Cross project defect prediction model based on enhanced transfer learning

This study proposes a two-stage framework for Cross-Project Defect Prediction (CPDP) to address class and feature distribution imbalance. It uses adversarial training-enhanced transfer learning to identify defective software modules. Through experiments on public datasets and comparison with traditional models, its superiority is shown. The first stage involves feature extraction with two encoders and advanced preprocessing techniques. The second stage utilizes transfer learning, ensemble learning, fine-tuning, and the SMOTE method. Future research can expand its application and optimize the model to handle complex imbalances or incorporate other techniques to enhance predictive performance, increasing the practical potential of the CPDP model in software engineering.

Text 121398.docx - Draft Version Restricted to Repository staff only Download (98kB)

Actions (login required)

View Item