Analyzing of Total Number of Railway Accidents in Türkiye via Different Computational Models

Year 2023, Volume: 16 Issue: 3, 782 - 799, 31.12.2023

Ziya Çakıcı , Ali Mortazavi , Oruç Altıntaşı

https://doi.org/10.18185/erzifbed.1294815

Abstract

Accurate prediction of transport-related accidents is considered an important step in assessing the magnitude of the transport-related problems and accelerating decision-making to mitigate them. Therefore, such studies are of great importance for decision makers. In this study, it is aimed to accurately determine (estimate) the annual total number of railway accidents in Türkiye, considering the track length, train-km and Gross National Product (GNP) variables obtained from Türkiye Statistical Institute. In this context, firstly, four different computational models, three of which are optimization-based (one linear, the others nonlinear) and one based on Artificial Neural Network (ANN), are created. Subsequently, the goal was to minimize the Mean Square Error (MSE) between the observed and modeled data for each computational model developed. In the optimization-based models, the selection of the most suitable internal weighting coefficients was accomplished by utilizing the Differential Evolution Algorithm. Finally, within the scope of the study, all statistical results (mean square error, coefficient of determination) obtained for four different calculation models are compared with each other. Consequently, the analysis of the total number of railway accidents in Türkiye reveals that the quadratic model yields more realistic results compared to the other models.

Keywords

railway accident, differential evolution algorithm, artificial neural networks, linear model, non-linear model

References

• [1] Meng, H., Tong, X., Zheng, Y., Xie, G., Ji, W., & Hei, X. (2022). Railway accident prediction strategy based on ensemble learning. Accident Analysis & Prevention, 176, 106817.
• [2] Liu, J., Schmid, F., Li, K., & Zheng, W. (2021). A knowledge graph-based approach for exploring railway operational accidents. Reliability Engineering & System Safety, 207, 107352.
• [3] Hadj-Mabrouk, H. (2020). Analysis and prediction of railway accident risks using machine learning. AIMS Electronics and Electrical Engineering, 4(1), 19-46.
• [4] Kyriakidis, M., Majumdar, A., & Ochieng, W. Y. (2015). Data based framework to identify the most significant performance shaping factors in railway operations. Safety science, 78, 60-76.
• [5] San Kim, D., & Yoon, W. C. (2013). An accident causation model for the railway industry: Application of the model to 80 rail accident investigation reports from the UK. Safety science, 60, 57-68.
• [6] Gibson, W. H., Mills, A. M., Smith, S., & Kirwan, B. K. (2012). Railway action reliability assessment, a railway specific approach to human error quantification. Rail Human Factors. Supporting reliability, safety and cost reduction.
• [7] Ghofrani, F., He, Q., Goverde, R. M., & Liu, X. (2018). Recent applications of big data analytics in railway transportation systems: A survey. Transportation Research Part C: Emerging Technologies, 90, 226-246.
• [8] Ye, F., & Lord, D. (2014). Comparing three commonly used crash severity models on sample size requirements: Multinomial logit, ordered probit and mixed logit models. Analytic methods in accident research, 1, 72-85.
• [9] Iranitalab, A., & Khattak, A. (2017). Comparison of four statistical and machine learning methods for crash severity prediction. Accident Analysis & Prevention, 108, 27-36.
• [10] Akalın, K. B. (2016). Investigation of factors affecting tram accident severity with multinomial logit model”. MSc thesis, Eskisehir, Turkey: Eskisehir Osmangazi University.
• [11] Dabbour, E., Easa, S., & Haider, M. (2017). Using fixed-parameter and random-parameter ordered regression models to identify significant factors that affect the severity of drivers’ injuries in vehicle-train collisions. Accident Analysis & Prevention, 107, 20-30.
• [12] Liu, J., & Khattak, A. J. (2017). Gate-violation behavior at highway-rail grade crossings and the consequences: using geo-spatial modeling integrated with path analysis. Accident Analysis & Prevention, 109, 99-112.
• [13] Liu, X., Saat, M. R., & Barkan, C. P. (2017). Freight-train derailment rates for railroad safety and risk analysis. Accident Analysis & Prevention, 98, 1-9.
• [14] Baysari, M. T., McIntosh, A. S., & Wilson, J. R. (2008). Understanding the human factors contribution to railway accidents and incidents in Australia. Accident Analysis & Prevention, 40(5), 1750-1757.
• [15] Iranitalab, A., & Khattak, A. (2020). Probabilistic classification of hazardous materials release events in train incidents and cargo tank truck crashes. Reliability Engineering & System Safety, 199, 106914.
• [16] Mirabadi, A., & Sharifian, S. (2010). Application of association rules in Iranian Railways (RAI) accident data analysis. Safety Science, 48(10), 1427-1435.
• [17] Wujie, J., Le, J., & Cheng, Z. (2022). Analyzing and predicting railway operational accidents based on fishbone diagram and Bayesian networks. Tehnički vjesnik, 29(2), 542-552.
• [18] Bridgelall, R., & Tolliver, D. D. (2021). Railroad accident analysis using extreme gradient boosting. Accident Analysis & Prevention, 156, 106126.
• [19] Li, Z., Liu, P., Wang, W., & Xu, C. (2012). Using support vector machine models for crash injury severity analysis. Accident Analysis & Prevention, 45, 478-486.
• [20] Evans, A. W. (2021). Fatal train accidents on Europe’s railways: An update to 2019. Accident Analysis & Prevention, 158, 106182.
• [21] Tan, E., Sadak, D., & Ayvaz, M. T. (2020). Optimum design of sewer systems by using differential evolution algorithm. Turkish Journal of Civil Engineering, 31(5), 10229–10250.
• [22] Kamal, M., & Inel, M. (2019). Optimum design of reinforced concrete continuous foundation using differential evolution algorithm. Arabian Journal for Science and Engineering, 44, 8401-8415.
• [23] Sriboonchandr, P., Kriengkorakot, N., & Kriengkorakot, P. (2019). Improved differential evolution algorithm for flexible job shop scheduling problems. Mathematical and Computational Applications, 24(3), 80.
• [24] Baskan, O. (2019). A multiobjective bilevel programming model for environmentally friendly traffic signal timings. Advances in Civil Engineering, 2019, 1-13.
• [25] Abdelkader, E. M., Al-Sakkaf, A., Alfalah, G., & Elshaboury, N. (2022). Hybrid Differential Evolution-Based Regression Tree Model for Predicting Downstream Dam Hazard Potential. Sustainability, 14(5), 3013.
• [26] Yu, X., Jiang, N., Wang, X., & Li, M. (2023). A hybrid algorithm based on grey wolf optimizer and differential evolution for UAV path planning. Expert Systems with Applications, 215, 119327.
• [27] Elçi, A., & Ayvaz, M. T. (2014). Differential-evolution algorithm based optimization for the site selection of groundwater production wells with the consideration of the vulnerability concept. Journal of Hydrology, 511, 736-749.
• [28] Murat, Y. S., & Ceylan, H. (2006). Use of artificial neural networks for transport energy demand modeling. Energy policy, 34(17), 3165-3172.
• [29] Njoh, A. J. (2000). Transportation infrastructure and economic development in sub-Saharan Africa. Public Works Management & Policy, 4(4), 286-296.
• [30] Ali, G. A., Al-Alawi, S. M., & Bakheit, C. S. (1998). A comparative analysis and prediction of traffic accident causalities in the Sultanate of Oman using artificial neural networks and statistical methods. Sultan Qaboos University Journal for Science, 3, 11-20.
• [31] Shaik, M. E., Islam, M. M., & Hossain, Q. S. (2021). A review on neural network techniques for the prediction of road traffic accident severity. Asian Transport Studies, 7, 100040.
• [32] https://www.tuik.gov.tr/
• [33] Sonmez, M., Akgüngör, A. P., & Bektaş, S. (2017). Estimating transportation energy demand in Turkey using the artificial bee colony algorithm. Energy, 122, 301-310.
• [34] Ceylan, H., Ceylan, H., Haldenbilen, S., & Baskan, O. (2008). Transport energy modeling with meta-heuristic harmony search algorithm, an application to Turkey. Energy policy, 36(7), 2527-2535.
• [35] Korkmaz, E., & Akgüngör, A. P. (2018). Flower pollination algorithm approach for the transportation energy demand estimation in Turkey: model development and application. Energy Sources, Part B: Economics, Planning, and Policy, 13(11-12), 429-447.
• [36] Baskan, O., & Ceylan, H. (2014). Differential evolution algorithm based solution approaches for solving transportation network design problems. Pamukkale University Journal of Engineering Sciences, 20(9), 324-331.
• [37] Baskan, O., Ceylan, H., & Ozan, C. (2020). Investigating acceptable level of travel demand before capacity enhancement for signalized urban road networks. Turkish Journal of Civil Engineering, 31(2), 9897-9917.
• [38] Cheng, C. J. (2008). Robust control of a class of neural networks with bounded uncertainties and time-varying delays. Computers & Mathematics with Applications, 56(5), 1245-1254.
• [39] Sum, J., & Leung, A. C. S. (2008). Prediction error of a fault tolerant neural network. Neurocomputing, 72(1-3), 653-658.