Hybrid functional link artificial neural network approach for predicting maintainability of object-oriented software

Abstract

In present day, software development methodology is mostly based on object-oriented paradigm. With the increase in the number of these software system, their effective maintenance aspects becomes a crucial factor. Most of the maintainability prediction models in literature are based on techniques such as regression analysis and simple neural network. In this paper, three artificial intelligence techniques (AI) such as hybrid approach of functional link artificial neural network (FLANN) with genetic algorithm (GA), particle swarm optimization (PSO) and clonal selection algorithm (CSA), i.e., FLANN-Genetic (FGA and AFGA), FLANN-PSO (FPSO and MFPSO), FLANN-CSA (FCSA) are applied to design a model for predicting maintainability. These three AI techniques are applied to predict maintainability on two case studies such as Quality Evaluation System (QUES) and User Interface System (UIMS). This paper also focuses on the effectiveness of feature reduction techniques such as rough set analysis (RSA) and principal component analysis (PCA) when they are applied for predicting maintainability. The results show that feature reduction techniques are very effective in obtaining better results while using FLANN-Genetic.