Improving the Quality of Open Source Software

Abstract

This study aims at development of generating metrics based code smells prediction to improve the software quality assurance by working at preventive maintenance level. In order to do so, Refactoring is the best solution for identification of smelly areas in the code to reveal the portions which demands patching. It not only increases the life of code but eventually increases the quality of software in long run, where versions of a software are launched one after the other. The empirical model development considered Deep learning based neural network technique for establishing the association between code smells and metrics in the source code of Eclipse which is a Java based application contributing efficiently on the open source platform. A statistical analysis was pre applied on the set of code smells and metrics for finding the connection between the both. Later on, Multi Layer Perceptron model development on four versions of Eclipse has been made. Subsequently Area Under Curve (ROC) has been generated for class & method level code smells. The value of ROC in predicting code smells pointed towards the fact that Neural Network Multi Layer Perceptron model perform fair to good in determining the presence of code smells based on software metrics in Eclipse. Therefore from the results obtained it is concluded that smelly classes are predicted efficiently by software metric based code smells prediction model. The present study will be beneficial to the software development community to locate the refactoring areas and providing resources for testing. The results of empirical study also guide the development community by providing information relative to code smells and its types. The aim of this study is to provide statistical proof of linkage between metrics and code smells. The software metric based prediction � 2023 Scrivener Publishing LLC.