دورية أكاديمية
Software defect prediction using hybrid model (CBIL) of convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM).
| العنوان: | Software defect prediction using hybrid model (CBIL) of convolutional neural network (CNN) and bidirectional long short-term memory (Bi-LSTM). |
|---|---|
| المؤلفون: | Farid AB; Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Helwan, Egypt.; Department of Information Systems, Faculty of Computers and Artificial Intelligence, Beni-Suef University, Beni-Suef, Egypt., Fathy EM; Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Helwan, Egypt., Sharaf Eldin A; Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Helwan, Egypt.; Department of Information Systems, Faculty of Information Technology and Computer Science, Sinai University, Sinai, Egypt., Abd-Elmegid LA; Department of Information Systems, Faculty of Computers and Artificial Intelligence, Helwan University, Helwan, Egypt. |
| المصدر: | PeerJ. Computer science [PeerJ Comput Sci] 2021 Nov 16; Vol. 7, pp. e739. Date of Electronic Publication: 2021 Nov 16 (Print Publication: 2021). |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: PeerJ Inc Country of Publication: United States NLM ID: 101660598 Publication Model: eCollection Cited Medium: Internet ISSN: 2376-5992 (Electronic) Linking ISSN: 23765992 NLM ISO Abbreviation: PeerJ Comput Sci Subsets: PubMed not MEDLINE |
| أسماء مطبوعة: | Original Publication: San Diego, CA : PeerJ Inc., [2015]- |
| مستخلص: | In recent years, the software industry has invested substantial effort to improve software quality in organizations. Applying proactive software defect prediction will help developers and white box testers to find the defects earlier, and this will reduce the time and effort. Traditional software defect prediction models concentrate on traditional features of source code including code complexity, lines of code, etc. However, these features fail to extract the semantics of source code. In this research, we propose a hybrid model that is called CBIL. CBIL can predict the defective areas of source code. It extracts Abstract Syntax Tree (AST) tokens as vectors from source code. Mapping and word embedding turn integer vectors into dense vectors. Then, Convolutional Neural Network (CNN) extracts the semantics of AST tokens. After that, Bidirectional Long Short-Term Memory (Bi-LSTM) keeps key features and ignores other features in order to enhance the accuracy of software defect prediction. The proposed model CBIL is evaluated on a sample of seven open-source Java projects of the PROMISE dataset. CBIL is evaluated by applying the following evaluation metrics: F -measure and area under the curve (AUC). The results display that CBIL model improves the average of F -measure by 25% compared to CNN, as CNN accomplishes the top performance among the selected baseline models. In average of AUC, CBIL model improves AUC by 18% compared to Recurrent Neural Network (RNN), as RNN accomplishes the top performance among the selected baseline models used in the experiments. Competing Interests: The authors declare there are no competing interests. (©2021 Farid et al.) |
| References: | PLoS One. 2019 Feb 1;14(2):e0211359. (PMID: 30707738) Comput Intell Neurosci. 2019 Feb 26;2019:2537689. (PMID: 30936911) |
| فهرسة مساهمة: | Keywords: Abstract syntax tree; Bidirectional long short-term memory; Convolutional neural network; Deep learning; Machine learning; Software defect prediction; Defect |
| تواريخ الأحداث: | Date Created: 20211213 Latest Revision: 20211215 |
| رمز التحديث: | 20231215 |
| مُعرف محوري في PubMed: | PMC8627227 |
| DOI: | 10.7717/peerj-cs.739 |
| PMID: | 34901421 |
| قاعدة البيانات: | MEDLINE |
Full Text Finder | تدمد: | 2376-5992 |
|---|---|
| DOI: | 10.7717/peerj-cs.739 |