Safe Route - IoT and AI-based Fire Evacuation System for Smart Buildings

This research introduces an innovative approach using IoT sensors and Ant Colony Optimization (ACO) to optimize evacuation routes in emergency preparedness. The system architecture allows for seamless communication between IoT sensors and the ACO algorithm, enabling timely decision-making in emergency scenarios. The study uses diverse datasets to enhance adaptability and comprehensiveness, paving the way for a transformative paradigm in fire safety for smart buildings. The ACO algorithm's performance is compared with Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Artificial Bee Colony (ABC) algorithm. Evaluation criteria include convergence time, number of iterations, and total running time. Results show that the ACO algorithm consistently outperforms or matches other algorithms across all graph complexities. It converges faster and achieves shorter runtimes, with improvements becoming more pronounced as graph complexity increases. The ACO algorithm's effectiveness in solving complex shortest path problems is demonstrated through rigorous analysis and comparison.