The Use of Neural Networks to Predict Frequency of Road Accidents in Poland and Slovenia
Downloads
Despite a general decline in recent years, road accidents are still a major problem worldwide, including in Poland and Slovenia. Even if there is no denying that the COVID-19 epidemic has had an impact on accident rates, the statistics nonetheless show that urgent action is required to further lower their frequency. The purpose of this study is to project how many traffic accidents will occur in Slovenia and Poland between 2024 and 2030. This was accomplished by analysing historical data on yearly accident incidence from Eurostat and the Polish Police. To create the predicted numbers, certain neural network models were used, utilising these datasets. The results indicate that the number of road accidents is likely to stabilise soon. This forecast is influenced by a number of factors, including the continued increase in car ownership and the ongoing development of road infrastructure, including the construction of new motorways and roads. It is important to remember that the accuracy of the forecast is susceptible to inherent limitations due to the random sampling of the data used to test, validate and train the models.
Downloads
Abdullah E, Emam A. Traffic accidents analyzer using big data. In: Proceedings of the 2015 International Conference on Computational Science and Computational Intelligence (CSCI 2015). Institute of Electrical and Electronics Engineers (IEEE); 2016. p. 392-397. DOI: 10.1109/CSCI.2015.187
Al-Madani H. Global road fatality trends’estimations based on country-wise microlevel data, Accident Analysis & Prevention. 2018;111:297–310, DOI: 10.1016/j.aap.2017.11.035
Arteaga C, Paz A, Park J. Injury severity on traffic crashes: A text mining with an interpretable machine-learning approach. Safety Science. 2020;132:104988. DOI: 10.1016/j.ssci.2020.104988
Bąk I, Cheba K, Szczecińska B. The statistical analysis of road traffic in cities of Poland. Transportation Research Procedia, 2019;39:14-23, DOI: 10.1016/j.trpro.2019.06.003
Biswas AA, Mia J, Majumder A. Forecasting the Number of Road Accidents and Casualties using Random Forest Regression in the Context of Bangladesh. In Proceedings of the 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kanpur, India, 6-8 July 2019.
Bloomfield P. An exponential model in the spectrum of a scalar time series. Biometrika 1973;60:217–226 https://www.jstor.org/stable/2334533
Central Statistical Office. 2022. www.gus.pl [Accessed 12th May 2022].
Chand A, Jayesh S, Bhasi AB. Road traffic accidents: An overview of data sources, analysis techniques and contributing factors, Materials Today: Proceedings. 2021:47:5135-5141. DOI: 10.1016/j.matpr.2021.05.415
Chen C. Analysis and forecast of traffic accident big data. ITM Web Conf., 2017:12:04029. DOI: 10.1051/itmconf/20171204029
Chudy-Laskowska K, Pisula T. Forecasting the number of road accidents in Subcarpathia. Logistics. 2015:4.
Chudy-Laskowska K, Pisula T. Forecast of the number of road accidents in Poland. Logistics. 2014:6
Data mining techniques StatSoft. 2022. https://www.statsoft.pl/textbook/stathome_stat.html?https%3A%2F%2Fwww.statsoft.pl%2Ftextbook%2Fstdatmin.html [Accessed 12th May 2022].
Dudek G. Exponential smoothing models for short-term power system load forecasting. Energy market. 2013:3:106.
Dudek G. Forecasting time series with multiple seasonal cycles using neural networks with local learning. In: Rutkowski L, et al. (eds) Artificial Intelligence and Soft Computing. ICAISC 2013. Lecture Notes in Computer Science,7894. Springer, Berlin, Heidelberg. DOI: 10.1007/978-3-642-38658-9_5
Dutta B, Barman MP, Patowary AN. Application of Arima model for forecasting road accident deaths in India. International Journal of Agricultural and Statistical Sciences. 2020;16:2:607-615.
Fijorek K, Mróz K, Niedziela K, Fijorek D. Forecasting electricity prices on the day-ahead market using data mining methods. Energy Market. 2010;12.
Fiszeder P. GARCH class models in empirical financial research. Scientific Publishers of the Nicolaus Copernicus University. Torun 2009.
Forecasting based on time series. 2022. http://pis.rezolwenta.eu.org/Materialy/PiS-W-5.pdf [Accessed 12th May 2022].
Gorzelanczyk P, Pyszewska D, Kalina T, Jurkovic M. Analysis of road traffic safety in the Pila poviat. Scientific Journal of Silesian University of Technology. Series Transport. 2020;107:33-52. DOI: 10.20858/sjsutst.2020.107.3
Helgason A, Fractional integration methods and short time series: Evidence from asimulation study, Political Analysis. 2016;24:1:59–68. http://www.jstor.org/stable/24573204
Statistic Road Accident 2022 https://statystyka.policja.pl/ [Accessed 12th May 2022].
Eurostat 2022 https://ec.europa.eu/eurostat/data/database [Accessed 12th May 2022].
Lake BM, Ullman TD, Tenenbaum JB, Gershman SJ. Building machines that learn and think like people. Behaviour Brain Sciences 2017;40:e253.
Becoming Human. How Netflix uses AI, data science, and machine learning – from a product perspective. 2022. www.becominghuman.ai [Accessed 12th May 2022].
Forbes. The amazing ways eBay is using Artificial Intelligence to boost business success. 2022. www.forbes.com [Accessed 12th May 2022].
Wu Y, et al. Google’s neural machine translation system: Bridging the gap between human and machine translation. ArXiv. 2022;1609.08144. www.arxiv.org [Accessed 12th May 2022].
Oronowicz-Jaśkowiak W. The application of neural networks in the work of forensic experts in child abuse cases. Advances in Psychiatry and Neurology. 2019;28(4):273-282. DOI: 10.5114/ppn.2019.92489
Copyright (c) 2026 Piotr GORZELAŃCZYK, Marina ZANNE
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
