Convolutional Neural Network-Based Research on Software Engineering Defect Prediction
Xiongwei Qiu, Pengtong Fan, Jiale Ren · 2023
Defect prediction plays a crucial role in software engineering by identifying potential issues before they manifest as costly problems. In this research, we focus on enhancing defect prediction techniques using Convolutional Neural Networks (CNNs). CNNs have demonstrated significant success in various domains, primarily image analysis, due to their ability to capture complex patterns and relationships within data. We propose a novel approach that leverages the power of CNNs to automatically learn and extract features from software engineering datasets, enabling improved defect prediction accuracy. Our experimental results showcase the effectiveness of the CNN-based technique in comparison to traditional methods. The proposed CNN model exhibits promising potential to advance defect prediction capabilities and contribute to the overall quality and reliability of software systems. This research opens up new avenues for applying deep learning techniques to software engineering challenges and paves the way for further exploration in this interdisciplinary field.