FedCSD: A Federated Learning Based Approach for Code-Smell Detection

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...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	IEEE access Ročník 12; s. 1
Hlavní autori:	Alawadi, Sadi, Alkharabsheh, Khalid, Alkhabbas, Fahed, Kebande, Victor R., Awaysheh, Feras M., Palomba, Fabio, Awad, Mohammed
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Piscataway IEEE 01.01.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:	Accuracy Application programs Code Code smell Code Smell Detection Codes Codes (symbols) Companies Computer software maintenance Computer software selection and evaluation Costs Cryptography Data privacy Datasets Experiments Federated learning Ho-momorphic encryptions Homomorphic encryption Homomorphic-encryptions Maintenance costs Maintenance engineering Model accuracy Object oriented modeling Object oriented modelling Object oriented programming Odors Privacy Privacy preserving Quality management Software development Software engineering Software quality Source code Technical Debit Training
ISSN:	2169-3536, 2169-3536
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	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.
Bibliografia:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ISSN:	2169-3536 2169-3536
DOI:	10.1109/ACCESS.2024.3380167