Zhidan Yuan

Zhidan Yuan

Auto-generated profile, based on publicly available information

Zhidan Yuan

College of Information Engineering, Jiangsu Maritime Institute, Nanjing, Jiangsu, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 February 2020 in IEEE Access
Verified
Journal Article
Open access
ZYZhidan Yuan
Zhidan Yuan
Xiang ChenXiang Chen
Xiang Chen
ZCZhanqi Cui
Zhanqi Cui
YMYanzhou Mu
Yanzhou Mu
Cross-project defect prediction (CPDP) methods can be used when the target project is a new project or lacks enough labeled program modules. In these new target projects, we can easily extract and then measure these modules with software measurement tools. However, labeling these program modules is time-consuming, error-prone and requires professional domain knowledge. Moreover, directly using labeled modules in the other projects (i.e., the source projects) can not achieve satisfactory performance due to the large data distribution difference in most cases. In this article, to our best knowledge, we are the first to propose a novel method ALTRA, which can utilize both active learning and TrAdaBoost to alleviate this issue. In particular, we firstly use Burak filter to select similar labeled modules from the source project after analyzing the unlabeled modules in the target project. Then we use active learning to choose representative unlabeled modules from the target project and ask experts to label the type (i.e., defective or non-defective) of these modules. Later, we use TrAdaBoost to determine the weights of labeled modules in the source project and the target project, and then construct the model via weighted support vector machine. After selecting a small number of modules (i.e., only 5% modules ) in the target project, we terminate the method ALTRA and return the final constructed model. To show the effectiveness of our proposed method ALTRA, we choose 10 large-scale open-source projects from different application domains. In terms of both F1 and AUC performance indicators, we find ALTRA can perform significantly better than seven state-of-the-art CPDP baselines. Moreover, we also show that the usage of Burak filter, the uncertainty active learning strategy, the class imbalanced learning method and TrAdaBoost are competitive in our proposed method ALTRA.

1 January 2025 in International Journal of Intelligent Networks
Verified
Journal Article
Open access
ZYZhidan Yuan
Zhidan Yuan
YZYikai Zhang
Yikai Zhang
YYYingqi Yu
Yingqi Yu
TLTaizhi Lv
Taizhi Lv
THTao Huang
Tao Huang

11 September 2024
Verified
Conference Paper
Open access
ZYZhidan Yuan
Zhidan Yuan
ZWZhuangzhuang Wang
Zhuangzhuang Wang
EWEnze Wu
Enze Wu
THTao Huang
Tao Huang
YCYingying Chen
Yingying Chen
Distributed system failure prediction identifies potential failures by constructing machine learning models based on Key Performance Indicator (KPI) data. However, due to the diversity of KPI metrics, not all metrics are relevant to specific failures. This lead to redundancy in the KPI metrics used to construct the models. To address this issue, we investigate the impact of filter-based ranking feature selection methods on distributed system failure prediction. In our empirical study, we conduct experiments based on the ZTE dataset by using six feature selection methods and four tree-based models. We explore the effects of different feature selection methods and selection ratios on model performance. Additionally, we study whether feature selection methods can effectively identify important KPI metrics from the perspective of model interpretability. The results indicate that compared to not using feature selection methods, employing such methods allows for the construction of effective failure prediction models with only a subset of KPI metrics. Model performance improves with an increase in feature selection ratio until reaching a point of stabilization. Moreover, feature selection methods effectively identify important KPI metrics within the dataset.

5 January 2026 in Information and Software Technology
Verified
Journal Article
Closed access
ZYZhidan Yuan
Zhidan Yuan
Xiang ChenXiang Chen
Xiang Chen
JZJuan Zhang
Juan Zhang
WZWeiming Zeng
Weiming Zeng