Implementation of Hybrid Particle Swarm Optimization for Optimized Regression Testing

Abstract

Software test case optimization improves the efficiency of the software by proper structure and reduces the fault in the software. The existing research applies various optimization methods such as Genetic Algorithm, Crow Search Algorithm, Ant Colony Optimization, etc., for test case optimization. The existing methods have limitations of lower efficiency in fault diagnosis, higher computational time, and high memory requirement. The existing methods have lower efficiency in software test case optimization when the number of test cases is high. This research proposes the Tournament Winner Genetic Algorithm (TW-GA) method to improve the efficiency of software test case optimization. Hospital Information System (HIS) software was used to evaluate TW-GA model performance in test case optimization. The tournament Winner in the proposed method selects the instances with the best fitness values and increases the exploitation of the search to find the optimal solution. The TW-GA method has higher exploitation that helps to find the mutant and equivalent mutation that significantly increases fault diagnosis in the software. The TW-GA method discards the information with a lower fitness value that reduces the computational time and memory requirement. The TW-GA method requires 5.47 s and the MOCSFO method requires 30 s for software test case optimization.