融合局部和全局时空特征的交通事故风险预测

doi:10.3778/j.issn.1673-9418.2008093

摘要/Abstract

摘要：

交通事故预测在城市公共安全、应急处置以及建设规划方面发挥着重要的作用。然而，在预测交通事故风险时仍然存在以下问题：首先交通事故的发生受到众多因素的影响，例如天气、道路状况等。其次交通事故的发生在空间范围内存在多尺度的时空依赖，主要包括局部区域的时空相关性和全局区域的时空相似性。同时，由于实际场景中交通事故发生次数相对较少，给预测带来了零膨胀问题。因此，对交通事故进行准确的预测具有很大的挑战，现有的预测方法无法综合考虑上述问题。提出了一种新颖的融合局部和全局时空特征的交通事故风险预测模型（ST-RiskNet），同时考虑时间、天气、交通流量等影响事故发生的多源因素，通过局部区域时空相关性模块和全局区域时空相似性模块同时建模多尺度的时空相关性和相似性，并设计样本加权损失函数，针对事故风险较大的样本设置较大的权重来解决零膨胀问题。在两个真实交通事故数据集的结果表明，ST-RiskNet的预测效果优于现有的预测方法。

关键词: 交通事故预测, 多源时空数据, 零膨胀, 图卷积（GCN）

Abstract:

Traffic accident forecasting is very important for urban public security, emergency treatment and construc-tion planning. However, the following problems still exist when forecasting traffic accident risk. Firstly, traffic accidents are affected by multiple factors, such as weather and road conditions. Besides, there are multi-scale correlations in the spatial dimension, i.e. local region spatial-temporal correlation and global region spatial-temporal similarity. Meanwhile, there is zero-inflated issue in the forecasting because of few traffic accidents in reality. Therefore, it is very challenging to forecast traffic accidents accurately, and existing traffic accident forecasting methods cannot take all the above problems into account. A novel model, named local and global spatial-temporal networks (ST-RiskNet), for traffic accident risk forecasting is proposed. The ST-RiskNet takes multi-source factors that affect traffic accidents into consideration, such as time, weather, traffic flow. It uses a local region spatial-temporal correlation module and a global region spatial-temporal similarity module to model the multi-scale spatial-temporal correlation and similarity simultaneously. Meanwhile, a sample weighted loss function is designed to solve the zero-inflated problem, which pays more weights to the higher risk samples. Extensive experiments on two real-world traffic accident datasets demonstrate the effectiveness of the ST-RiskNet against the state-of-the-art baseline methods.

Key words: traffic accident forecasting, multi-source spatial-temporal data, zero-inflated, graph convolutional network (GCN)

王贝贝, 万怀宇, 郭晟楠, 林友芳. 融合局部和全局时空特征的交通事故风险预测[J]. 计算机科学与探索, 2021, 15(9): 1694-1702.

WANG Beibei, WAN Huaiyu, GUO Shengnan, LIN Youfang. Local and Global Spatial-Temporal Networks for Traffic Accident Risk Forecasting[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(9): 1694-1702.

参考文献

[1] REN H L, SONG Y, WANG J W, et al. A deep learning app-roach to the citywide traffic accident risk prediction[C]//Proceedings of the 21st International Conference on Intel-ligent Transportation Systems, Maui, Nov 4-7, 2018. Pisca-taway: IEEE, 2018: 3346-3351.
[2] CHEN C, FAN X, ZHENG C, et al. SDCAE: stack denoising convolutional autoencoder model for accident risk prediction via traffic big data[C]//Proceedings of the 2018 International Conference on Advanced Cloud and Big Data, Lanzhou, Aug 12-15, 2018. Piscataway: IEEE, 2018: 328-333.
[3] YUAN Z N, ZHOU X, YANG T B, et al. Hetero-ConvLSTM: a deep learning approach to traffic accident prediction on heterogeneous spatio-temporal data[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, Aug 19-23, 2018. New York: ACM, 2018: 984-992.
[4] BAO J, LIU P, UKKUSURI S V, et al. A spatiotemporal deep learning approach for citywide short-term crash risk predic-tion with multi-source data[J]. Accident Analysis & Preven-tion, 2019, 122: 239-254.
[5] CALIENDO C, GUIDA M, PARISI A, et al. A crash-prediction model for multilane roads[J]. Accident Analysis & Prevention, 2007, 39(4): 657-670.
[6] OLUTAYO V A, ELUDIRE A A. Traffic accident analysis using decision trees and neural networks[J]. International Journal of Information Technology & Computer Science, 2014, 6(2): 22-28.
[7] LYU Y S, TANG S M, ZHAO H X, et al. Real-time highway traffic accident prediction based on the k-nearest neighbor method[C]//Proceedings of the 2009 International Confer-ence on Measuring Technology and Mechatronics Automation, Zhangjiajie, Apr 11-12, 2009. Piscataway: IEEE, 2009: 547-550.
[8] CHEN Q J, SONG X, YAMADA H, et al. Learning deep representation from big and heterogeneous data for traffic accident inference[C]//Proceedings of the 30th AAAI Con-ference on Artificial Intelligence, Phoenix, Feb 12-17, 2016. Menlo Park: AAAI, 2016: 338-344.
[9] ZHOU Z Y, WANG Y, XIE X K, et al. RiskOracle: a minute-level citywide traffic accident forecasting framework[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conference, the 10th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 7-12, 2020. Menlo Park: AAAI, 2020: 1258-1265.
[10] GUO S, LIN Y, FENG N, et al. Attention based spatial-temporal graph convolutional networks for traffic flow fore-casting[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Conference, the 9th AAAI Symposium on Educational Advances in Artificial Intelligence, Honolulu, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 922-929.
[11] PAN S R, HU R Q, LONG G D, et al. Adversarially regu-larized graph autoencoder for graph embedding[C]//Procee-dings of the 27th International Joint Conference on Artificial Intelligence, Stockholm, Jul 13-19, 2018: 2609-2615.
[12] KIPF T, WELLING M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th Inter-national Conference on Learning Representations, Toulon, Apr 24-26, 2017: 1-14.
[13] BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral net-works and locally connected networks on graphs[C]//Pro-ceedings of the 2nd International Conference on Learning Representations, Banff, Apr 14-16, 2014: 1-14.
[14] DEFFERRARD M, BRESSON X, VANDERGHEYNST P, et al. Convolutional neural networks on graphs with fast loca-lized spectral filtering[C]//Proceedings of the 29th Annual Conference on Neural Information Processing Systems, Barcelona, Dec 5-10, 2016. Red Hook: Curran Associates, 2016: 3844-3852.
[15] HAMILTON W, YING Z, LESKOVEC J, et al. Inductive representation learning on large graphs[C]//Proceedings of the 30th Annual Conference on Neural Information Processing Systems, Long Beach, Dec 4-9, 2017. Red Hook: Curran Associates, 2017: 1024-1034.
[16] VELICKOVIC P, CUCURULL G, CASANOVA A, et al. Graph attention networks[C]//Proceedings of the 6th Interna-tional Conference on Learning Representations, Vancouver, Apr 30-May 3, 2018: 1-12.
[17] WU Z H, PAN S R, LONG G D, et al. Graph WaveNet for deep spatial-temporal graph modeling[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, Aug 10-16, 2019: 1907-1913.
[18] SONG C, LIN Y, GUO S, et al. Spatial-temporal synchronous graph convolutional networks: a new framework for spatial-temporal network data forecasting[C]//Proceedings of the 34th AAAI Conference on Artificial Intelligence, the 32nd Innovative Applications of Artificial Intelligence Conference, the 10th AAAI Symposium on Educational Advances in Artificial Intelligence, New York, Feb 7-12, 2020. Menlo Park: AAAI, 2020: 914-921.
[19] BAI L, YAO L, KANHERE S S, et al. STG2seq: spatial-temporal graph to sequence model for multi-step passenger demand forecasting[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, Aug 10-16, 2019: 1981-1987.
[20] MA C, ZHANG Y X, WANG Q L, et al. Point-of-interest recommendation: exploiting self-attentive autoencoders with neighbor-aware influence[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, Oct 22-26, 2018. New York: ACM, 2018: 697-706.
[21] CHEN T Q, GUESTRIN C. XGBoost: a scalable tree Boos-ting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 785-794.
[22] CHUNG J, GULCEHRE C, CHO K H, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling[J]. arXiv:1412.3555, 2014.
[23] SHI X J, CHEN Z R, WANG H, et al. Convolutional LSTM network: a machine learning approach for precipitation now-casting[C]//Proceedings of the 28th Annual Conference on Neural Information Processing Systems, Montreal, Dec 7-12, 2015. Red Hook: Curran Associates, 2015: 802-810.