Jie Chen

Jie Chen

Auto-generated profile, based on publicly available information

Jie Chen

Department of Computer Science, Hangzhou Dianzi University, Hangzhou, 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
19 June 2020 in IEEE Access
Verified
Journal Article
Open access
XZXiaoqing Zheng
Xiaoqing Zheng
HWHongcheng Wang
Hongcheng Wang
JCJie Chen
Jie Chen
YKYaguang Kong
Yaguang Kong
SZSong Zheng
Song Zheng
Automated surface inspection (ASI) is critical to quality control in industrial manufacturing processes. Recent advances in deep learning have produced new ASI methods that automatically learn high-level features from training samples while being robust to changes and capable of detecting different types of surfaces and defects. However, they usually rely heavily on manpower to collect and label training samples. In this paper, a generic semi-supervised deep learning-based approach for ASI that requires a small quantity of labeled training data is proposed. While the approach follows the MixMatch rules to conduct sophisticated data augmentation, we introduce a new loss function calculation method and propose a new convolutional neural network based on a residual structure to achieve accurate defect detection. An experiment on two public datasets (DAGM and NEU) and one industrial dataset (CCL) is carried out. For public datasets, the experimental results are compared against several best benchmarks in the literature. For the industrial dataset, the results are compared against deep learning methods based on benchmark neural networks. The proposed method achieves the best performance in all comparisons. In addition, a comparative experiment of model performance given a different number of labeled samples is conducted, demonstrating that the proposed method can achieve good performance with few labeled training samples.

17 June 2020 in IEEE Transactions on Reliability
Verified
Journal Article
Closed access
HHHaiyang Hou
Haiyang Hou
JYJiawei Yu
Jiawei Yu
LJLi Zhong Jin
Li Zhong Jin
JCJie Chen
Jie Chen
HHHua Hu
Hua Hu
Cyber–physical system (CPS) is a complex system that contains multiple components working cooperatively. According to its characteristics, we propose an object-oriented generalized stochastic Petri net (OGSPN), in which the CPS is abstracted into several types of objects and its logical structure and working process is visually described. Moreover, we model and measure the time consumed by each activity in CPS for quantitative analysis. To simplify the process of performance analysis on this model, in this article we propose a compression algorithm to convert OGSPN into a generalized stochastic Petri net (GSPN). Considering the uncertainty in CPS, we use a fuzzy mathematics based method to process the compressed model of GSPN for improving the accuracy of the performance analysis. We apply our method to a real-world thick metal plate production line in a manufacturing company, and the availability of our method is verified by extensive experiments.

3 August 2022 in Journal of Grid Computing
Verified
Journal Article
Closed access
PDF file
HHHaiyang Hu
Haiyang Hu
JCJie Chen
Jie Chen
HLHanwen Liu
Hanwen Liu
ZLZhongjin Li
Zhongjin Li
LHLiguo Huang
Liguo Huang

18 November 2022 in Software Quality Journal
Verified
Journal Article
Closed access
PDF file
XCXin Chen
Xin Chen
HYHaihua Yu
Haihua Yu
DYDongjin Yu
Dongjin Yu
JCJie Chen
Jie Chen
XSXiaoxiao Sun
Xiaoxiao Sun

5 December 2024 in Automated Software Engineering
Verified
Journal Article
Closed access
PDF file
DYDongjin Yu
Dongjin Yu
YXYihang Xu
Yihang Xu
LWLehui Weng
Lehui Weng
JCJie Chen
Jie Chen
XCXin Chen
Xin Chen
QYQuanxin Yang
Quanxin Yang

22 February 2023 in Science of Computer Programming
Verified
Journal Article
Closed access
JCJie Chen
Jie Chen
TJTao Jiang
Tao Jiang
DYDongjin Yu
Dongjin Yu
HHHaiyang Hu
Haiyang Hu