<![CDATA[Accurate and efficient traffic data collection is fundamental for sustainable transportation planning. Traditional methods of Average Daily Traffic (ADT) surveys, such as manual counts or pneumatic tubes, are often labor-intensive, costly, and limited in scalability. This paper proposes an integrated ADT survey model that leverages Internet of Things (IoT) sensors and Artificial Intelligence (AI) algorithms to provide real-time, reliable, and scalable traffic monitoring. Using open traffic datasets from Caltrans PeMS (California Performance Measurement System) and Jakarta Open Data as case studies, we designed and simulated an intelligent ADT framework that combines edge IoT devices, cloud-based big-data processing, and AI-based predictive analytics. The proposed methodology is evaluated through simulation and pilot deployment, demonstrating higher ADT estimation accuracy (95%) than traditional approaches, reduced operational costs, and improved adaptability for multimodal transport systems. This research contributes to smart mobility systems, offering practical solutions for urban planners and policymakers in both developed and developing contexts.]]>
Copyrights © 2026
