Autonomous Lane Change Decision-Making Using Optimized Deep Learning Models for Intelligent Transportation Systems

This research presents an intelligent lane change decision-making framework based on optimized deep learning models and traffic prediction techniques. The system integrates traffic prediction with behavioral decision logic to support safe and efficient autonomous vehicle navigation in dynamic traffic environments. A Deep Extreme Learning Machine (DELM) model optimized using swarm intelligence algorithms, including Particle Swarm Optimization (PSO) and Harris Hawks Optimization (HHO), is used to analyze traffic conditions and generate adaptive lane change decisions. The framework utilizes real-time traffic camera data and incorporates temporal and spatial traffic features to improve decision reliability. The proposed approach supports intelligent transportation systems and smart city infrastructure by improving road safety, reducing congestion, and enabling adaptive driving strategies.