Please use this identifier to cite or link to this item:
http://repository.aaup.edu/jspui/handle/123456789/1809
Title: | FedCSD: A Federated Learning Based Approach for Code-Smell Detection |
Authors: | Alawadi, Sadi $Other$Other Alkharabsheh, Khalid $Other$Other Alkhabbas, Fahed$Other$Other R. Kebande, Victor$Other$Other M. Awaysheh, Feras$Other$Other Palomba, Fabio $Other$Other Awad, Mohammed $AAUP$Palestinian |
Keywords: | Software quality technical debit federated learning privacy-preserving code smell detection. |
Issue Date: | 25-Mar-2024 |
Publisher: | IEEE / IEEE Access |
Citation: | Alawadi, S., Alkharabsheh, K., Alkhabbas, F., Kebande, V. R., Awaysheh, F. M., Palomba, F., & Awad, M. (2024). Fedcsd: A federated learning based approach for code-smell detection. IEEE Access. |
Series/Report no.: | Volume: 12;2024 |
Abstract: | Software quality is critical, as low quality, or “Code smell,” increases technical debt and maintenance costs. There is a timely need for a collaborative model that detects and manages code smells by learning from diverse and distributed data sources while respecting privacy and providing a scalable solution for continuously integrating new patterns and practices in code quality management. However, the current literature is still missing such capabilities. This paper addresses the previous challenges by proposing a Federated Learning Code Smell Detection (FedCSD) approach, specifically targeting “God Class,” to enable organizations to train distributed ML models while safeguarding data privacy collaboratively. We conduct experiments using manually validated datasets to detect and analyze code smell scenarios to validate our approach. Experiment 1, a centralized training experiment, revealed varying accuracies across datasets, with dataset two achieving the lowest accuracy (92.30%) and datasets one and three achieving the highest (98.90% and 99.5%, respectively). Experiment 2, focusing on cross-evaluation, showed a significant drop in accuracy (lowest: 63.80%) when fewer smells were present in the training dataset, reflecting technical debt. Experiment 3 involved splitting the dataset across 10 companies, resulting in a global model accuracy of 98.34%, comparable to the centralized model’s highest accuracy. The application of federated ML techniques demonstrates promising performance improvements in code-smell detection, benefiting both software developers and researchers. |
URI: | http://repository.aaup.edu/jspui/handle/123456789/1809 |
Appears in Collections: | Faculty & Staff Scientific Research publications |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
Admin Tools