Intelligent Software Defect Prediction

Preface
Acknowledgments
Contents
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
			1.3.4.1 Cross-Version Defect Prediction
			1.3.4.2 Just-in-Time Defect Prediction
			1.3.4.3 Effort-Aware Defect Prediction
	1.4 Notations and Corresponding Descriptions
	1.5 Structure of This Book
	References
2 Machine Learning Techniques for 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
			3.1.1.1 Methodology
			3.1.1.2 Experiments
			3.1.1.3 Discussions
		3.1.2 Collaborative Representation Classification Based Software Defect Prediction
			3.1.2.1 Methodology
			3.1.2.2 Experiments
			3.1.2.3 Discussions
	3.2 Semi-supervised WPDP
		3.2.1 Sample-Based Software Defect Prediction with Active and Semi-supervised Learning
			3.2.1.1 Methodology
			3.2.1.2 Experiments
			3.2.1.3 Discussions
	References
4 Cross-Project Defect Prediction
	4.1 Basic CPDP
		4.1.1 Manifold Embedded Distribution Adaptation
			4.1.1.1 Methodology
			4.1.1.2 Experiments
			4.1.1.3 Discussions
	4.2 Class Imbalance Problem in CPDP
		4.2.1 An Improved SDA Based Defect Prediction Framework
			4.2.1.1 Methodology
			4.2.1.2 Experiments
			4.2.1.3 Discussions
	4.3 Semi-Supervised CPDP
		4.3.1 Cost-Sensitive Kernelized Semi-supervised Dictionary Learning
			4.3.1.1 Methodology
			4.3.1.2 Experiments
			4.3.1.3 Discussion
	References
5 Heterogeneous Defect Prediction
	5.1 Basic HDP
		5.1.1 Unified Metric Representation and CCA-Based Transfer Learning
			5.1.1.1 Methodology
			5.1.1.2 Experiments
			5.1.1.3 Discussions
	5.2 Class Imbalance Problem in HDP
		5.2.1 Cost-Sensitive Transfer Kernel Canonical Correlation Analysis
			5.2.1.1 Methodology
			5.2.1.2 Experiments
			5.2.1.3 Discussions
		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
			5.3.1.1 Methodology
			5.3.1.2 Experiments
			5.3.1.3 Discussions
		5.3.2 Sparse Representation Based Double Obfuscation Algorithm
			5.3.2.1 Methodology
			5.3.2.2 Experiments
			5.3.2.3 Discussions
	References
6 An Empirical Study on HDP Approaches
	6.1 Goal Question Metric (GQM) Based Research Methodology
		6.1.1 Major Challenges
		6.1.2 Review of Research Status
		6.1.3 Analysis on Research Status
		6.1.4 Research Goal
		6.1.5 Research Questions
		6.1.6 Evaluation Metrics
	6.2 Experiments
		6.2.1 Datasets
		6.2.2 SDP Approaches for Comparisons
		6.2.3 Experimental Design
		6.2.4 Experimental Results
	6.3 Discussions
	References
7 Other Research Questions of SDP
	7.1 Cross-Version Defect Prediction
		7.1.1 Methodology
		7.1.2 Experiments
		7.1.3 Discussions
	7.2 Just-in-Time Defect Prediction
		7.2.1 Methodology
		7.2.2 Experiments
			7.2.2.1 Experiment Setup
			7.2.2.2 Evaluation Metrics
			7.2.2.3 Research Questions
		7.2.3 Discussions
	7.3 Effort-Aware Just-in-Time Defect Prediction
		7.3.1 Methodology
			7.3.1.1 Dependent and Independent Variables
			7.3.1.2 Simple Unsupervised Models
			7.3.1.3 The Supervised Models
			7.3.1.4 Research Questions
			7.3.1.5 Performance Indicators
		7.3.2 Experiments
		7.3.3 Discussions
	References
8 Conclusion
	8.1 Conclusion