Y
Yifeng Zhang
Researcher at Wuhan University
Publications - 5
Citations - 198
Yifeng Zhang is an academic researcher from Wuhan University. The author has contributed to research in topics: Software bug & Software quality assurance. The author has an hindex of 4, co-authored 4 publications receiving 90 citations.
Papers
More filters
Journal ArticleDOI
Software defect prediction based on kernel PCA and weighted extreme learning machine
Zhou Xu,Zhou Xu,Jin Liu,Jin Liu,Xiapu Luo,Zijiang Yang,Yifeng Zhang,Peipei Yuan,Yutian Tang,Tao Zhang +9 more
TL;DR: KPWE, a new software defect prediction framework that considers the feature extraction and class imbalance issues, is proposed, and the empirical study on 44 software projects indicate that KPWE is superior to the baseline methods in most cases.
Journal ArticleDOI
LDFR: Learning deep feature representation for software defect prediction
Zhou Xu,Zhou Xu,Shuai Li,Jun Xu,Jin Liu,Jin Liu,Xiapu Luo,Yifeng Zhang,Tao Zhang,Jacky Keung,Yutian Tang +10 more
TL;DR: A deep neural network is used with a new hybrid loss function that consists of a triplet loss to learn a more discriminative feature representation of the defect data and a weighted cross-entropy loss to remedy the imbalance issue.
Journal ArticleDOI
A comprehensive comparative study of clustering-based unsupervised defect prediction models
TL;DR: This work performed a large-scale empirical study on 40 unsupervised models on an open-source dataset including 27 project versions with 3 types of features to explore the impacts of clustering-based models on defect prediction performance.
Proceedings ArticleDOI
Identifying Crashing Fault Residence Based on Cross Project Model
TL;DR: This work makes the first attempt to develop a cross project ICFR model to address the data scarcity problem by transferring the knowledge from external projects to the current project via utilizing a state-of-the-art Balanced Distribution Adaptation (BDA) based transfer learning method.
Proceedings ArticleDOI
Semi-supervised Knowledge Distillation for Tiny Defect Detection
TL;DR: Current unsupervised anomaly detection methods are extended into a semi-supervised manner, simultaneously leveraging normal data and a limited amount of abnormal data.