Prediction of traffic accidents on suburban roads Isfahan Province using recurrent neural networks

Document Type : Original Article

Authors
Farzad Mirzaei Shenatalolia 1
Amir Masoud Rahimi 2
1 M.Sc., Student, Civil Engineering Department, Faculty of Engineering, University of Zanjan, Zanjan, Iran.
2 Associate Professor, Civil Engineering Department, Faculty of Engineering, University of Zanjan, Zanjan, Iran.
10.22034/road.2024.424485.2219
Abstract
Deep learning techniques play crucial role in today's modern world. In recent years, the recurrent neural network has led to extensive research for predicting time series. This study tries to take into account time series dependencies using recurrent neural network. Based on long-short-term memory algorithm, to predict the severity of driving injuries based on 10,269 random records that occurred on the roads of Isfahan province from 2018 to December 2021, it should be designed and implemented. To do this, several network architectures and configurations were tested through a systematic grid search to determine an optimal network for predicting the injury severity of traffic accidents. The selected network architecture is fully composed of seven independent variables, a long-short-term memory layer with 64 input nodes, and an output layer with a softmax function. Also, in order to understand the advantages and better comparison in this model, two optimal algorithms including the random gradient descent algorithm and Adam's optimal algorithm were also compared, So that the results of the model on the network showed that Adam's optimal algorithm works better than the random gradient descent algorithm because the accuracy of the model when using Adam's algorithm is equal to It became 73.26%, while for the random gradient descent algorithm, the accuracy of the model reached 68.20%. The findings of this study showed that the recurrent neural network model in the framework of deep learning can be a promising tool for predicting the severity of accidents.
Keywords
Deep Learning
Recurrent Neural Network
Long-Short-Term Memory
Softmax
Adam's Optimal Algorithm
Stochastic Gradient Descent Algorithm
- برادران رحمانیان و کی منش، محمودرضا (2021). پیش بینی شدت تصادفات جاده­ای با استفاده از شبکه عصبی مصنوعی و مقایسه آن با روش آنالیز چند متغیره. نشریه جاده، دوره 29، شماره(106)، 1-10.
-Afandizadeh, M. Ziyadi Rezaie Moghaddam, F. (2011). Prediction of accident severity using artificial neural networks. International Journal of Civil Engineering, 9(1): 41-48.
-Aghayan, Kunt and N. Noii (2011). Prediction for traffic accident severity: comparing the artificial neural network, genetic algorithm, combined genetic algorithm and pattern search methods. Transport 26(4): 353-366.
-Anderson, A .Mokhtarimousavi, Azizinamini and M. Hadi (2020). Factors affecting injury severity in vehicle-pedestrian crashes: A day-of-week analysis using random parameter ordered response models and Artificial Neural Networks. International Journal of Transportation Science and Technology, 9(2): 100-115.
-Antić, Jovanović, Lipovac, Vujanić and Pešić (2013). Bottom-Up" and" Top-Down" Approach for Defining Road Safety Strategy-Case Study: City of Belgrade. International Journal for Traffic & Transport Engineering, 3(2).
-Abdel-Aty, Cai, Gong and Yuan, J (2019). Real-time crash risk prediction using long short-term memory recurrent neural network. Transportation Research Record, 2673(4): 314-326.
 -B. Pradhan and Sameen, M. I. (2017). Severity prediction of traffic accidents with recurrent neural networks. Applied Sciences, 7(6): 476.
-Bai, Y., J. Xie, C. Liu, Y. Tao, B. Zeng and C. Li (2021). Regression modeling for enterprise electricity consumption: A comparison of recurrent neural network and its variants. International Journal of Electrical Power & Energy Systems, 126: 106612.
-Bargegol, I., V. N. M. Gilani, M. Ghasedi and M. Ghorbanzadeh (2016). Delay modeling of un-signalized roundabouts using neural network and regression. Computational Research Progress in Applied Science & Engineering, 2(1): 28-34.
-Chakraborty, A., D. Mukherjee and S. Mitra (2019). Development of pedestrian crash prediction model for a developing country using artificial neural network. International Journal of Injury Control and Safety Promotion, 26(3): 283-293.
-Chen, Cui, Zheng, Li, Zhu, M., Ma, Tang, and Wang (2019). Traffic accident’s severity prediction: A deep-learning approach-based CNN network. IEEE Access, 7: 39897-39910.
-Ghasedi, M., M. Sarfjoo and I. Bargegol (2021). Prediction and analysis of the severity and number of suburban accidents using logit model, factor analysis and machine learning: a case study in a developing country. SN Applied Sciences, 3(1):1-16.
 
-Hossain, Islam and Shaik, M. E. (2021). A review on neural network techniques for the prediction of road traffic accident severity. Asian Transport Studies 7,100040.
-Lee, J., T. Yoon, S. Kwon and J. Lee (2019). Model evaluation for forecasting traffic accident severity in rainy seasons using machine learning algorithms: Seoul city study. Applied Sciences, 10(1): 129.
-K. Ksaibati, S. Nazneen and Rezapour, M. (2020). Application of deep learning techniques in predicting motorcycle crash severity. Engineering Reports 2(7): e12175.
-Khayamim Imaninasab and Shiran, G.(2021). Crash Severity Analysis of Highways Based on Multinomial Logistic Regression Model, Decision Tree Techniques, and Artificial Neural Network: A Modeling Comparison. Sustainability, 13(10): 5670.
- Liu, Y. Hu and J. Lei ,Ren, H., Y. Song, J. (2017). A deep learning approach to the prediction of
short-term traffic accident risk. arXiv preprint arXiv,1710.09543.
-G. Zhang,T. Ma, Yu, H., P. Liu and Z. Li, (2021). Fusion convolutional neural network-based interpretation of unobserved heterogeneous factors in driver injury severity outcomes in single-vehicle crashes. Analytic Methods in Accident Research, 30: 100157.
-Guerrero, Jinadasa, Maegga and Zimmerman, K. (2015). Road traffic injury on rural roads in Tanzania: measuring the effectiveness of a road safety program. Traffic Injury Prevention, 16(5):
456-460.
-Organization, W. H. (2019). Global status report on alcohol and health 2018, World Health Organization.
Qian, Y., X. Zhang, G. Fei, Q. Sun, X. Li, L. Stallones and H. Xiang (2020). Forecasting deaths of road traffic injuries in China using an artificial neural network. Traffic injury Prevention, 21(6): 407-412.