Intelligent transportation systems: Machine learning approaches for urban mobility in smart cities

Urban mobility in smart cities presents a complex challenge, demanding innovative solutions to address the ever-growing demands of transportation systems. This paper introduces a comprehensive approach that integrates machine learning techniques into the optimization of urban transportation. The proposed framework employs a multilayer objective function and incorporates constraints, considering factors such as interaction cost between transportation modes, energy consumption, and environmental impact. Leveraging a modified Teaching-Learning Based Optimization (TLBO) algorithm and a hybrid Artificial Neural Network-Recurrent Neural Network (ANN-RNN) technique, the model aims to enhance system adaptability and efficiency. In contrast to existing research, our work emphasizes a holistic optimization strategy that balances both the efficiency and sustainability of urban transportation. The outcomes of this research contribute to the advancement of Intelligent Transportation Systems, offering a nuanced understanding of system dynamics and providing a foundation for resilient and adaptive transportation networks in the evolving landscape of smart cities.