View in EDS

A Survey of Software Defect Prediction Based on Deep Learning.

Saved in:
Bibliographic Details
Title: A Survey of Software Defect Prediction Based on Deep Learning.
Authors: Nevendra, Meetesh, Singh, Pradeep
Source: Archives of Computational Methods in Engineering; Nov2022, Vol. 29 Issue 7, p5723-5748, 26p
Abstract: Software defect prediction (SDP) is a procedure to develop a model that can be utilized by software practitioners and researchers in the initial phases of the software development life cycle (SDLC) for distinguishing defective modules or classes. With the increase in software complexity, defect prediction (DP) has become one of the software industry's essential processes. Thus, for the past two decades, researchers have taken an increasing interest in SDP's problem. Several techniques have been used in the past for SDP. This paper systematically investigates the literature from the last six years (2015–2020) that used deep learning (DL) techniques for SDP. The functional capabilities of different DL techniques and their pros and cons are evaluated for SDP. An extensive comparative study of DL techniques for file-level and change-level SDP is also performed. The challenges and the issues in SDP in the context of DL techniques are highlighted. The extensive comparative analysis of benchmark open-source projects shows that the DL techniques achieve better and more significant results than machine learning approaches. However, the utilization of the DL techniques in SDP is inadequate, and a more significant number of investigations should be carried out to acquire well-formed and generalizable results. [ABSTRACT FROM AUTHOR]
Copyright of Archives of Computational Methods in Engineering is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Complementary Index
Description
Abstract:Software defect prediction (SDP) is a procedure to develop a model that can be utilized by software practitioners and researchers in the initial phases of the software development life cycle (SDLC) for distinguishing defective modules or classes. With the increase in software complexity, defect prediction (DP) has become one of the software industry's essential processes. Thus, for the past two decades, researchers have taken an increasing interest in SDP's problem. Several techniques have been used in the past for SDP. This paper systematically investigates the literature from the last six years (2015–2020) that used deep learning (DL) techniques for SDP. The functional capabilities of different DL techniques and their pros and cons are evaluated for SDP. An extensive comparative study of DL techniques for file-level and change-level SDP is also performed. The challenges and the issues in SDP in the context of DL techniques are highlighted. The extensive comparative analysis of benchmark open-source projects shows that the DL techniques achieve better and more significant results than machine learning approaches. However, the utilization of the DL techniques in SDP is inadequate, and a more significant number of investigations should be carried out to acquire well-formed and generalizable results. [ABSTRACT FROM AUTHOR]
ISSN:11343060
DOI:10.1007/s11831-022-09787-8