Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Speed Prediction and Analysis of Nearby Road Causality Using Explainable Deep Graph Neural Network

설명 가능 그래프 심층 인공신경망 기반 속도 예측 및 인근 도로 영향력 분석 기법

  • Kim, Yoo Jin (Department of Computer Engineering, Hongik University) ;
  • Yoon, Young (Department of Computer Engineering, Hongik University)
  • 김유진 (홍익대학교 컴퓨터공학과) ;
  • 윤영 (홍익대학교 컴퓨터공학과)
  • Received : 2021.11.17
  • Accepted : 2022.01.20
  • Published : 2022.01.28
Download PDF
⟨ Previous Next ⟩

Abstract

AI-based speed prediction studies have been conducted quite actively. However, while the importance of explainable AI is emerging, the study of interpreting and reasoning the AI-based speed predictions has not been carried out much. Therefore, in this paper, 'Explainable Deep Graph Neural Network (GNN)' is devised to analyze the speed prediction and assess the nearby road influence for reasoning the critical contributions to a given road situation. The model's output was explained by comparing the differences in output before and after masking the input values of the GNN model. Using TOPIS traffic speed data, we applied our GNN models for the major congested roads in Seoul. We verified our approach through a traffic flow simulation by adjusting the most influential nearby roads' speed and observing the congestion's relief on the road of interest accordingly. This is meaningful in that our approach can be applied to the transportation network and traffic flow can be improved by controlling specific nearby roads based on the inference results.

교통 혼잡을 해결하기 위한 AI 기반 속도 예측 연구는 활발하게 진행되고 있다. 하지만, 인공지능의 추론 과정을 설명하는 설명 가능한 AI의 중요성이 대두되고 있는 가운데 AI 기반 속도 예측의 결과를 해석하고 원인을 추리하는 연구는 미흡하였다. 따라서 본 논문에서는 '설명 가능 그래프 심층 인공신경망 (GNN)'을 고안하여 속도 예측뿐만 아니라, GNN 모델 입력값의 마스킹 기법에 기반하여 인근 도로 영향력을 정량적으로 분석함으로써 혼잡 등의 상황에 대한 추론 근거를 도출하였다. TOPIS 통행 속도 데이터를 활용하여 서울 시내 혼잡 도로를 기준으로 예측 및 분석 방법론을 적용한 후 영향력 높은 인근 도로의 속도를 가상으로 조절하는 시뮬레이션 통하여 혼잡 도로의 통행 속도가 개선됨을 확인하여 제안한 방법론의 타당성을 입증하였다. 이는 교통 네트워크에 제안한 방법론을 적용하고, 그 추론 결과에 기반한 특정 인근 도로를 제어하여 교통 흐름을 개선할 수 있다는 점에 의미가 있다.

Keywords

Acknowledgement

This research was supported by the Korean Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure, and Transport (Grant 21TLRP-B148676-04), by the Basic Science Research Programs through the National Research Foundation of Korea (NRF) funded by the Korea government (MSIT) (2020R1F1A104826411), by the Ministry of Trade, Industry and Energy (MOTIE) and the Korea Institute for Advancement of Technology (KIAT), under Grants P0014268 Smart HVAC demonstration support, and by the 2021 Hongik University Research Fund.

References

  1. S. Cheon, S. Kim & C. Lee. (2020). The paradigm change of traffic congestion cost estimation and the results of traffic congestion cost estimation in 2017. Monthly KOTI Magazine on Transport (pp.11-16).
  2. D. Kim, K. Hwang & Y. Yoon. (2019). Prediction of Traffic Congestion in Seoul by Deep Neural Network. The Journal of The Korea Institute of Intelligent Transport Systems, 18(4), 44-57. DOI : 10.12815/kits.2019.18.4.44
  3. C. Lee & Y. Yoon. (2020). Context-Aware Link Embedding with Reachability and Flow Centrality Analysis for Accurate Speed Prediction for Large-Scale Traffic Networks. Electronics, 9(11), 1800. DOI : 10.3390/electronics9111800
  4. M. S. Ahmed & A. R. Coo. (1979). Analysis of freeway traffic time-series data by using Box-Jenkins techniques. Transportation Research Record, 722, 1-9.
  5. X. Ma, Z. Tao, Y. Wang, H. Yu & Y. Wang. (2015). Long short-term memory neural network for traffic speed prediction using remote microwave sensor data. Transportation Research Part C: Emerging Technologies, 54, 187-197. DOI : 10.1016/j.trc.2015.03.014
  6. Y. Jia, J. Wu & Y. Du. (2016). Traffic speed prediction using deep learning method. 2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC), 1217-1222. DOI : 10.1109/ITSC.2016.7795712
  7. K. Xu, W. Hu, J. Leskovec & S. Jegelka. (2018). How powerful are graph neural networks?. arXiv preprint arXiv:1810.00826.
  8. A. Adadi & M. Berrada. (2018). Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI). IEEE, 6, 52138-52160. DOI : 10.1109/ACCESS.2018.2870052
  9. L. Breiman. (2001). Random forests. Machine learning, 45, 5-32. DOI : 10.1023/A:1010933404324
  10. J. H. Friedman. (2001). Greedy function approximation: a gradient boosting machine. The Annals of Statistics, 29(5), 1189-1232. https://doi.org/10.1214/aos/1013203451
  11. R. Ying, D. Bourgeois, J. You, M. Zitnik & J. Leskovec. (2019). GNN explainer: A tool for post-hoc explanation of graph neural networks. arXiv preprint arXiv:1903.03894.
  12. A. Bundy & L. Wallen. (1984). Catalogue of Artificial Intelligence Tools. Berlin, Heidelberg : Springer. DOI : 10.1007/978-3-642-96964-5_1
  13. C. Molnar, T. Freiesleben, G. Konig, G. Casalicchio, M.N. Wright & B. Bischl (2021). Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process. arXiv preprint arXiv:2109.01433.
  14. J. Cheng, L. Dong & M. Lapata (2016). Long short-term memory-networks for machine reading. arXiv preprint arXiv:1601.06733.
  15. M. Abdoos, & A.L. Bazzan (2021). Hierarchical traffic signal optimization using reinforcement learning and traffic prediction with long-short term memory. Expert Systems with Applications, 171, p.114580. DOI: 10.1016/j.eswa.2021.114580