Abstract
Traditional accident prediction models have been mostly designed with statistical analysis that finds and analyzes the causal relationships between traffic accidents and a variety of human, road geometry, and environmental factors. However, these statistical methods have limitations in that they are based on assumptions about data distribution and function type. Therefore, this study suggests an accident prediction model using deep learning. This newly suggested risk prediction model is for predicting risk by reflecting static features of the road, such its length and the speed limit on it, and dynamic features of the road, such as traffic volume when driving on it, and the altitude and azimuth of the sun. For this purpose, 4470 accident cases, collected over 5 months from August to December 2018 in Seoul—the most complex, high-traffic, and accident-prone city in Korea—were analyzed. As a result of testing the model using such data, it was found to have an accuracy of 75% and recall of 81%. Based on testing results for the suggested risk prediction model, a system was developed to guide not only accident-prone regions predicted using statistical data but to also guide a risk level for the road. This level of risk is estimated based upon each given situation, so it can change even for the same road. This guide system can be used to provide a level of risk for each road segment and region but also to improve roads with recommendations, such as installation of safety features. In addition, it could support a mobile system that provides a driver with the optimized driving path for safety.
Similar content being viewed by others
References
Lim J, Kim J, Lee S, Kim H (2014) A study on the road safety analysis model - focused on national highway areas in Cheonbuk province. J Korean Soc Civ Eng 34(2):583–595
Rye J, Park S, Park S, Kwon C (2018) A study for development of expressway traffic accident prediction model using deep learning. Korean Soc Intell Transp Syst 17(4):14–25
Chung M, Kim J (2016) The internet information and technology research directions based on the fourth industrial revolution. KSII Trans Internet Inf Syst 10(3):1311–1320
Coppola R, Morisio M (2016) Connected car: technologies, issues, future trends. ACM Comput Surv 49(3):1–36
Hosseini S, Khodadadi A, Alizadeh K, Arabzadeh A, Farajtabar M, Zha H, Rabiee H (2018) Recurrent Poisson factorization for temporal recommendation. IEEE Trans Knowl Data Eng 32(1):121–134
Karim EB, Tarek S (2013) Safety performance functions using traffic conflicts. Saf Sci 51(1):160–164
Lee J, Chung K, Papakonstantinou I, Kang S, Kim DK (2020) An optimal network screening method of hotspot identification for highway crashes with dynamic site length. Accid Anal Prev 135:105358. https://doi.org/10.1016/j.aap.2019.105358
Farid A, Abdel-Aty M, Lee J (2019) Comparative analysis of multiple techniques for developing and transferring safety performance functions. Accid Anal Prev 122:85–98
Afghari AP, Haque MM, Washington S, Smyth T (2019) Effects of globally obtained informative priors on Bayesian safety performance functions developed for Australian crash data. Accid Anal Prev 129:55–65
Park J, Abdel-Aty M, Wang L, Lee G, Hong J (2019) Influence of multiple freeway design features on freight traffic safety. J Adv Transp 2019:1–8
Wang K, Zhao S, Jackson E (2019) Functional forms of the negative binomial models in safety performance functions for rural two-lane intersections. Accid Anal Prev 124:193–201
Biancardo SA, Russo F, Zhang W, Veropalumbo R (2019) Design criteria for improving safety performance of rural intersections. J Adv Transp 2019:1–10
Tang H, Donnell ET (2019) Application of a model-based recursive partitioning algorithm to predict crash frequency. Accid Anal Prev 132:105274. https://doi.org/10.1016/j.aap.2019.105274
Pradhan B, Sameen MI (2020) Review of traffic accident predictions with neural networks. In: Laser Scanning Systems in Highway and Safety Assessment, pp 97–109
Pradhan B, Sameen MI (2020) Predicting injury severity of road traffic accidents using a hybrid extreme gradient boosting and deep neural network approach. In: Laser Scanning Systems in Highway and Safety Assessment, pp 119–127
Zheng W, Wang HB, Zhang ZM, Li N, Yin PH (2019) Multi-layer feed-forward neural network deep learning control with hybrid position and virtual-force algorithm for mobile robot obstacle avoidance. Int J Control Autom Syst 17(4):1007–1018
Duan S, Yu S, Chen Y, Principe JC (2020) On kernel method–based connectionist models and supervised deep learning without backpropagation. Neural Comput 32(1):97–135
Shin DH, Chung K, Park R (2019) Detection of emotion using multi-block deep learning in a self-management interview app. Appl Sci 9(22):4830–4845
Ghosh R, Vamshi C, Kumar P (2019) RNN based online handwritten word recognition in Devanagari and Bengali scripts using horizontal zoning. Pattern Recogn 92:203–218
Zhang X, Li R, Dai H, Liu Y, Zhou B, Wang Z (2019) Localization of myocardial infarction with multi-lead bidirectional gated recurrent unit neural network. IEEE Access 7:161152–161166
Zhang W, Yu Y, Qi Y, Shu F, Wang Y (2019) Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning. Transportmetrica A: Transp Sci 15(2):1688–1711
Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45(11):2673–2681
Feng K, Pi X, Liu H, Sun K (2019) Myocardial infarction classification based on convolutional neural network and recurrent neural network. Appl Sci 9(9):1879–1890
Abdel-Nasser M, Mahmoud K (2019) Accurate photovoltaic power forecasting models using deep LSTM-RNN. Neural Comput & Applic 31(7):2727–2740
Tong W, Li L, Zhou X, Hamilton A, Zhang K (2019) Deep learning PM 2.5 concentrations with bidirectional LSTM RNN. Air Qual Atmos Health 12(4):411–423
Liu F, Chen Z, Wang J (2019) Video image target monitoring based on RNN-LSTM. Multimed Tools Appl 78(4):4527–4544
Urban traffic information system of Korea. https://www.utic.go.kr:449/main/main.do. Accessed 14 Dec 2019
Voice phishing-keeper of Korea. https://phishing-keeper.fss.or.kr/fss/vstop/main.jsp. Accessed 14 Dec 2019
Ji B, Hong E (2019) Deep-learning-based real-time road traffic prediction using long-term evolution access data. Sensors 19(23):5327–5342
Funding
This work is supported by the Korea Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (Grant 20CTAP-C157011-01).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Park, R.C., Hong, E.J. Urban traffic accident risk prediction for knowledge-based mobile multimedia service. Pers Ubiquit Comput 26, 417–427 (2022). https://doi.org/10.1007/s00779-020-01442-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00779-020-01442-y