Enhancing Urban Mobility: Intelligent Traffic Control Systems Using Machine Learning Algorithms

Abstract

This study investigates the impact of Intelligent Traffic Control Systems (ITCS) on vulnerable road user categories and evaluates the performance of various machine learning models in the context of urban mobility enhancement. Simulated data was generated for Young Novice Drivers, Older Drivers, and Pedestrians/Bicyclists, with impact percentages derived from literature reviews and hypothetical scenarios. Bar graphs and pie charts visually represented the extent of improvement for each road user category. Subsequently, the study evaluated the performance of Time Series Models, Regression Models, and Artificial Neural Networks, employing simulated accuracy percentages. Bar graphs, pie charts, and a line graph were utilized to illustrate the varying performances of these models. The methodology integrates simulated data and visualization techniques to offer a holistic representation of ITCS impact and machine learning model performance. The results highlight significant improvements in urban mobility, with distinct impacts on different road user categories. Machine learning models, particularly Artificial Neural Networks, demonstrated varying levels of efficacy. The findings contribute to discussions on the targeted application and optimization of ITCS for diverse user groups, guiding informed decision-making for urban planners and policymakers.