Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
A Survey of Software Defect Prediction Based on Deep Learning
https://orcid.org/0000-0002-2806-8432
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.
A Survey of Software Defect Prediction Based on Deep Learning
https://orcid.org/0000-0002-2806-8432
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.
A Survey of Software Defect Prediction Based on Deep Learning
https://orcid.org/0000-0002-2806-8432
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.
A Survey of Software Defect Prediction Based on Deep Learning
Nevendra, Meetesh (Autor:in) / Singh, Pradeep (Autor:in)
2022
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Deep Learning-Based Defect Detection for Sustainable Smart Manufacturing
| DOAJ | 2022
Deep Learning-Based Crack Detection: A Survey
| Springer Verlag | 2023
Deep Learning-Based Automatic Defect Detection Method for Sewer Pipelines
| DOAJ | 2023
Deep learning-based weld defect classification using VGG16 transfer learning adaptive fine-tuning
| Springer Verlag | 2023