The Use of Multimodal Service Level and Artificial Neural Networks for the Improvement of Public Transport

Abstract

Abstract Most of the major modern cities of the world face problems due to traffic conditions. However, in the last decade the degree of motorization combined with increased urbanization and population density causes excess traffic capacity during peak hours on the main streets of already congested cities. In these circumstances, public transport should provide a reliable and alternative choice for daily travel. The article is focused on the development of models to quantify the environment in which public transport operates and the quality of services. Also, the use of artificial neural network as a tool for assisted analysis of all traffic components can help local authorities to improve the performance of public transport service. In addition, improvements in the reliability of public transport service can reduce travel costs and change the modal split.