SwePub
Sök i LIBRIS databas

  Utökad sökning

onr:"swepub:oai:DiVA.org:bth-26101"
 

Sökning: onr:"swepub:oai:DiVA.org:bth-26101" > FedCSD :

  • Alawadi, Sadi,1983-Blekinge Tekniska Högskola,Institutionen för datavetenskap (författare)

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

  • Artikel/kapitelEngelska2024

Förlag, utgivningsår, omfång ...

  • Institute of Electrical and Electronics Engineers (IEEE),2024
  • electronicrdacarrier

Nummerbeteckningar

  • LIBRIS-ID:oai:DiVA.org:bth-26101
  • https://urn.kb.se/resolve?urn=urn:nbn:se:bth-26101URI
  • https://doi.org/10.1109/ACCESS.2024.3380167DOI

Kompletterande språkuppgifter

  • Språk:engelska
  • Sammanfattning på:engelska

Ingår i deldatabas

Klassifikation

  • Ämneskategori:ref swepub-contenttype
  • Ämneskategori:art swepub-publicationtype

Anmärkningar

  • 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. © 2013 IEEE.

Ämnesord och genrebeteckningar

Biuppslag (personer, institutioner, konferenser, titlar ...)

  • Alkharabsheh, KhalidAl-Balqa Applied University, Jordan (författare)
  • Alkhabbas, FahedMalmö University, Internet of Things and People Research Center (författare)
  • Kebande, Victor R.Blekinge Tekniska Högskola,Institutionen för datavetenskap(Swepub:bth)vvk (författare)
  • Awaysheh, Feras M.Institute of Computer Science, Estonia (författare)
  • Palomba, FabioUniversity of Salerno, Italy (författare)
  • Awad, MohammedArab American University, Palestine (författare)
  • Blekinge Tekniska HögskolaInstitutionen för datavetenskap (creator_code:org_t)

Sammanhörande titlar

  • Ingår i:IEEE Access: Institute of Electrical and Electronics Engineers (IEEE)12, s. 44888-449042169-3536

Internetlänk

Hitta via bibliotek

Till lärosätets databas

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

 
pil uppåt Stäng

Kopiera och spara länken för att återkomma till aktuell vy