A Software Quality Prediction Model for Aspect Oriented System using Neuro-Fuzzy Approach

Nowadays, the usage of software has increased exponentially in various fields like education systems, industries, health systems, and many others. Various software architectures are already available in the market e.g. modular oriented, component-based, object-oriented, aspect-oriented, etc. Aspect-Oriented (AO) system software has gained much attention due to its superior features to the aforementioned systems. However, AO systems face the challenges of being complex and hard testing environment, a quality assessment of these systems is necessary. In this paper, a software quality estimation model for aspect oriented system using neuro-fuzzy approach has been developed. For which, a detailed study on aspect oriented systems has been accomplished in terms of various attributes affecting the quality of these software. In this paper, a framework of software quality prediction model has been designed using the adaptive neuro-fuzzy inference engine (ANFIS) approach. Data of 200 software pieces have been collected in this study where 150 software data is used to train the ANFIS model whereas 50 software data is used for testing purposes. The quality estimated by the proposed ANFIS model is compared with the actual quality of these software data and quantitative analysis is performed in terms of error measures. Finally, it was found that the proposed ANFIS model worked better in terms of MSE, MRE, MARE, MBRE, and MIBRE error measures.