ARTIFICIAL INTELLIGENCE IN TRAFFIC MANAGEMENT: ENHANCING FLOW EFFICIENCY AND REDUCING CONGESTION

Abstract

This study examined the role of artificial intelligence in traffic management with a focus on enhancing flow efficiency and reducing congestion in urban environments. A quantitative research design was employed, and data were collected from a sample of 320 traffic management professionals along with real-time and historical traffic datasets. Structural modeling and descriptive analysis were applied to evaluate the impact of AI-driven systems, including predictive analytics, adaptive signal control, and IoT-enabled traffic monitoring. The results indicated that adaptive signal control achieved the highest effectiveness with a mean score of 4.18 (83.6%), while artificial intelligence overall recorded 4.12 (82.4%). Predictive analytics showed a mean of 4.05 (81.0%), and traffic flow efficiency reached 4.09 (81.8%). Congestion reduction demonstrated a mean value of 4.14 (82.8%). Performance analysis revealed that IoT-enabled systems achieved 91.0% decision accuracy and 89.3% system efficiency, while adaptive signal control recorded 89.2% real-time responsiveness. The findings further showed a 33.1% improvement in traffic flow, a 31.6% reduction in congestion levels, a 29.4% increase in road utilization, and a 27.3% reduction in travel time. These results confirmed that AI integration significantly improved traffic management outcomes and supported the development of efficient and sustainable urban mobility systems.

Keywords : Adaptive Signal Control, Artificial Intelligence, Congestion Reduction, Intelligent Transportation Systems, Traffic Flow Efficiency, Urban Mobility.