Application of Intelligent Adaptive Neuro Fuzzy Method for Reusability of Component Based Software System

Abstract

Component Based Software System (CBSS) provides an easy and efficient way to develop new software application with the help of existing software components of similar functionalities. It increases the reusability of software components and reduce the development time, cost and effort of software developers. To select the appropriate component, it become essential to assess the reusability of software components so that suitable component can be selected to reuse in another application. For assessing the reusability of CBSS, several factors are required to be considered. In this paper, four reusability sub-factors Interface Complexity (IC), Understandability (Un), Customizability (Co) and Reliability (Re) are used as input variables and reusability is assessed using Fuzzy Inference System (FIS) and Adaptive Neuro Fuzzy Inference System (ANFIS) approach because these two approaches are commonly used approach for assessing the quality factors. For experimental work, one case study has been done where rules are generated to assess reusability using four different reusability factors by taking feedback from researchers and academicians using online survey. Reusability was assessed for ten different values of input variables. Experiment shows that results obtained from ANFIS method were closer to the original values. Root Mean Square Error (RMSE) of FIS results was 6.05% which was further reduced by the application of ANFIS approach and finally 2.20% of RMSE was achieved. This research work will be helpful for software developers and researchers to assess the reusability of software components and they will be able to take corrective decision for choosing the appropriate component to be reused in new software applications, which will reduce their effort, time and cost of development