Forecasting the Number of Road Accidents in Poland Depending on the Day of the Week Using Neural Networks

A very large number of people are killed on the roads. Although the value is decreasing from year to year and the pandemic has reduced the number of traffic accidents even further, the number is still very high. For this reason, it is necessary to find out on which days of the week the highest number of traffic accidents occur, and to know the accident forecast for the coming years, so that we can do everything possible to minimize the analyzed value. The aim of the article is to develop a forecast of the number of road accidents in Poland depending on the days of the week. For this purpose, monthly data on the number of road accidents in Poland by days of the week were analyzed on the basis of Police data. Based on this data, a forecast of the number of road accidents for 2022-2024 was made in Statistica software. Selected neural network models were used to forecast the number of road accidents. The results show that we can still expect a reduction in the number of road accidents on Polish roads, but the prevailing pandemic disturbs the results obtained. The choice of the number of random samples (learning, testing and validation) affects the obtained results.

• Record URL:
  • https://doi.org/10.3311/PPtr.22203
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/15873811
• Supplemental Notes:
  • © 2023 Budapest University of Technology and Economics. All rights reserved.
• Authors:
  • Gorzelańczyk, Piotr
  • 0000-0001-9662-400X
• Publication Date: 2023

Language

• English

Media Info

• Media Type: Web
• Features: Figures; References; Tables;
• Pagination: pp 431-435
• Serial:
  • Periodica Polytechnica Transportation Engineering
  • Volume: 51
  • Issue Number: 4
  • Publisher: Budapest University of Technology and Economics
  • ISSN: 1587-3811
  • Serial URL: http://www.pp.bme.hu/tr/index
• Publication flags:

  Open Access (libre)

Subject/Index Terms

• TRT Terms: Crash data; Crash risk forecasting; Data analysis; Neural networks; Predictive models; Weekdays
• Geographic Terms: Poland
• Subject Areas: Data and Information Technology; Highways; Safety and Human Factors;

Filing Info

• Accession Number: 01944152
• Record Type: Publication
• Files: TRIS
• Created Date: Jan 28 2025 9:18AM