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

Prediction of Traffic Congestion in Seoul by Deep Neural Network

심층인공신경망(DNN)과 다각도 상황 정보 기반의 서울시 도로 링크별 교통 혼잡도 예측

  • Kim, Dong Hyun (Department of Computer Engineering, University of Hongik) ;
  • Hwang, Kee Yeon (Department of Urban Engineering., University of Hongik) ;
  • Yoon, Young (Department of Computer Engineering, University of Hongik)
  • 김동현 (홍익대학교 컴퓨터공학과) ;
  • 황기연 (홍익대학교 도시공학과) ;
  • 윤영 (홍익대학교 컴퓨터공학과)
  • Received : 2019.06.07
  • Accepted : 2019.07.06
  • Published : 2019.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

Various studies have been conducted to solve traffic congestions in many metropolitan cities through accurate traffic flow prediction. Most studies are based on the assumption that past traffic patterns repeat in the future. Models based on such an assumption fall short in case irregular traffic patterns abruptly occur. Instead, the approaches such as predicting traffic pattern through big data analytics and artificial intelligence have emerged. Specifically, deep learning algorithms such as RNN have been prevalent for tackling the problems of predicting temporal traffic flow as a time series. However, these algorithms do not perform well in terms of long-term prediction. In this paper, we take into account various external factors that may affect the traffic flows. We model the correlation between the multi-dimensional context information with temporal traffic speed pattern using deep neural networks. Our model trained with the traffic data from TOPIS system by Seoul, Korea can predict traffic speed on a specific date with the accuracy reaching nearly 90%. We expect that the accuracy can be improved further by taking into account additional factors such as accidents and constructions for the prediction.

여러 대도시에서 교통 혼잡 문제를 해결하기 위해 정확한 교통 흐름을 예측하는 다양한 연구가 진행되었다. 대부분의 연구가 과거의 교통 흐름 패턴이 미래에도 반복될 것이라는 가정하에 예측 모델을 개발하였으나 교통사고 등과 같은 뜻하지 않은 비반복적 교통 패턴을 예측하는 데에는 신뢰성이 낮게 나타났다. 이런 문제를 해결하기 위한 대안으로 지능형 교통 시스템(ITS)을 통해 얻은 빅데이터와 인공지능을 접목한 교통 흐름 예측 연구가 진행되어 왔다. 하지만 시계열 분석에 일반적으로 사용되는 알고리즘인 RNN의 경우, 단기 예측에 최적화되어 장기 예측 정확도가 낮다는 단점을 가지고 있다. 이런 문제를 해결하기 위해 본 논문에서는 기온과 강수량 등의 기상 정보 외에도 각종 외부 요인들을 고려하여 장기적 시점에서 교통 혼잡도를 예측하는 '심층 인공 신경망 모델'을 제안하였다. TOPIS 자료를 이용한 사례 연구 결과 서울시 주요 도로 링크의 교통 혼잡도를 90%에 가까운 정확도로 예측이 가능하였다. 추후 교통사고나 도로 공사와 같은 도로에 영향을 미치는 이벤트 데이터를 추가로 확보할 수 있다면 정확도는 더욱 높아질 것으로 예상된다.

Keywords

References

  1. Breiman L.(2001), "Random forests," Machine Learning, vol. 45, no. 1, pp.5-32. https://doi.org/10.1023/A:1010933404324
  2. Bridle J. S.(1990), "Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters," In Advances in Neural Information Processing Systems, pp.211-217.
  3. Chirigati F., Doraiswamy H., Damoulas T. and Freire J.(2016), "Data polygamy: the many-many relationships among urban spatio-temporal data sets," In Proceedings of the 2016 International Conference on Management of Data, pp.1011-1025.
  4. Jeon H.(2018), A Deep-learning Approach to Predict Short-term Traffic Speeds Considering City-wide Spatio-temporal Correlations.
  5. Jung H., Yoon J. and Bae S.(2017), "Traffic Congestion Estimation by Adopting Recurrent Neural Network," The Journal of The Korea Institute of Intelligent Transport Systems, vol. 16, no. 6, pp.67-78. https://doi.org/10.12815/kits.2017.16.6.67
  6. Kim H. Y.(2010), "A geostatistical approach for improved prediction of traffic volume in urban area," Journal of the Korean Association of Geographic Information Studies, vol. 13, no. 4, pp.138-147. https://doi.org/10.11108/KAGIS.2010.13.4.138
  7. Kim H., Park S. and Jang K.(2016), "Short-term Traffic States Prediction Using k-Nearest Neighbor Algorithm: Focused on Urban Expressway in Seoul," Journal of Korean Society of Transportation, vol. 34, no. 2, pp.158-167. https://doi.org/10.7470/jkst.2016.34.2.158
  8. Kingma D. P. and Ba J.(2014), "Adam: A method for stochastic optimizatio," arXiv preprint arXiv:1412.6980.
  9. Koesdwiady A., Soua R. and Karray F.(2016), "Improving traffic flow prediction with weather information in connected cars: A deep learning approach," IEEE Transactions on Vehicular Technology, vol. 65, no. 12, pp.9508-9517. https://doi.org/10.1109/TVT.2016.2585575
  10. Korea Expressway Corporation, http://www.ex.co.kr, 2018.
  11. Korea Meteorological Administration, http://data.kma.go.kr, 2019.
  12. LeCun Y., Boser B., Denker J. S., Henderson D., Howard R. E., Hubbard W. and Jackel L. D.(1989), "Backpropagation applied to handwritten zip code recognition," Neural Computation, vol. 1, no. 4, pp.541-551. https://doi.org/10.1162/neco.1989.1.4.541
  13. Lee M.(2016), Forecasting short-term travel speed in a dense highway network considering both temporal and spatial relationship : using a deep-learning architecture.
  14. Lee S., Kim B. and Kwon H.(2004), "The study of Estimation model for the short-term travel time prediction," The Journal of The Korea Institute of Intelligent Transport Systems, vol. 3, no. 1, pp.31-44.
  15. Ma X., Tao Z., Wang Y., Yu H. and Wang Y.(2015), "Long short-term memory neural network for traffic speed prediction using remote microwave sensor data," Transportation Research Part C: Emerging Technologies, vol. 54, pp.187-197. https://doi.org/10.1016/j.trc.2015.03.014
  16. Ministry of Land, Infrastructure and Transport, http://www.index.go.kr, 2018.
  17. Nair V., and Hinton G. E.(2010), "Rectified linear units improve restricted boltzmann machines," In Proceedings of the 27th international conference on machine learning (ICML-10), pp.807-814.
  18. Pedamonti D.(2018), "Comparison of non-linear activation functions for deep neural networks on MNIST classification task," arXiv preprint arXiv:1804.02763.
  19. Prechelt L.(1998), "Early stopping-but when?," In Neural Networks: Tricks of the trade, pp.55-69.
  20. Rumelhart D. E., Hinton G. E. and Williams R. J.(1986), "Learning representations by back-propagating errors," Nature, vol. 323, no. 6088, p.533. https://doi.org/10.1038/323533a0
  21. Seoul Metropolitan Government, http://data.seoul.go.kr, 2018.
  22. Seoul Transport Operation and Information Services, http://topis.seoul.go.kr, 2018.
  23. Tang J., Liu F., Zou Y., Zhang W. and Wang Y.(2017), "An improved fuzzy neural network for traffic speed prediction considering periodic characteristic," IEEE Transactions on Intelligent Transportation Systems, vol. 18, no. 9, pp.2340-2350. https://doi.org/10.1109/TITS.2016.2643005
  24. Yao H., Wu F., Ke J., Tang X., Jia Y., Lu S., Gong P., Ye J., Chuxing D. and Li Z.(2018), "Deep multi-view spatial-temporal network for taxi demand prediction," In Thirty-Second AAAI Conference on Artificial Intelligence, pp.2588-2595.
  25. Zhao Z., Chen W., Wu X., Chen P. C. and Liu J.(2017), "LSTM network: a deep learning approach for short-term traffic forecast," IET Intelligent Transport Systems, vol. 11, no. 2, pp.68-75. https://doi.org/10.1049/iet-its.2016.0208

Cited by

  1. Context-Aware Link Embedding with Reachability and Flow Centrality Analysis for Accurate Speed Prediction for Large-Scale Traffic Networks vol.9, pp.11, 2019, https://doi.org/10.3390/electronics9111800
  2. For Preventative Automated Driving System (PADS): Traffic Accident Context Analysis Based on Deep Neural Networks vol.9, pp.11, 2019, https://doi.org/10.3390/electronics9111829