文献类型：期刊文献

英文题名：Y Cross-Project Defect Prediction via Landmark Selection-Based Kernelized Discriminant Subspace Alignment

作者：Li, Zhiqiang[1];Niu, Jingwen[2];Jing, Xiao-Yuan[3,4];Yu, Wangyang[1];Qi, Chao[1]

第一作者：Li, Zhiqiang

通讯作者：Li, ZQ[1]

机构：[1]Shaanxi Normal Univ, Sch Comp Sci, Xian 710119, Peoples R China;[2]Xinxiang Univ, Sch Comp & Informat Engn, Xinxiang 453003, Henan, Peoples R China;[3]Wuhan Univ, Sch Comp Sci, Wuhan 430072, Peoples R China;[4]Guangdong Univ Petrochem Technol, Sch Comp, Maoming 525000, Peoples R China

第一机构：Shaanxi Normal Univ, Sch Comp Sci, Xian 710119, Peoples R China

通讯机构：[1]corresponding author), Shaanxi Normal Univ, Sch Comp Sci, Xian 710119, Peoples R China.

年份：2021

卷号：70

期号：3

起止页码：996-1013

外文期刊名：IEEE TRANSACTIONS ON RELIABILITY

收录：;WOS:【SCI-EXPANDED(收录号:WOS:000692208600015)】；

基金：Thisworkwas supported in part by theNationalNatural Science Foundation of China under Grant 61902228, in part by the NSFC-Key Project of General Technology Fundamental Research United Fund under Grant U1736211, in part by the NSFC-Key Project under Grant 61933013, in part by the Natural Science Basic Research Program of Shaanxi Province under Grant 2020JQ-422, in part by the Natural Science Foundation of Guangdong Province under Grant 2019A1515011076, in part by the Innovation Group of Guangdong Education Department under Grant 2020KCXTD014 and Grant 2018KCXTD019, in part by the Key Project of Natural Science Foundation of Hubei Province under Grant 2018CFA024, and in part by the Fundamental Research Funds for the Central Universities under Grant GK202103083 and Grant GK202105006.

语种：英文

外文关键词：Cross-project defect prediction (CPDP); discriminant subspace alignment; domain adaptation; kernel projection; landmark selection; source label propagation

摘要：Cross-project defect prediction (CPDP) refers to identifying defect-prone software modules in one project (target) using historical data collected from other projects (source), which can help developers find bugs and prioritize their testing efforts. Recently, CPDP has attracted great research interest. However, the source and target data usually exist redundancy and nonlinearity characteristics. Besides, most CPDP methods do not exploit source label information to uncover the underlying knowledge for label propagation. These factors usually lead to unsatisfactory CPDP performance. To address the above limitations, we propose a landmark selection-based kernelized discriminant subspace alignment (LSKDSA) approach for CPDP. LSKDSA not only reduces the discrepancy of the data distributions between the source and target projects, but also characterizes the complex data structures and increases the probability of linear separability of the data. Moreover, LSKDSA encodes label information of the source data into domain adaptation learning process and makes itself with good discriminant ability. Extensive experiments on 13 public projects fromthree benchmark datasets demonstrate that LSKDSA performs better than a range of competing CPDP methods. The improvement is 3.44% - 11.23% in g-measure, 5.75% - 11.76% in AUC, and 9.34% - 33.63% in MCC, respectively.