The College of Computer Science and Information Technology recently hosted the defense of a Master’s thesis

The College of Computer Science and Information Technology recently hosted the defense of a Master’s thesis titled “Improving Traffic Flow Using Swarm Intelligence Techniques” by student Ali Hassan Ahmed.

Dr. Shahla Othman Omar supervises the thesis, the study aimed to evaluate the performance of six individual swarm intelligence algorithms—Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Elephant Herding Optimization (EHO), Grey Wolf Optimizer (GWO), Social Spider Optimization (SSO), and Whale Optimization Algorithm (WOA)—in optimizing traffic routes. The research also analyzed hybrid models derived from these algorithms.

Using a multi-objective framework with the Analytic Hierarchy Process (AHP) and the entropy method to calculate weights, the study analyzed the algorithms’ efficiency based on key metrics: execution time, memory consumption, number of iterations to convergence, and time to reach the optimal solution.

The study concluded that the PSO algorithm achieved the fastest execution time, while EHO recorded the fewest iterations and the shortest time to convergence. Furthermore, the hybrid models outperformed the individual algorithms, demonstrating their effectiveness in complex traffic environments.

The researcher recommended expanding the study to include more realistic traffic networks with thousands of nodes. The thesis also suggested applying the algorithms to embedded controllers linked to live traffic data (GPS, sensors, cameras) to ensure continuous updates and practical validation of their efficiency.