Kuiyu Zhu

Kuiyu Zhu

Auto-generated profile, based on publicly available information

Kuiyu Zhu

School of Software, Northwestern Polytechnical University, Xi’an City, Shaanxi Province, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
17 September 2022 in Journal of Systems and Software
Verified
Journal Article
Closed access
KZKuiyu Zhu
Kuiyu Zhu
MYMing Yin
Ming Yin
DZDan Zhu
Dan Zhu
XZXiaogang Zhang
Xiaogang Zhang
CGCunzhi Gao
Cunzhi Gao
JJJijiao Jiang
Jijiao Jiang

1 June 2021 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
KZKuiyu Zhu
Kuiyu Zhu
MYMing Yin
Ming Yin
YLYizhen Li
Yizhen Li
Technical debt expresses the use of non-optimal solutions for short-term gains. Self-admitted technical debt is a technical debt that is deliberately introduced and recognized by developers in source code comments, including design debt, requirement debt, and defect debt, etc. Currently, many methods are proposed to detect SATD. However, these methods are limited to the identification of SATD or non-SATD. In this paper, we propose a CNN-BiLSTM method to detect and classify SATD. Through our cross-project experiments on 10 projects, it is shown that our method can not only effectively detect SATD, but also classify design debt, requirement debt, and defect debt in SATD.

1 June 2022 in Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology
Verified
Journal Article
Closed access
PDF file
MYMing Yin
Ming Yin
KZKuiyu Zhu
Kuiyu Zhu
HXHongli Xiao
Hongli Xiao
DZDan Zhu
Dan Zhu
JJJijiao Jiang
Jijiao Jiang
Effectively identifying self-admitted technical debt (SATD) from project source code comments helps developers quickly find and repay these debts, thereby reducing its negative impact. Previous studies used techniques based on patterns, text mining, natural language processing, and neural networks to detect SATD. Compared with these above, Convolutional Neural Networks (CNN) have the strong feature extraction ability. Deep network ensembles are demonstrated great potential for the task of sentences classification. In order to boost the performance of CNN-based SATD detecting, we propose a deep neural network ensemble contribute to ensemble learning in a simple yet effective way. Specifically, CNN, CNN-LSTM (convolutional neural network and long short-term memory), and DPCNN (Deep Pyramid Convolutional Neural Networks) are used as individual classifiers to diversify the deep network ensembles. In order to improve the explainability, we introduce attention to measure the contribution of feature words to SATD classification. 62,285 source code comments from 10 projects were used in our experiments. The results show that our approach can effectively reduce misjudgment and detect more SATD, especially for cross-project, so as to greatly improve the detection accuracy.