Publikationer från Malmö universitet
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
FedCSD: A Federated Learning Based Approach for Code-Smell Detection
Blekinge Inst Technol, Dept Comp Sci, S-37179 Karlskrona, Sweden.;Univ Santiago de Compostela, Comp Graph & Data Engn COGRADE Res Grp, Santiago De Compostela 15705, Spain..
Al Balqa Appl Univ, Prince Abdullah bin Ghazi Fac Informat & Commun Te, Software Engn Dept, As Salt 19117, Jordan..ORCID-id: 0000-0002-3182-418X
Malmö universitet, Fakulteten för teknik och samhälle (TS), Institutionen för datavetenskap och medieteknik (DVMT). Malmö universitet, Internet of Things and People (IOTAP).ORCID-id: 0000-0002-8025-4734
Blekinge Inst Technol, Dept Comp Sci, S-37179 Karlskrona, Sweden..
Vise andre og tillknytning
2024 (engelsk)Inngår i: IEEE Access, E-ISSN 2169-3536, Vol. 12, s. 44888-44904Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

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.

sted, utgiver, år, opplag, sider
Institute of Electrical and Electronics Engineers (IEEE), 2024. Vol. 12, s. 44888-44904
Emneord [en]
Software quality, technical debit, federated learning, privacy-preserving, code smell detection
HSV kategori
Identifikatorer
URN: urn:nbn:se:mau:diva-66923DOI: 10.1109/ACCESS.2024.3380167ISI: 001193664800001Scopus ID: 2-s2.0-85189169469OAI: oai:DiVA.org:mau-66923DiVA, id: diva2:1854566
Tilgjengelig fra: 2024-04-26 Laget: 2024-04-26 Sist oppdatert: 2024-04-26bibliografisk kontrollert

Open Access i DiVA

fulltext(2285 kB)54 nedlastinger
Filinformasjon
Fil FULLTEXT01.pdfFilstørrelse 2285 kBChecksum SHA-512
74c244f54d5a0719cdbb6f8a6503d31b26e3c9e6895dae0ea671590a1a102310548c525a890cee4dac6deda2363093527cb9da64dbbf02750a5df4357c6c068a
Type fulltextMimetype application/pdf

Andre lenker

Forlagets fulltekstScopus

Person

Alkhabbas, Fahed

Søk i DiVA

Av forfatter/redaktør
Alkharabsheh, KhalidAlkhabbas, FahedPalomba, FabioAwad, Mohammed
Av organisasjonen
I samme tidsskrift
IEEE Access

Søk utenfor DiVA

GoogleGoogle Scholar
Totalt: 54 nedlastinger
Antall nedlastinger er summen av alle nedlastinger av alle fulltekster. Det kan for eksempel være tidligere versjoner som er ikke lenger tilgjengelige

doi
urn-nbn

Altmetric

doi
urn-nbn
Totalt: 149 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf