Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

2024 - 20262

Settings

Author: search.filters.author.Demirors, OnurSubject: search.filters.subject.COSMIC

Search Results

Now showing 1 - 2 of 2
  • Article
    Citation - WoS: 1
    Citation - Scopus: 1
    Automating Software Size Measurement With Language Models: Insights From Industrial Case Studies
    (Elsevier Science Inc, 2026) Unlu, Huseyin; Tenekeci, Samet; Kennouche, Dhia Eddine; Demirors, Onur
    Objective software size measurement is critical for accurate effort estimation, yet many organizations avoid it due to high costs, required expertise, and time-consuming manual effort. This often leads to vague predictions, poor planning, and project overruns. To address this challenge, we investigate the use of pre-trained language models - BERT and SE-BERT - to automate size measurement based on textual requirements using COSMIC and MicroM methods. We constructed one heterogeneous dataset and two industrial datasets, each manually measured by experienced analysts. Models were evaluated in three settings: (i) generic model evaluation, where the models are trained and tested on heterogeneous data, (ii) internal evaluation, where the models are trained and tested on organization-specific data, and (iii) external evaluation, where generic models were tested on organization-specific data. Results show that organization-specific models significantly outperform generic models, indicating that aligning training data with the target organization's requirement style is critical for accuracy. SE-BERT, a domain-adapted variant of BERT, improves performance, particularly in low-resource settings. These findings highlight the practical potential of tailoring training data for broader adoption and cost-effective software size measurement in industrial contexts.
  • Article
    Citation - WoS: 1
    Citation - Scopus: 1
    Application of a Size Measurement Standard for Data Warehouse Projects
    (Wiley, 2024) Unlu, Hueseyin; Yueruem, Ozan Rasit; Yildiz, Ali; Demirors, Onur
    MethodologyIn this research, we conducted a case study to establish a foundation for size measurement and effort estimation in DWH projects. We first applied a productivity-based estimation approach using linear regression with the ISBSG repository to assist organizations without historical data. We then evaluated various machine learning algorithms to improve estimation accuracy. Finally, we tested a combined model that integrates both approaches for estimating effort in external projects.ResultsUsing the ISBSG dataset, linear regression models based on productivity achieved a Mean Magnitude of Relative Error (MMRE) of 0.285. Machine learning algorithms improved accuracy by 22.81%, reducing the MMRE to 0.220. The final model, applied to external projects, yielded MRE values between 0.010 and 0.245.ConclusionThe ISBSG repository is a valuable resource for effort estimation in DWH projects. Combining productivity-based estimation with machine learning enhances accuracy and predictive performance, making it a more reliable approach than traditional models.