Khaleel, Shahbaa I. and Ahmed, Rasha (2025) Enhancing Refactoring Prediction at the Method-Level Using Stacking and Boosting Models. Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, 11 (2). pp. 276-289.
![[thumbnail of 11-Enhancing Refactoring Prediction at the Method-Level Using Stacking and Boosting Models.pdf]](http://eprints.uad.ac.id/style/images/fileicons/text.png) |
Text
11-Enhancing Refactoring Prediction at the Method-Level Using Stacking and Boosting Models.pdf Download (781kB) |
Abstract
Refactoring software code is crucial for developers since it enhances code maintainability and decreases technical complexity. The existing manual approach to refactoring demonstrates restricted scalability because of its requirement for substantial human intervention and big training information. A method-level refactoring prediction technique based on meta-learning uses classifier stacking and boosting and Lion Optimization Algorithm (LOA) for feature selection. The evaluation of the proposed model used four Java open source projects namely JUnit, McMMO, MapDB, and ANTLR4 showing exceptional predictive results. The technique successfully decreased training data necessities by 30% yet generated better prediction results by 10–15% above typical models to deliver 100% accuracy and F1 scores on DTS3 and DTS4 datasets. The system decreased incorrect refactoring alert counts by 40% which lowered the amount of needed developer examination.
| Item Type: | Artikel Umum |
|---|---|
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering |
| Divisi / Prodi: | Faculty of Industrial Technology (Fakultas Teknologi Industri) > S1-Electrical Engineering (S1-Teknik Elektro) |
| Depositing User: | M.Eng. Alfian Ma'arif |
| Date Deposited: | 08 Jul 2025 07:20 |
| Last Modified: | 08 Jul 2025 07:20 |
| URI: | http://eprints.uad.ac.id/id/eprint/84788 |
Actions (login required)
 |
View Item |