Software Defect Prediction Based On Deep Learning Models: Performance Study
Abstract
In recent years, defect prediction, one of the major software engineering problems, has been in the focus of researchers since it has a pivotal role in estimating software errors and faulty modules. Researchers with the goal of improving prediction accuracy have developed many models for software defect prediction. However, there are a number of critical conditions and theoretical problems in order to achieve better results. In this paper, two deep learning models, Stack Sparse Auto-Encoder (SSAE) and Deep Belief Network (DBN), are deployed to classify NASA datasets, which are unbalanced and have insufficient samples. According to the conducted experiment, the accuracy for the datasets with sufficient samples is enhanced and beside this SSAE model gains better results in comparison to DBN model in the majority of evaluation metrics.
Cite
@article{arxiv.2004.02589,
title = {Software Defect Prediction Based On Deep Learning Models: Performance Study},
author = {Ahmad Hasanpour and Pourya Farzi and Ali Tehrani and Reza Akbari},
journal= {arXiv preprint arXiv:2004.02589},
year = {2020}
}
Comments
10 pages, 4 figures, 6 tables, 42 references