Traffic accident prediction method based on multi-view spatial-temporal learning

• Autorzy: Feng Jian , Liu Tian , Qiao Yuqiang

Identyfikatory

DOI

10.24425/bpasts.2024.151955

• Języki publikacji: EN

Abstrakty

EN

Traffic accident prediction is a crucial component of an intelligent traffic system, which is important to maintain citizen safety and decrease economic losses. Current methods for traffic accident prediction based on deep learning fail to consider the driving mechanisms of traffic accidents, so a novel traffic accident prediction method based on multi-view spatial-temporal learning is proposed, which represents the driving mechanism of traffic accidents from multiple views. Firstly, for the urban regions divided by grids, a new augmentation was designed to augment the spatial semantic information of regions through learnable semantic embedding, then deformable convolutional networks with non-fixed convolution kernels are used to learn dynamic spatial dependencies between regions and gated recurrent units are used to learn temporal dependencies, which can capture dynamic spatial-temporal evolution patterns of traffic accidents. Secondly, long short-term memory is employed to learn the traffic flow breakdown from the flow difference of adjacent time steps in each region to recognize the traffic accident precursor in the risk environment. Thirdly, accident patterns in different regions are learned from historical traffic flow to determine whether the flow is the dominant factor and capture the spatial heterogeneity of traffic accidents. Finally, the above features are fused for accident prediction at the regional level. Experiments are conducted on two real datasets, and the experimental results show that the proposed method outperforms eight benchmark methods.

Słowa kluczowe

EN

traffic accident prediction; accident precursor; spatial heterogeneity; spatial temporal dependencies

PL

prognozowanie wypadków drogowych; poprzednik wypadku; niejednorodność przestrzenna; zależność czasoprzestrzenna

• Wydawca: Polska Akademia Nauk, Wydział IV Nauk Technicznych
• Czasopismo: Bulletin of the Polish Academy of Sciences. Technical Sciences
• Rocznik: 2024
• Tom: Vol. 72, nr 6
• Strony: art. no. e151955
• Opis fizyczny: Bibliogr. 30 poz., rys., tab.

Twórcy

autor

Feng Jian

• College of Computer Science & Technology, Xi’an University of Science and Technology, Xi’an 710000, China

• https://orcid.org/0009-0009-6641-6432

autor

Liu Tian

• College of Computer Science & Technology, Xi’an University of Science and Technology, Xi’an 710000, China

• https://orcid.org/0000-0002-3216-4195

autor

Qiao Yuqiang

• Shaanxi Branch, China United Network Communications Group Co., Ltd., Xi’an 710000, China

Bibliografia

• [1] R. Tomasz, E. Szczepański, and M. Jacyna, “Safety factor in the sustainable fleet management model,” Arch. Transp., vol. 49, no. 1, pp. 103–114, 2019, doi: 10.5604/01.3001.0013.2780.
• [2] E. Macioszek, A. Granà, and S. Krawiec, “Identification of factors increasing the risk of pedestrian death in road accidents involving a pedestrian with a motor vehicle,” Arch. Transp., vol. 65, no. 1, pp. 7–25, 2023, doi: 10.5604/01.3001.0016.2474.
• [3] M. Izdebski, I. Jacyna-Gołda, and P. Gołda, “Minimisation of the probability of serious road accidents in the transport of dangerous goods,” Reliab. Eng. Syst. Safe., vol. 217, p. 108093, 2022, doi: 10.1016/j.ress.2021.108093.
• [4] J. Murawski, E. Szczepański, I. Jacyna-Gołda, M. Izdebski and D. Jankowska-Karpa, “Intelligent mobility: A model for assessing the safety of children traveling to school on a school bus with the use of intelligent bus stops,” Eksploat. Niezawodn., vol. 24, no. 4, pp. 695–706, 2022, doi: 10.17531/ein.2022.4.10.
• [5] Y. Qian, H. Sun, and S. Feng, “Obstacle avoidance method of autonomous vehicle based on fusion improved A*APF algorithm,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 71, no. 2, p. e144624, 2023, doi: 10.24425/bpasts.2023.144624.
• [6] Y. Qian, C. Deng, J. Xu, X. Qu, and Z. Song, “Occlusion-aware collision avoidance trajectory planning with potential collision risk assessment for autonomous vehicle,” Bull. Pol. Acad. Sci. Tech. Sci., vol. 72, no. 4, p. e149819, 2024, doi: 10.24425/bpasts.2024.149819.
• [7] M. Méndez, M.G. Merayo, and M. Núñez, “Long-term traffic flow forecasting using a hybrid CNN-BiLSTM model,” Eng. Appl. Artif. Intel., vol. 121, p. 106041, 2023, doi: 10.1016/j.engappai.2023.106041.
• [8] Y. Shin and Y. Yoon, “PGCN: Progressive graph convolutional networks for spatial–temporal traffic forecasting,” IEEE Trans. Intell. Transp., vol. 25, no. 7, pp. 7633–7644, 2024, doi: 10.1109/TITS.2024.3349565.
• [9] N.S. Chauhan, N. Kumar, and A. Eskandarian, “A Novel Confined Attention Mechanism Driven Bi-GRU Model for Traffic Flow Prediction,” IEEE Trans. Intell. Transp., vol. 25, no. 8, pp. 9181–9191, 2024, doi: 10.1109/TITS.2024.3375890.
• [10] F. Kavehmadavani, V.D. Nguyen, T.X. Vu, and S. Chatzinotas, “Intelligent traffic steering in beyond 5G open RAN based on LSTM traffic prediction,” IEEE Trans. Wirel. Commun., vol. 22, no. 11, pp. 7727–7742, 2023, doi: 10.1109/TWC.2023.3254903.
• [11] Z. Yuan, X. Zhou, and T. Yang, “Hetero-ConvLSTM: A Deep Learning Approach to Traffic Accident Prediction on Heterogeneous Spatio-Temporal Data,” in 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018, pp. 984–992, doi: 10.1145/3219819.3219922.
• [12] L. Yu, B. Du, X. Hu, L. Sun, L. Han, and W. Lv, “Deep Spatio-Temporal Graph Convolutional Network for Traffic Accident Prediction,” Neurocomputing, vol. 423, pp. 135–147, 2021, doi: 10.1016/j.neucom.2020.09.043.
• [13] B. Wang, Y. Lin, S. Guo, and H. Wan, “GSNet: Learning Spatial-Temporal Correlations from Geographical and Semantic Aspects for Traffic Accident Risk Forecasting,” in 35th AAAI Conference on Artificial Intelligence, 2021, pp. 4402–4409, doi: 10.1609/aaai.v35i5.16566.
• [14] P. Trirat, S. Yoon and J.G. Lee, “MG-TAR: Multi-view graph convolutional networks for traffic accident risk prediction,” IEEE Trans. Intell. Transp., vol. 24, no. 4, pp. 3779–3794, 2023, doi: 10.1109/TITS.2023.3237072.
• [15] B. An, A. Vahedian, X. Zhou, W.N. Street, and Y. Li, “HintNet: Hierarchical knowledge transfer networks for traffic accident forecasting on heterogeneous spatio-temporal data,” in 2022 SIAM International Conference on Data Mining (SDM), 2022, pp. 334–342, doi: 10.1137/1.9781611977172.38.
• [16] J. Dai et al., “Deformable Convolutional Networks,” in IEEE international conference on computer vision, 2017, pp. 764–773, doi: 10.1109/ICCV.2017.89.
• [17] Z. Li, H. Yu, G. Zhang, and J. Wang, “A Bayesian Vector Autoregression-based Data Analytics Approach to Enable Irregularly-spaced Mixed-frequency Traffic Collision Data Imputation with Missing Values,” Transp. Res. Part. C Emerg. Technol., vol. 108, pp. 302–319, 2019, doi: 10.1016/j.trc.2019.09.013.
• [18] K.A. Getahun, “Time Series Modeling of Road Traffic Accidents in Amhara Region,” J. Big. Data, vol. 8, no. 1, pp. 1–15, 2021, doi: 10.1186/s40537-021-00493-z.
• [19] M.B.A. Rabbani et al., “A Comparison Between Seasonal Autoregressive Integrated Moving Average (SARIMA) and Exponential Smoothing (ES) Based on Time Series Model for Forecasting Road Accidents,” Arab. J. Sci. Eng., vol. 46, no. 11, pp. 11113–11138, 2021, doi: 10.1007/s13369-021-05650-3.
• [20] Y. Castro and Y.J. Kim, “Data Mining on Road Safety: Factor Assessment on Vehicle Accidents Using Classification Models,” Int. J. Crashworthiness, vol. 21, no. 2, pp. 104–111, 2016, doi: 10.1080/13588265.2015.1122278.
• [21] X. Xiong, L. Chen, and J. Liang, “A New Framework of Vehicle Collision Prediction by Combining SVM and HMM,” IEEE Trans. Intell. Transp. Syst., vol. 19, no. 3, pp. 699–710, 2017, doi: 10.1109/TITS.2017.2699191.
• [22] Y. Lee, C.H. Wei and K.C. Chao, “Non-parametric machine learning methods for evaluating the effects of traffic accident duration on freeways,” Arch. Transp., vol. 43, no. 3, pp. 91–104, 2017, doi: 10.5604/01.3001.0010.4228.
• [23] M. Fallah Tafti, and R. Roshani, “Development of models to study traffic accidents on the final sections of access roads to the cities: a case study of three major Iranian cities,” Arch. Transp., vol. 59, no. 3, pp. 129–148, 2021, doi: 10.5604/01.3001.0015.2646.
• [24] Q. Chen, X. Song, H. Yamada, and R. Shibasaki, “Learning Deep Representation from Big and Heterogeneous Data for Traffic Accident Inference,” in 30th AAAI Conference on Artificial Intelligence, 2016, pp. 338–344, doi: 10.1609/aaai.v30i1.10011.
• [25] C. Chen, X. Fan, C. Zheng, L. Xiao, M. Cheng, and C. Wang, “SDCAE: Stack Denoising Convolutional Autoencoder Model for Accident Risk Prediction Via Traffic Big Data,” in 16th International Conference on Advanced Cloud and Big Data (CBD), 2018, pp. 328–333, doi: 10.1109/CBD.2018.00065.
• [26] M.I. Sameen and B. Pradhan, “Severity prediction of traffic accidents with recurrent neural networks,” Appl. Sci., vol. 7, no. 6, p. 476, 2017, doi: 10.3390/app7060476.
• [27] S. Wang, Y. Zhang, X. Piao, X. Lin, Y. Hu, and B. Yin, “Data-unbalanced traffic accident prediction via adaptive graph and self-supervised learning,” Appl. Soft Comput., vol. 157, p. 111512, 2024, doi: 10.1016/j.asoc.2024.111512.
• [28] B. Wang, H. Wan, S. Guo, and Y. Lin, “Local and Global Spatial-Temporal Networks for Traffic Accident Risk Forecasting,” Front. Comput. Sci., vol. 15, no. 9, pp. 1694–1702, 2021, doi: 10.3778/j.issn.1673-9418.2008093.
• [29] M. Abdel-Aty, A. Pande, C. Lee, V. Gayah, and C.D. Santos, “Crash Risk Assessment Using Intelligent Transportation Systems Data and Real-time Intervention Strategies to Improve Safety on Freeways,” J. Intell. Transp. Syst., vol. 11, no. 3, pp. 107–120, 2007, doi: 10.1080/15472450701410395.
• [30] P. Trirat and J.G. Lee, “DF-TAR: A Deep Fusion Network for Citywide Traffic Accident Risk Prediction with Dangerous Driving Behavior,” in Web Conference 2021, 2021, pp. 1146–1156, doi: 10.1145/3442381.3450003.