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

Traffic Speed Prediction Based on Graph Neural Networks for Intelligent Transportation System

지능형 교통 시스템을 위한 Graph Neural Networks 기반 교통 속도 예측

  • Kim, Sunghoon (Department of Data Science, Seoul Women's University) ;
  • Park, Jonghyuk (Department of Industrial Engineering, Seoul National University) ;
  • Choi, Yerim (Department of Data Science, Seoul Women's University)
  • 김성훈 (서울여자대학교 데이터사이언스학과) ;
  • 박종혁 (서울대학교 산업경영공학과) ;
  • 최예림 (서울여자대학교 데이터사이언스학과)
  • Received : 2020.06.09
  • Accepted : 2021.01.05
  • Published : 2021.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Deep learning methodology, which has been actively studied in recent years, has improved the performance of artificial intelligence. Accordingly, systems utilizing deep learning have been proposed in various industries. In traffic systems, spatio-temporal graph modeling using GNN was found to be effective in predicting traffic speed. Still, it has a disadvantage that the model is trained inefficiently due to the memory bottleneck. Therefore, in this study, the road network is clustered through the graph clustering algorithm to reduce memory bottlenecks and simultaneously achieve superior performance. In order to verify the proposed method, the similarity of road speed distribution was measured using Jensen-Shannon divergence based on the analysis result of Incheon UTIC data. Then, the road network was clustered by spectrum clustering based on the measured similarity. As a result of the experiments, it was found that when the road network was divided into seven networks, the memory bottleneck was alleviated while recording the best performance compared to the baselines with MAE of 5.52km/h.

최근 활발히 연구되는 딥러닝 방법론은 인공지능의 성능을 급속도로 향상시켰고, 이에 따라 다양한 산업 분야에서 딥러닝을 활용한 시스템이 제시되고 있다. 교통 시스템에서는 GNN을 활용한 공간-시간 그래프 모델링이 교통 속도 예측에 효과적인 것으로 밝혀졌지만, 이는 메모리 병목 현상을 유발하기 때문에 모델이 비효율적으로 학습된다는 단점이 있다. 따라서 본 연구에서는 그래프 분할 방법을 통해 도로 네트워크를 분할하여 메모리 병목 현상을 완화함과 동시에 우수한 성능을 달성하고자 한다. 제안 방법론을 검증하기 위해 인천시 UTIC 데이터 분석 결과를 바탕으로 Jensen-Shannon divergence를 사용하여 도로 속도 분포의 유사도를 측정하였다. 그리고 측정된 유사도를 바탕으로 스펙트럴 클러스터링을 수행하여 도로 네트워크를 군집화하였다. 성능 측정 결과, 도로 네트워크가 7개의 네트워크로 분할되었을 때 MAE 기준 5.52km/h의 오차로 비교 모델 대비 가장 우수한 정확도를 보임과 동시에 메모리 병목 현상 또한 완화되는 것을 확인할 수 있었다.

Keywords

References

  1. Endres, D. M. and Schindelin, J. E.(2003), "A New Metric for Probability Distributions," IEEE Transactions on Information Theory, vol. 49, no. 7, pp.1858-1860. https://doi.org/10.1109/TIT.2003.813506
  2. Fu, R., Zhang, Z. and Li, L.(2016), "Using LSTM and GRU Neural Network Methods for Traffic Flow Prediction," Youth Academic Annual Conference of Chinese Association of Automation, Wuhan, China, pp.324-328.
  3. George, K. and Vipin, K.(1998), "A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs," SIAM Journal on scientific Computing, vol. 20, no. 1, pp.359-392. https://doi.org/10.1137/S1064827595287997
  4. Hinton, G. E., Osindero, S. and Teh, Y. W.(2006), "A Fast Learning Algorithm for Deep Belief Nets," Neural Computation, vol. 18, no. 7, pp.1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  5. D. Kim, K. Hwang and Y. Yoon,(2019), "Prediction of Traffic Congestion in Seoul by Deep Neural Network," The Journal of the Korea Institute of Intelligent Transport Systems, vol. 18, no. 4, pp.44-57.
  6. Y. Kim, J. Kim, Y, Han, J. Kim and J. Hwang,(2020), "Development of Traffic Speed Prediction Model Reflecting Spatio-Temporal Impact Based on Deep Neural Network," The Journal of the Korea Institute of Intelligent Transport Systems, vol. 19, no. 1, pp.1-16.
  7. K-indicator(2020), https://www.index.go.kr/
  8. Kipf, T. N. and Welling, M.(2016), "Semi-Supervised Classification with Graph Convolutional Networks," arXiv preprint arXiv:1609.02907.
  9. LeCun, Y., Bengio, Y. and Hinton, G.(2015), "Deep Learning," Nature, vol. 521, no. 7553, pp.436-444. https://doi.org/10.1038/nature14539
  10. Li, Y., Yu, R., Shahabi, C. and Liu, Y.(2018), "Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting," The International Conference on Learning Representations. Vancouver, Canada
  11. Lv, Z., Xu, J., Zheng, K., Yin, H., Zhao, P. and Zhou, X.(2018), "Lc-rnn: A Deep Learning Model for Traffic Speed Prediction," International Joint Conferences on Artificial Intelligence, Stockholm, Sweden, pp.3470-3476.
  12. Ma, X., Dai, Z., He, Z., Ma, J., Wang, Y. and Wang, Y.(2017), "Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction," Sensors, vol. 4, no. 17, p.818.
  13. Mallick, T., Balaprakash, P., Rask, E. and Macfarlane, J.(2020), "Graph-Partitioning-Based Diffusion Convolution Recurrent Neural Network for Large-Scale Traffic Forecasting," Transportation Research Record, vol. 2674, No. 9, pp.473-488. https://doi.org/10.1177/0361198120930010
  14. Oord, A. Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A. and Kavukcuoglu, K.(2016), "Wavenet: A Generative Model for Raw Audio," arXiv preprint arXiv:1609.03499.
  15. C. Park, C. Lee, H. Bahng, K. Kim, S. Jin, S. Ko and J. Choo,(2019), "STGRAT: A Spatio-Temporal Graph Attention Network for Traffic Forecasting," arXiv preprint arXiv:1911.13181.
  16. Wang, J., Gu, Q., Wu, J., Liu, G. and Xiong, Z.(2016), "Traffic Speed Prediction and Congestion Source Exploration: A Deep Learning Method," IEEE 16th International Conference on Data Mining, Barcelona, Spain, pp.499-508.
  17. Wu, Z., Pan, S., Long, G., Jiang, J. and Zhang, C.(2019), "Graph Wavenet for Deep Spatial-Temporal Graph Modeling," International Joint Conference on Artificial Intelligence, Macao, China.
  18. Lv, Y., Duan, Y., Kang, W., Li, Z. and Wang, F. Y.(2014), "Traffic Flow Prediction with Big Data: A Deep Learning Approach," IEEE Transactions on Intelligent Transportation Systems, vol. 2, no. 16, pp.865-873.
  19. Yu, B., Yin, H. and Zhu, Z.(2018), "Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting," International Joint Conference on Artificial Intelligence, Stockholm, Sweden, pp.3634-3640.
  20. Yu, H., Wu, Z., Wang, S., Wang, Y. and Ma, X.(2017), "Spatiotemporal Recurrent Convolutional Networks for Traffic Prediction in Transportation Networks," Sensors, vol. 7, no. 17, p.1501.
  21. Zhang, J., Shi, X., Xie, J., Ma, H., King, I. and Yeung, D. Y.(2018), "Gaan: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs," Uncertainty in Artificial Intelligence, California, USA.
  22. 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. 2, no. 11, pp.68-75.