Urban transportation systems in rapidly growing cities face significant challenges, including traffic congestion, pollution, and inefficiencies. This paper proposes an adaptive transportation framework for Juarez City, Mexico, leveraging the integration of Internet of Things (IoT), machine learning (ML), and the Komodo Optimization Algorithm (KOA). The framework aims to optimize traffic flow, reduce congestion, and enhance public transportation efficiency by utilizing real-time traffic and climate data. A mixed-methods approach is employed, combining quantitative data analysis from IoT sensors and public datasets with qualitative insights from stakeholder interviews. Machine learning models, including regression and time-series algorithms, are developed to predict traffic patterns and optimize routing strategies. KOA is implemented to refine transportation strategies, ensuring adaptability to dynamic urban conditions. Preliminary results demonstrate the potential of the proposed system to improve urban mobility and resilience. This research contributes to the growing body of knowledge on smart city transportation systems and offers practical solutions for cities facing similar challenges. The findings are expected to provide valuable insights for urban planners and policymakers, fostering sustainable and efficient transportation systems in rapidly urbanizing environments.