ABSTRACT
The screening of road accident black spots is to predict accident prone locations in the road network, with the aim of preventing further accidents with remedial measures. As black spots are linked to a location, certain features of the location and its nearby branches of the network should be capable of explaining the black spots. Several open data sources now provide feature-rich road network and facilities datasets. This paper proposes a data-driven machine learning solution for black spot screening using features of road network and facilities. The accident neighborhood is a concept introduced in the paper that represents the nearby locations associated with the happening of accidents. The concept has been realized as graph embeddings of road network, which, together with a deep neural network classifier, are the two major components of the solution. An evaluation of the solution using data from a Hong Kong district indicates that recognition of both the surrounding road network structure and the local features near accident sites can yield accurate models for black spot prediction.
- Anon. 2015. Global status report on road safety 2015, Geneva, Switzerland: World Health Organization.Google Scholar
- Francisco Calvo-Poyo, José Navarro-Moreno, and Juan de Oña. 2020. Road Investment and Traffic Safety: An International Study. Sustainability 12, 16 (2020), 6332. DOI:http://dx.doi.org/10.3390/su12166332Google ScholarCross Ref
- Joe Matthews, Keith Newman, Amy Green, Lee Fawcett, Neil Thorpe, and Karsten Kremer. 2019. A decision support toolkit to inform Road Safety Investment Decisions. Proceedings of the Institution of Civil Engineers - Municipal Engineer 172, 1 (2019), 53–67. DOI:http://dx.doi.org/10.1680/jmuen.16.00057Google ScholarCross Ref
- Arun Chand, S. Jayesh, and A.B. Bhasi. 2021. Road traffic accidents: An overview of data sources, analysis techniques and contributing factors. Materials Today: Proceedings 47 (2021), 5135–5141. DOI:http://dx.doi.org/10.1016/j.matpr.2021.05.415Google ScholarCross Ref
- Sachin Kumar and Durga Toshniwal. 2015. A data mining framework to analyze road accident data. Journal of Big Data 2, 1 (2015). DOI:http://dx.doi.org/10.1186/s40537-015-0035-yGoogle ScholarCross Ref
- Nicholas Fiorentini and Massimo Losa. 2020. Long-term-based road blackspot screening procedures by machine learning algorithms. Sustainability 12, 15 (2020), 5972. DOI:http://dx.doi.org/10.3390/su12155972Google ScholarCross Ref
- Maen Ghadi and Árpád Török. 2019. A comparative analysis of Black Spot Identification Methods and road accident segmentation methods. Accident Analysis & Prevention 128 (2019), 1–7. DOI:http://dx.doi.org/10.1016/j.aap.2019.03.002Google ScholarCross Ref
- Jonathan J. Rolison, Shirley Regev, Salissou Moutari, and Aidan Feeney. 2018. What are the factors that contribute to road accidents? an assessment of law enforcement views, ordinary drivers’ opinions, and Road Accident Records. Accident Analysis & Prevention 115 (2018), 11–24. DOI:http://dx.doi.org/10.1016/j.aap.2018.02.025Google ScholarCross Ref
- Zhanyong Fan, Chun Liu, Dongjian Cai, and Shun Yue. 2019. Research on black spot identification of safety in urban traffic accidents based on machine learning method. Safety Science 118 (2019), 607–616. DOI:http://dx.doi.org/10.1016/j.ssci.2019.05.039Google ScholarCross Ref
- Changjian Zhang 2021. A crash risk identification method for freeway segments with horizontal curvature based on real-time vehicle kinetic response. Accident Analysis & Prevention 150 (2021), 105911. DOI:http://dx.doi.org/10.1016/j.aap.2020.105911Google ScholarCross Ref
- van der Maaten, L. & Hinton, G. 2008, Visualizing Data using t-SNE, Journal of Machine Learning Research 9, 2579–2605.Google Scholar
Index Terms
- Predictive Screening of Accident Black Spots based on Deep Neural Models of Road Networks and Facilities: A Case Study based on a District in Hong Kong
Recommendations
Road Danger Estimation for Winter Road Management
CYBERC '14: Proceedings of the 2014 International Conference on Cyber-Enabled Distributed Computing and Knowledge DiscoveryWith over a billion vehicles on the road of the world traffic and traffic related issues are becoming extremely important topics of research. The identification of dangerous sites can help with managing the traffic and introduction of new policies, but ...
Dynamic spatio-temporal integration of traffic accident data
SIGSPATIAL '18: Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information SystemsUp to 50% of delay in traffic is due to non-reoccurring events such as traffic accidents. Accidents lead to delays, which can be costly for transport companies. Road authorities are also very interested in warning drivers about accidents, e.g., to ...
Simulation and Analysis of Typical Winter Road Traffic Accidents in China
ICICTA '10: Proceedings of the 2010 International Conference on Intelligent Computation Technology and Automation - Volume 03There are many winter road traffic accidents in China, and the Death Toll is on the top in the world for a long time, where, the traffic accidents under the condition of ice & snow road have some special characters. This article take the typical case ...
Comments