The COVID-19 pandemic profoundly impacted social dynamics and individuals' lifestyles worldwide, leading to significant changes in traffic density and vehicle usage habits. This study analyzes the changes in urban traffic density and individual vehicle usage habits in Balıkesir province during the pandemic period (2021-2022) and the post-pandemic normalization period (2023-2024). Within the scope of the research, vehicle passage densities at 19 signalized intersections in the city center of Balıkesir were examined, and predictive models were created using machine learning methods such as linear regression and the Random Forest algorithm. The findings reveal that traffic flows in economically active areas, such as industrial zones, were less affected by the pandemic, whereas traffic density significantly decreased in commercial and social centers. Additionally, an increase in individual vehicle usage and a decline in public transportation preferences during the pandemic period were observed. The study also explores recovery trends in post-pandemic traffic flow and intersection-based differences in detail. This study underscores the importance of traffic data obtained during the pandemic for sustainable traffic management and transportation planning. At the end of the study, solutions such as the integration of intelligent traffic systems, the promotion of environmentally friendly transportation modes, and increasing the appeal of public transportation systems were proposed. These findings are expected to guide decision-makers in improving urban traffic dynamics and preparing for similar crises in the future.
Intelligent transportation systems intersection analysis signalization systems traffic density COVID-19
The COVID-19 pandemic profoundly impacted social dynamics and individuals' lifestyles worldwide, leading to significant changes in traffic density and vehicle usage habits. This study analyzes the changes in urban traffic density and individual vehicle usage habits in Balıkesir province during the pandemic period (2021-2022) and the post-pandemic normalization period (2023-2024). Within the scope of the research, vehicle passage densities at 19 signalized intersections in the city center of Balıkesir were examined, and predictive models were created using machine learning methods such as linear regression and the Random Forest algorithm. The findings reveal that traffic flows in economically active areas, such as industrial zones, were less affected by the pandemic, whereas traffic density significantly decreased in commercial and social centers. Additionally, an increase in individual vehicle usage and a decline in public transportation preferences during the pandemic period were observed. The study also explores recovery trends in post-pandemic traffic flow and intersection-based differences in detail. This study underscores the importance of traffic data obtained during the pandemic for sustainable traffic management and transportation planning. At the end of the study, solutions such as the integration of intelligent traffic systems, the promotion of environmentally friendly transportation modes, and increasing the appeal of public transportation systems were proposed. These findings are expected to guide decision-makers in improving urban traffic dynamics and preparing for similar crises in the future.
Intelligent transportation systems intersection analysis signalization systems traffic density COVID-19
Primary Language | English |
---|---|
Subjects | Artificial Intelligence (Other) |
Journal Section | Articles |
Authors | |
Early Pub Date | December 30, 2024 |
Publication Date | December 30, 2024 |
Submission Date | December 16, 2024 |
Acceptance Date | December 27, 2024 |
Published in Issue | Year 2024 Volume: 8 Issue: 2 |