As the majority of faults are found in a few of its modules so there is a need to investigate the modules that are affected severely as compared to other modules and proper maintenance need to be done in time especially for the critical applications. In this present work, hybrid fuzzy-Genetic Algorithm and Particle Swarm Optimization trained Neural Network techniques are empirically evaluated and earlier published results of the Mamdani Based Fuzzy Inference System and Neuro-Fuzzy Based techniques are also discussed for the comparative analysis in order to predict level of impact of faults in NASA’s public domain defect dataset coded in Perl programming language. The results are recorded in terms of accuracy, mean absolute error (MAE) and root mean squared error (RMSE). The results of Neuro-Fuzzy model are also convincing but Fuzzy-GA based hybrid model provide relatively better prediction accuracy as compared to other models and hence, it is proposed for the maintenance severity prediction of the software systems.
Key words: Fuzzy, neuro-fuzzy, genetic algorithm, particle swarm optimization (PSO), accuracy, MAE, RMSE.
Copyright © 2018 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0