Software code refactoring based on deep neural network‐based fitness function

Abstract

Refactoring is extensively recognized for enhancing the internal structure of object-oriented software while preserving its external behavior. However, determining refactoring opportunities is challenging for designers and researchers alike. In recent years, machine learning algorithms have shown a great possibility of resolving this issue. This study proposes a deep neural network-based fitness function (DNNFF) to resolve the software refactoring issue. This study suggests an effective learning technique that automatically featured extracted from the trained models and predicted code clones to recommend which category to refactor. The software engineers automatically assess the recommended refactoring solutions using Genetic Algorithms (GA) for minimum iterations. A Deep Neural Networks (DNN) utilizes these training instances to assess the refactoring solutions for the residual iterations. The refactoring process primarily depends on software designers' skills and perceptions. The simulation findings demonstrate that the suggested DNNFF model enhances the code change score of 98.7%, automatic refactoring score of 97.3%, defect correlation ratio of 96.9%, refactoring precision ratio of 95.9%, flaw detection ratio of 94.4%, and reduces the execution time of 10.2% compared to other existing methods.

A Comparative Study of Automated Refactoring Tools

“…1, is organized in a five-step process: (1) selection of subject project and tools that will be considered in the context of this comparative study. (2) developing the evaluation framework that will be used to evaluate and compare the selected tools. (3) execution of selected tools on selected projects to collect related data about code smell presence before and after applying refactoring.…”

“…Automating the code smell detection and correction process is essential, especially in large software systems. In this regard, researchers have proposed various automated and semi-automated approaches supported with tools for code smell detection and correction, where they differ in their capabilities [2][3][4][5][6][7][8][9].…”

“…Later, AbuHassan and Alshayeb [11] extended Misbhauddin's work and added four additional categories. The suggested seven categories for refactoring approaches are: Machine Learning (ML) and optimization-based [2,3], graph-based [4], software metricsbased [5], rule-based [6], token-based [7], text-based [8], and tree-based [9]. ML and optimization-based category has a wide range of subcategories that use statistical approaches, artificial intelligence, and different ML techniques to correct refactoring opportunities.…”