abstract
This study investigates the application of deep learning techniques, specifically Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), for defect detection in software engineering. A systematic search was conducted across databases including IEEE Xplore, ACM Digital Library, and Google Scholar, focusing on literature published between 2010 and 2023.
Studies were selected based on relevance, rigor, credibility, and originality. The methodology involved evaluating the performance metrics of various neural network architectures in different industrial contexts. By synthesizing data through a narrative approach, the study provides insights into the strengths and limitations of CNNs and RNNs, guiding the selection of the most appropriate model for specific defect detection applications. The findings aim to contribute to the optimization of defect detection processes in software engineering, enhancing th
outcomes
