Traffic Prediction and Optimization Using Deep Extreme Learning Machine with Swarm Intelligence for Intelligent Transportation Systems

This research presents a machine learning-based framework for traffic prediction and optimization using a Deep Extreme Learning Machine (DELM) optimized with swarm intelligence algorithms, specifically Particle Swarm Optimization (PSO) and Harris Hawks Optimization (HHO). The system integrates a robust data preprocessing pipeline designed to handle real-time traffic data from traffic camera networks. Variational Mode Decomposition (VMD) was applied to manage non-linear traffic signals before model training. The proposed approach demonstrates improved scalability and predictive capability for intelligent transportation systems and smart city environments. The framework supports real-time traffic monitoring, congestion prediction, and autonomous vehicle decision-making.