. al.(1977), Dynamic Detection and Identification of Incidents on Freeways Volume !: Summary, ESL-R-764 EE Lab., MIT.
  8. Persaud B., Hall F. and Hall L.(1990), "Congestion Identification Aspects of the McMaster Incident Detection Algorithm," TRR-1287, pp. 167-175.
  9. Dudek C., Weaver G., Ritch G. and Messer C.(1975), "Detecting Freeway Incidents under Low-volume Conditions," TRR-533, pp. 34-43.
  10. Lin W. and Daganzo C.(1997), "A Simple Detection Scheme for Delay-inducing Freeway Incidents," Transportation Research 31A(2), pp. 141-155.
  11. Ozbay K. and Kachroo P.(1999), Incident Management in Intelligent Transportation Systems, Artech House.
  12. Stephanedes Y. and Chassiakos A.(1993), "Freeway Incident Detection Through Filtering," Transp. Research-C, vol. 1, no. 3, Pergamon, pp 219-233. https://doi.org/10.1016/0968-090X(93)90024-A
  13. FHWA(1996), Traffic Control Systems Handbook, USDOT.
  14. FHWA(1997), Freeway Management Handbook, USDOT.
  15. Kim S. and Kim Y.(2008), "Development and Evaluation of AIDA Using Modified Flow- Occupancy Diagram," Journal of Korean Society of Transportation, vol. 26, no. 4, pp. 229-239.
  16. Choi J., Shin C. and Kang S.(2012), "Development of an AIDA for Uninterrupted Flow by Diminishing the Random Noise Effect of Traffic Detector Variables," Journal of the Korea Institute of ITS, vol. 11, no. 2. pp. 29-38.
  17. Chen S., Wang W. and Zuylen H.(2009), "Construct Support Vector Machine Ensemble to Detect Traffic Incident," Expert Systems with Application, vol. 36, Issue 8, pp.10976-10986. https://doi.org/10.1016/j.eswa.2009.02.039
  18. Brumback T., Fonseca D. and Moynihan G.(2011), " A Mathematical Model for Freeway Incident Detection and Characterization: a Fuzzy approach," IJDS, vol. 2, no. 1. pp. 1-16.