Employing neural networks to predict the number of incidents on specific types of Polish roads
Piotr Gorzelańczyk | Stanisław Staszic State University of Applied Sciences in Piła
ORCID 0000-0001-9662-400X
Janusz Drzewiecki | Stanisław Staszic State University of Applied Sciences in Piła
ORCID 0009-0009-0173-0981
„Bezpieczeństwo. Teoria i Praktyka”, 3/2024, s. 125-139
DOI 10.48269/2451-0718-btip-2024-3-009
PDF: English
Abstract: The article’s goal is to predict how many accidents will occur on different types of roads in Poland. This was accomplished by the analysis of annual data on the number of traffic accidents in Poland by type of road. A prediction for the years 2022–2040 was developed using police statistics. The frequency of accidents in Poland was anticipated using a few neural network models. The findings indicate that we can still expect a stabilization of the number of road accidents. This is impacted by the rise in traffic on Polish roads and the construction of new highways. The number of learning, test, and validation samples chosen at random has an impact on the outcomes.
Key words: road accident, pandemic, forecasting, neural networks
Prognozowanie liczby wypadków drogowych w Polsce dla poszczególnych rodzajów dróg przy wykorzystaniu sieci neuronowych