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 Vehicle Queue Length Estimation Model Using Deep Learning

딥러닝을 활용한 차량대기길이 추정모형 개발

  • Lee, Yong-Ju (Dept. of Transportation Research Institute, Univ. of Ajou) ;
  • Hwang, Jae-Seong (Dept. of Construction and Transportation Eng., Univ. of Ajou) ;
  • Kim, Soo-Hee (Dept. of Research Institute, Korea Expressway Corporation) ;
  • Lee, Choul-Ki (Dept. of Transportation System Eng., Univ. of Ajou)
  • 이용주 (아주대학교 교통연구센터) ;
  • 황재성 (아주대학교 건설교통공학과) ;
  • 김수희 (한국도로공사 도로교통연구원) ;
  • 이철기 (아주대학교 교통시스템공학과)
  • Received : 2018.02.21
  • Accepted : 2018.04.02
  • Published : 2018.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study was to construct an artificial intelligence model that learns and estimates the relationship between vehicle queue length and link travel time in urban areas. The vehicle queue length estimation model is modeled by three models. First of all, classify whether vehicle queue is a link overflow and estimate the vehicle queue length in the link overflow and non-overflow situations. Deep learning model is implemented as Tensorflow. All models are based DNN structure, and network structure which shows minimum error after learning and testing is selected by diversifying hidden layer and node number. The accuracy of the vehicle queue link overflow classification model was 98%, and the error of the vehicle queue estimation model in case of non-overflow and overflow situation was less than 15% and less than 5%, respectively. The average error per link was about 12%. Compared with the detecting data-based method, the error was reduced by about 39%.

본 연구는 교통운영 개선에 필요한 빅데이터 및 인공지능 모델 개발의 일환으로서, 도시부의 링크통행시간 및 통과교통량 등 가용 데이터 등을 이용하여 교통변수로 활용도가 높은 차량대기길이와의 관계를 딥러닝(Deep Learning)을 통해 학습하고 추정하는 인공지능 모델을 구축하는 것을 목표로 하였다. 차량대기길이 추정모형은 데이터 분석결과를 토대로 하여 우선 차량대기길이의 링크 초과여부를 분류한 후 링크 초과 및 링크 미초과 상황에서의 차량대기길이 추정하는 3개의 모형으로 모델링하였다. 딥러닝 모형은 텐서플로우로 구현하였으며, 모든 모형은 DNN 구조로서 은닉층과 노드 개수를 다양화하여 학습 및 테스트 후 최소 오차를 나타내는 네트워크 구조를 선정하였다. 차량대기길이 링크 초과여부 분류 모형은 약 98%의 정확도를 나타냈으며, 미초과 모형은 15% 미만, 초과 모형은 5% 미만의 오차를 각각 나타내었다. 링크별 평균 오차는 12%로 도출되었다. 이를 기존 검지기 데이터 기반의 방식과 비교한 결과 오차가 약 39% 감소된 것으로 분석되었다.

Keywords

References

  1. Allsop R. E.(1972), "Delay at a Fixed Time Traffic Signal-Theoretical Analyses," Transportation Science, vol. 6, no. 3, pp.260-285. https://doi.org/10.1287/trsc.6.3.260
  2. Cox D. R.(1958), "The Regression Analysis of Binary Sequences," Journal of the Royal Statistical Society, Series B(Methodological), vol. 20, no. 2, pp.215-242.
  3. Dunne M. C.(1967), "Traffic Delay at a Signalized Intersection with Binomial Arrivals," Transportation Science, vol. 1, pp.24-31. https://doi.org/10.1287/trsc.1.1.24
  4. Hwang J. -S., Lee Y. -J. and Lee C. -K.(2017), "Development of Queue Length, Link Travel Time Estimation and Traffic Condition Decision Algorithm using Taxi GPS Data," The Journal of the Korea Institute of Intelligent Transportation Systems, vol. 16, no. 3, pp.59-72. https://doi.org/10.12815/kits.2017.16.3.59
  5. Kang J. -H.(2005), "The Development of Traffic Queue Length Estimation Algorithm Using the Occupancy Rates," The Journal of the Korea Institute of Intelligent Transportation Systems, vol. 4, no. 2, pp.13-22.
  6. Kim D. -O. and Woo Y. -H.(1998), "Modelling for Queue Estimation on the Approach of Signalized Intersections," Journal of the Korean Society of Civil Engineers, vol. 18, no. 2-2, pp.159-171.
  7. Kingma D. P. and Ba J. L.(2014), "ADAM: A Method for Stochastic Optimization," arXiv:1412.6980.
  8. Lee Y. -J., Hwang J. -S. and Lee C. -K.(2016), "Study on Queue Length Estimation using GPS Trajectory Data," The Journal of the Korea Institute of Intelligent Transportation Systems, vol. 15, no. 3, pp.45-51. https://doi.org/10.12815/kits.2016.15.3.045
  9. May A. D.(1965), "Traffic Flow Theory the Traffic Engineer's Challenge," Proc. Inst. Traffic Eng., pp.290-303.
  10. Moon H. -R.(2005), "A development of Traffic Queue Length Measuring Algorithm Using Average Occupancy Time Based on COSMOS," Korean Society of Civil Engineers Conference, pp.4230-4234.
  11. Newell G. F.(1965), "Approximation Methods for Queues with Applications to the Fixed cycle Traffic Light," SIMA Rev., vol. 7, no. 2, pp.223-240. https://doi.org/10.1137/1007038
  12. Rosenblatt F.(1958), "The perceptron : A probabilistic model for information storage and organization in the brain," Psychological Review, vol. 65, no. 6, pp.386-408. https://doi.org/10.1037/h0042519
  13. Rumelhart D. E., Hinton G. E. and Williams R. J.(1986), "Learning representations by back-propagating errors," Nature, vol. 323, no. 9, pp.533-536. https://doi.org/10.1038/323533a0
  14. Wardrop J. G.(1952), "Some Theoretical Aspects of Road Traffic Research," Proc. Inst. Civ. Eng. 1, pp.325-362.
  15. Winsten C. B.(1956), M. Beckmann and C. B. McGuire, "Studies in the Economics of Transportation," Yale University Press.

Cited by

  1. 딥러닝으로 추정한 차량대기길이 기반의 감응신호 연구 vol.17, pp.4, 2018, https://doi.org/10.12815/kits.2018.17.4.54