Intelligent Software Defect Prediction

ISBN-13: 9789819928415 / Angielski

Xiao-Yuan Jing; Haowen Chen; Baowen Xu

Spis treści

1 Introduction

1.1 Software Quality Assurance

1.2 Software Defect Prediction

1.3 Research Directions of SDP

1.3.1 Within-Project Defect Prediction (WPDP)

1.3.2 Cross-Project Defect Prediction (CPDP)

1.3.3 Heterogeneous Defect Prediction (HDP)

1.3.4 Other Research Questions of SDP

1.4 Notations and Corresponding Descriptions

1.5 Structure of This Book

References

2 Application of Machine Learning Techniques in Intelligent SDP

2.1 Transfer Learning

2.2 Deep Learning

2.3 Other Techniques

2.3.1 Dictionary Learning

2.3.2 Semi-Supervised Learning

2.3.3 Multi-View Learning

References

3 Within-Project Defect Prediction

3.1 Basic WPDP

3.1.1 Dictionary Learning based Software Defect Prediction

3.1.2 Collaborative Representation Classification based Software Defect Prediction

3.2 Semi-Supervised WPDP

3.2.1 Sample-based Software Defect Prediction with Active and Semi-Supervised Learning

3.2.2 Other Solutions

References

4 Cross-Project Defect Prediction

4.1 Basic CPDP

4.1.1 Manifold embedded distribution adaptation

4.1.2 Other Solutions

4.2 Class imbalance problem in CPDP

4.2.1 An Improved SDA based Defect Prediction Framework

4.2.2 Other Solutions

4.3 Semi-Supervised CPDP

4.3.1 Cost-Sensitive Kernelized Semi-Supervised Dictionary Learning

4.3.2 Other Solutions

References

5 Heterogeneous Defect Prediction

5.1 Basic HDP

5.1.1 Unified Metric Representation and CCA-based Transfer Learning

5.1.2 Other Solutions

5.2 Class Imbalance Problem in HDP

5.2.1 Cost-Sensitive Transfer Kernel Canonical Correlation Analysis

5.2.2 Other Solutions

5.3 Multiple Sources and Privacy Preservation Problems in HDP

5.3.1 Multi-Source Selection Based Manifold Discriminant Alignment

5.3.2 Sparse Representation based Double Obfuscation Algorithm

References

6 Empirical Findings on HDP Approaches

6.1 Heterogeneous Defect Prediction

6.1.1 Major Challenges

6.1.2 Review of Research Status

6.1.3 Analysis on Research Status

6.2 Goal Question Metric (GQM) based Research Methodology

6.2.1 Research Goal

6.2.2 Research Questions

6.2.3 Evaluation Metrics

6.3 Experiments

6.4 Discussions

References

7 Other Research Questions of SDP

7.1 Cross-Version Defect Prediction

7.2 Just-in-Time Defect Prediction

7.3 Effort-Aware Just-in-Time Defect Prediction

8 Conclusions

References

O autorze

Xiao-Yuan Jing is a Professor at the School of Computer Science, Wuhan University. Prof. Jing’s research interests include software defect prediction, software effort estimation, and software engineering. His research has been published in authoritative software engineering journals and conference proceedings, such as IEEE Transactions on Software Engineering, Empirical Software Engineering, IEEE Transactions on Reliability, Information and Software Technology, Automated Software Engineering, ICSE, FSE, ASE, and ICSME. He has also pursued research on pattern recognition, machine learning, and artificial intelligence. He has published a range of studies in leading artificial intelligence journals and conference proceedings, including IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE Transactions on Neural Networks and Learning Systems, IEEE Transactions on Information Forensics and Security, CVPR, AAAI, and IJCAI. He has been selected as a highly cited Chinese researcher by Elsevier.

Haowen Chen is a Ph.D. candidate at the School of Computer Science, Wuhan University. Mr. Chen is currently working toward his Ph.D. degree at the School of Computer Science, Wuhan University. His research interests include software engineering and machine learning. His research has been published in IEEE Transactions on Software Engineering, Information and Software Technology, ICSE, etc.

Baowen Xu is a Professor at the Department of Computer Science and Technology, Nanjing University. Prof. Xu has pursued research on the theory, methodology, and technology research of test-driven software defect diagnosis and analysis, since the late 1980s. He has obtained a number of internationally advanced research results, which have had a substantial impact in this research field. He has undertaken more than 30 research projects from the Ministry of Aerospace Industry, China State Shipbuilding Corporation, the National Natural Science Foundation of China, the Ministry of Education, the Ministry of Science and Technology, Jiangsu Province, and enterprises such as Huawei, ZTE and Intel. Prof. Xu has received support from the National Science Fund for Distinguished Young Scholars, the National Natural Science Foundation of China (including the Major Research Plan, State Key Program, General Program, and International Joint Research Program), the National Basic Research Program of China, the Key Program and General Program of the National High Technology Research and Development Program of China, the Science and Technology Development Program, the High Technological Program, and the Natural Science Foundation of Jiangsu Province. He has published more than 300 papers, including in leading venues such as TOSEM, TSE, ICSE, FSE, IJCAI, etc. He has also served as the general chair, program committee chair or program committee member for more than 100 prominent academic conferences.

Blurb

With the increasing complexity of and dependency on software, software products may suffer from low quality, high prices, be hard to maintain, etc. Software defects usually produce incorrect or unexpected results and behaviors. Accordingly, software defect prediction (SDP) is one of the most active research fields in software engineering and plays an important role in software quality assurance. Based on the results of SDP analyses, developers can subsequently conduct defect localization and repair on the basis of reasonable resource allocation, which helps to reduce their maintenance costs.

This book offers a comprehensive picture of the current state of SDP research. More specifically, it introduces a range of machine-learning-based SDP approaches proposed for different scenarios (i.e., WPDP, CPDP, and HDP). In addition, the book shares in-depth insights into current SDP approaches’ performance and lessons learned for future SDP research efforts.

We believe these theoretical analyses and emerging challenges will be of considerable interest to all researchers, graduate students, and practitioners who want to gain deeper insights into and/or find new research directions in SDP. It offers a comprehensive introduction to the current state of SDP and detailed descriptions of representative SDP approaches.