Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
Systematic Literature Review on the Machine Learning Approach in Software Engineering |
| Συγγραφείς: |
Cerqueira, Marcelo, Silva, Paulo, Fernandes, Sergio |
| Πηγή: |
American Scientific Research Journal for Engineering, Technology, and Sciences; Vol. 85 No. 1 (2022); 370- 396 ; 2313-4402 ; 2313-4410 |
| Στοιχεία εκδότη: |
Mohammad Nassar for Researches (MNFR) |
| Έτος έκδοσης: |
2022 |
| Συλλογή: |
American Scientific Research Journal for Engineering, Technology, and Sciences (ASRJETS) |
| Θεματικοί όροι: |
Machine Learning, Software Engineering, Software Engineering Processes, Software Engineering Activities, Machine Learning Algorithms |
| Περιγραφή: |
The application of machine learning solutions in software engineering tools and processes can bring significant benefits to software engineering processes, as well as to processes results analysis. There are few primary, secondary, and tertiary studies referring to machine learning applications in software engineering. The apparent scarcity of this type of research makes it difficult to develop specific solutions for software engineering areas and processes. Thus, it is necessary to investigate and understand how the use of machine learning in software engineering is reported in the literature. This work aims to carry out a systematic literature review on the machine learning approach in software engineering. The search strategy resulted in 1725 articles, of which 54 articles were about empirical studies. The studies were grouped into four themes: the main machine learning algorithms and/or frameworks applied in software engineering; the software engineering activities in which these algorithms and/or machine learning frameworks are applied; the main types of application of these algorithms and/or frameworks; and the main results obtained with the application of these algorithms and/or frameworks. The results obtained indicate that the following algorithms are used: Support Vector Machine, Random Forest, Decision Tree and Naive Bayes and applied mainly in software testing and planning activities. Defect prediction and effort estimation are the main types of application of these algorithms and improvement in performance and accuracy of defect prediction and cost reduction are the main results obtained with the application of these algorithms in software engineering. |
| Τύπος εγγράφου: |
article in journal/newspaper |
| Περιγραφή αρχείου: |
application/pdf |
| Γλώσσα: |
English |
| Relation: |
http://asrjetsjournal.org/index.php/American_Scientific_Journal/article/view/7381/2506; http://asrjetsjournal.org/index.php/American_Scientific_Journal/article/view/7381 |
| Διαθεσιμότητα: |
http://asrjetsjournal.org/index.php/American_Scientific_Journal/article/view/7381 |
| Rights: |
Copyright (c) 2022 American Academic Scientific Research Journal for Engineering, Technology, and Sciences |
| Αριθμός Καταχώρησης: |
edsbas.1737788D |
| Βάση Δεδομένων: |
BASE |