ABSTRACT
Road safety is a major global public health concern, and effective prediction of traffic accidents at a fine-grained spatial scale plays a critical role in reducing roadway deaths and serious injuries. However, previous studies have either overlooked implicit spatial correlations or inadequately simulated road structures due to the lack of graph-structured datasets. To bridge this gap, we introduce a graph-based Traffic Accident Prediction (TAP) data repository, along with two representative tasks: accident occurrence and severity prediction. With its real-world graph structures, comprehensive geographical coverage, and rich geospatial features, this repository has considerable potential to facilitate various traffic-related tasks. We extensively evaluate eleven Graph Neural Network (GNN) baselines using the constructed datasets. We also develop a novel GNN-based model, which can capture additional angular and directional information from road networks. We demonstrate that the proposed model consistently outperforms the baselines. The data and code are available at https://github.com/baixianghuang/travel.
- National Highway Traffic Safety Administration. 2022. Early Estimate of Motor Vehicle Traffic Fatalities in 2021. Technical Report. https://crashstats.nhtsa.dot.gov/Api/Public/ViewPublication/813283Google Scholar
- Microsoft Bing. 2022. Bing Map Traffic API. https://www.bingmapsportal.comGoogle Scholar
- Quanjun Chen, Xuan Song, Harutoshi Yamada, and Ryosuke Shibasaki. 2016. Learning deep representation from big and heterogeneous data for traffic accident inference. In Thirtieth AAAI conference on artificial intelligence.Google ScholarDigital Library
- New York City Police Department. 2023. New York City Motor Vehicle Collisions. Retrieved June 22, 2023 from https://data.cityofnewyork.us/Public-Safety/Motor-Vehicle-Collisions-Crashes/h9gi-nx95Google Scholar
- Insurance Institute for Highway Safety (IIHS). 2023. Automated enforcement laws. https://www.iihs.org/topics/red-light-running/automated-enforcement-lawsGoogle Scholar
- Baixiang Huang, Bryan Hooi, and Kai Shu. 2023. TAP: A Comprehensive Data Repository for Traffic Accident Prediction in Road Networks (Long Version). arXiv preprint arXiv:2304.08640 (2023).Google Scholar
- Yaguang Li, Rose Yu, Cyrus Shahabi, and Yan Liu. 2017. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. arXiv preprint arXiv:1707.01926 (2017).Google Scholar
- Daryl Lloyd. 2016. Reported road casualties in Great Britain: Main results 2015. (2016).Google Scholar
- Sobhan Moosavi, Mohammad Hossein Samavatian, Srinivasan Parthasarathy, Radu Teodorescu, and Rajiv Ramnath. 2019. Accident risk prediction based on heterogeneous sparse data: New dataset and insights. In Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. 33--42.Google ScholarDigital Library
- Alameen Najjar, Shun'ichi Kaneko, and Yoshikazu Miyanaga. 2017. Combining satellite imagery and open data to map road safety. In Thirty-First AAAI Conference on Artificial Intelligence.Google ScholarDigital Library
- Nominatim. 2023. Nominatim. https://nominatim.orgGoogle Scholar
- City of Chicago. 2023. Chicago Traffic Crashes. https://catalog.data.gov/dataset/traffic-crashes-crashesGoogle Scholar
- New York State Department of Motor Vehicles. 2022. New York State Motor Vehicle Crashes. Retrieved June 22, 2023 from https://data.ny.gov/Transportation/Motor-Vehicle-Crashes-Vehicle-Information-Three-Ye/xe9x-a24fGoogle Scholar
- UK Department of Transport. 2016. UK Accidents. https://www.kaggle.com/datasets/daveianhickey/2000-16-traffic-flow-england-scotland-walesGoogle Scholar
- Jutaek Oh, Simon P Washington, and Doohee Nam. 2006. Accident prediction model for railway-highway interfaces. Accident Analysis & Prevention 38, 2 (2006), 346--356.Google ScholarCross Ref
- OpenStreetMap. 2023. OpenStreetMap. https://www.openstreetmap.orgGoogle Scholar
- Sarbaz Othman, Robert Thomson, and Gunnar Lannér. 2009. Identifying critical road geometry parameters affecting crash rate and crash type. In Annals of Advances in Automotive Medicine/Annual Scientific Conference, Vol. 53. Association for the Advancement of Automotive Medicine, 155.Google Scholar
- Seong-hun Park, Sung-min Kim, and Young-guk Ha. 2016. Highway traffic accident prediction using VDS big data analysis. The Journal of Supercomputing 72, 7 (2016), 2815--2831.Google ScholarDigital Library
- Maryland State Police. 2023. Maryland Statewide Vehicle Crashes. Retrieved June 22, 2023 from https://opendata.maryland.gov/Public-Safety/Maryland-Statewide-Vehicle-Crashes/65du-s3quGoogle Scholar
- Moosavi Sobhan. 2023. US Accidents Dataset. https://www.kaggle.com/datasets/sobhanmoosavi/us-accidentsGoogle Scholar
- SWOV. 2012. Fact Sheet: The relation between speed and crashes. https://shorturl.at/uJLO2Google Scholar
- TRIP. 2022. Addressing America's Traffic Safety Crisis: Examining The Causes of Increasing U.S. Traffic Fatalities and Identifying Solutions to Improve Road User Safety. Technical Report. https://tripnet.org/wp-content/uploads/2022/06/TRIP_Addressing_Americas_Traffic_Safety_Crisis_Report_June_2022.pdfGoogle Scholar
- Federal Highway Administration US Department of Transportation. 2023. Safety Countermeasures initiative. https://highways.dot.gov/safety/proven-safety-countermeasuresGoogle Scholar
- WHO et al. 2018. Global status report on road safety 2018: summary. Technical Report. World Health Organization.Google Scholar
- Rose Yu, Yaguang Li, Cyrus Shahabi, Ugur Demiryurek, and Yan Liu. 2017. Deep learning: A generic approach for extreme condition traffic forecasting. In Proceedings of the 2017 SIAM international Conference on Data Mining. SIAM, 777--785.Google ScholarCross Ref
- Zhengyang Zhou, Yang Wang, Xike Xie, Lianliang Chen, and Hengchang Liu. 2020. RiskOracle: A Minute-Level Citywide Traffic Accident Forecasting Framework. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. 1258--1265.Google ScholarCross Ref
- Zhengyang Zhou, Yang Wang, Xike Xie, Lianliang Chen, and Chaochao Zhu. 2020. Foresee urban sparse traffic accidents: A spatiotemporal multi-granularity perspective. IEEE Transactions on Knowledge and Data Engineering (2020).Google Scholar
- Xiaohua Zhu and Mark Antony Freeman. 2019. An evaluation of US municipal open data portals: A user interaction framework. Journal of the Association for Information Science and Technology 70, 1 (2019), 27--37.Google ScholarDigital Library
Index Terms
- TAP: A Comprehensive Data Repository for Traffic Accident Prediction in Road Networks
Recommendations
Road Traffic Accidents in Morocco: Exploratory Analysis of Driver, Vehicle, and Pedestrian Factors
AbstractRoad safety is a major concern for both personal safety and public health in Morocco. The Ministry of Equipment, Transport, Logistics, and Water (METLW) reported that in 2017, there were 89,375 personal injuries, with an average of 361 injuries ...
Statistical accident analysis supporting the control of autonomous vehicles
Autonomous vehicles offer the potential to drastically decrease the number and severity of road accidents. Most accidents occur due to human inattention or wrong decisions, whose factors can be eliminated by autonomous vehicles. However, not all ...
Internet of Vehicles Based Approach for Road Safety Applications Using Sensor Technologies
In this paper, the Internet of Vehicles approach is used to develop a novel low cost sensor based system for road safety applications in intelligent transportation systems. It was found that major hazards that compromise road safety include weather ...
Comments