FeSCH: A Feature Selection Method using Clusters of Hybrid-data for Cross-Project Defect Prediction

Ni, Chuanfa; Liu, Wangshu; Gu, Qing; Chen, Xiang; Chen, Daoxu

doi:10.1109/compsac.2017.127

Cited by 20 publications

(22 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the experiments, we use three widely used datasets: ReLink, AEEEM, and MORPH. Table shows the characteristics of these datasets.…”

Section: Experiments Design and Results Analysismentioning

confidence: 99%

“…However, in practice, it is rare that sufficient labeled data is available for a new project. Thus, researchers focus on cross‐project defect prediction (CPDP) scenario, which builds a model using labeled data from other projects (ie, source projects) to predict defective modules in a particular project (ie, target project). Considering the domain difference phenomenon between the source and target projects, a defect prediction model trained on some projects might not generalize well to other projects .…”

Section: Introductionmentioning

confidence: 99%

“…Considering the domain difference phenomenon between the source and target projects, a defect prediction model trained on some projects might not generalize well to other projects . Thus, transfer learning approaches, which aim to alleviate the differences between different projects, have been widely used to address the CPDP problem …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multitask defect prediction

Chen

Xia

et al. 2019

J Software Evolu Process

Self Cite

View full text Add to dashboard Cite

Within‐project defect prediction assumes that we have sufficient labeled data from the same project, while cross‐project defect prediction assumes that we have plenty of labeled data from source projects. However, in practice, we might only have limited labeled data from both the source and target projects in some scenarios. In this paper, we want to apply multitask learning to investigate such a new scenario. To our best knowledge, this problem (ie, both the source project and the target project have limited labeled data) has not been thoroughly investigated, and we are the first to propose a novel multitask defect prediction approach mask. mask consists of a differential evolution optimization phase and a multitask learning phase. The former phase aims to find optimal weights for shared and nonshared information in related projects (ie, the target project and its related source projects), while the latter phase builds prediction models for each project simultaneously. To verify the effectiveness of mask, we perform experimental studies on 18 real‐world software projects and compare our approach with four state‐of‐the‐art baseline approaches: single‐task learning (STL), simple combined learning (SCL), Peters filter, and Burak filter. Experimental results show that mask can achieve F1 of 0.397 and AUC of 0.608 on average with a few labeled data (ie, 10% of data). Across the 18 projects, mask can outperform baseline methods significantly in terms of F1 and AUC. Therefore, by utilizing the relatedness among multiple projects, mask can perform significantly better than the state‐of‐the‐art methods. The results confirm that mask is promising for software defect prediction when the source and target projects both have limited training data.

show abstract

“…In the experiments, we use three widely used datasets: ReLink, AEEEM, and MORPH. Table shows the characteristics of these datasets.…”

Section: Experiments Design and Results Analysismentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multitask defect prediction

Chen

Xia

et al. 2019

J Software Evolu Process

Self Cite

View full text Add to dashboard Cite

show abstract

“…He et al investigated the feasibility of the CPDP models constructed by a simplified feature subset. Ni et al proposed a cluster‐based feature selection method FeSCH, which is a two‐phase method. The feature clustering phase clusters features via a density‐based clustering method and the feature selection phase selects features from each cluster by a ranking strategy.…”

Section: Background and Related Workmentioning

confidence: 99%

Do different cross‐project defect prediction methods identify the same defective modules?

Chen

Qu³

et al. 2019

J Software Evolu Process

Self Cite

View full text Add to dashboard Cite

Cross‐project defect prediction (CPDP) is needed when the target projects are new projects or the projects have less training data, since these projects do not have sufficient historical data to build high‐quality prediction models. The researchers have proposed many CPDP methods, and previous studies have conducted extensive comparisons on the performance of different CPDP methods. However, to the best of our knowledge, it remains unclear whether different CPDP methods can identify the same defective modules, and this issue has not been thoroughly explored. In this article, we select 12 state‐of‐the‐art CPDP methods, including eight supervised methods and four unsupervised methods. We first compare the performance of these methods in the same experiment settings on five widely used datasets (ie, NASA, SOFTLAB, PROMISE, AEEEM, and ReLink) and rank these methods via the Scott‐Knott test. Final results confirm the competitiveness of unsupervised methods. Then we perform diversity analysis on defective modules for these methods by using the McNemar test. Empirical results verify that different CPDP methods may lead to difference in the modules predicted as defective, especially when the comparison is performed between the supervised methods and unsupervised methods. Finally, we also find there exist a certain number of defective modules, which cannot be correctly identified by any of the CPDP methods or can be correctly identified by only one CPDP method. These findings can be utilized to design more effective methods to further improve the performance of CPDP.

show abstract

“…They found that the proposed method increased the probability of defect detection at the cost of increasing false positive rate. Ni et al [14] proposed a novel method called FeSCH and designed three ranking strategies to choose appropriate features. The experimental results show that FeSCH can outperform WPDP, ALL, and TCA+ in most cases, and its performance is independent of the used classifiers.…”

Section: Related Workmentioning

confidence: 99%

An Improved Method for Cross-Project Defect Prediction by Simplifying Training Data

et al. 2018

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Cross-project defect prediction (CPDP) on projects with limited historical data has attracted much attention. To the best of our knowledge, however, the performance of existing approaches is usually poor, because of low quality cross-project training data. The objective of this study is to propose an improved method for CPDP by simplifying training data, labeled as TDSelector, which considers both the similarity and the number of defects that each training instance has (denoted by defects), and to demonstrate the effectiveness of the proposed method. Our work consists of three main steps. First, we constructed TDSelector in terms of a linear weighted function of instances’ similarity and defects. Second, the basic defect predictor used in our experiments was built by using the Logistic Regression classification algorithm. Third, we analyzed the impacts of different combinations of similarity and the normalization of defects on prediction performance and then compared with two existing methods. We evaluated our method on 14 projects collected from two public repositories. The results suggest that the proposed TDSelector method performs, on average, better than both baseline methods, and the AUC values are increased by up to 10.6% and 4.3%, respectively. That is, the inclusion of defects is indeed helpful to select high quality training instances for CPDP. On the other hand, the combination of Euclidean distance and linear normalization is the preferred way for TDSelector. An additional experiment also shows that selecting those instances with more bugs directly as training data can further improve the performance of the bug predictor trained by our method.

show abstract

FeSCH: A Feature Selection Method using Clusters of Hybrid-data for Cross-Project Defect Prediction

Cited by 20 publications

References 19 publications

Multitask defect prediction

Multitask defect prediction

Do different cross‐project defect prediction methods identify the same defective modules?

An Improved Method for Cross-Project Defect Prediction by Simplifying Training Data

Contact Info

Product

Resources

About