Forecasting the number of road accidents caused by pedestrians in Poland using neural networks

Gorzelańczyk, Piotr (2024) Forecasting the number of road accidents caused by pedestrians in Poland using neural networks. COGNITIVE SUSTAINABILITY, 3 (4). pp. 5-15. ISSN 2939-5240

Preview

Text 20490-ArticleText-81588-1-10-20250904.pdf - Published Version Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB) | Preview

Abstract

Every year, fewer traffic accidents occur in Poland and throughout the world. Pandemics have recently impacted this number, but it is still relatively high. All efforts should be made to lower this figure. The article's main goal is to project the number of pedestrian-related traffic accidents in Poland based on yearly statistics. from 2001. A projection for the years 2024–2030 was created using police data. Various neural network models were employed to predict the number of incidents. The findings indicate that a stabilisation in traffic accidents is yet to be expected. One way to look at this is as a result of both Poland’s population reduction and the growing number of cars on the road. The number of random samples (training, test, and validation) selected has little effect on the outcomes (Road safety statistics in the EU, 2024, Poland Population, 2024, Poland Number of Registered, 2024).

Actions (login required)

Edit Item