Yuan Cao

Dr. Yuan Cao


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
7 January 2025 in Electronics
Verified
Journal Article
Open access
PDF file
JWJianxin Wang
Jianxin Wang
Lingcheng MaLingcheng Ma
Lingcheng Ma
ZLZixin Li
Zixin Li
YCYuan Cao
Yuan Cao
HZHao Zhang
Hao Zhang
In the domain of printed circuit board (PCB) defect detection, challenges such as missed detections and false positives remain prevalent. To address these challenges, we propose a small-sample, high-precision PCB defect detection algorithm, called SSHP-YOLO. The proposed method incorporates an ELAN-C module that merges the convolutional block attention module (CBAM) with the efficient layer aggregation network (ELAN), thereby enhancing the model’s focus on defect features and improving the detection of minute defect details. Furthermore, we introduce the ASPPCSPC structure, which extracts multi-scale features using pyramid pooling combined with dilated convolutions while maintaining the resolution of feature maps. This design improves the detection accuracy and robustness, thereby enhancing the algorithm’s generalization ability. Additionally, we employ the SIoU loss function to optimize the regression between the predicted and ground-truth bounding boxes, thus improving the localization accuracy of minute defects. The experimental results show that SSHP-YOLO achieves a recall rate that is 11.84% higher than traditional YOLOv7, with a mean average precision (mAP) of 97.80%. This leads to a substantial improvement in the detection accuracy, effectively mitigating issues related to missed and false detections in PCB defect detection tasks.

13 January 2023 in Electronics
Verified
Journal Article
Open access
PDF file
CWChangqing Wang
Changqing Wang
BZBei Zhang Zhang
Bei Zhang Zhang
YCYuan Cao
Yuan Cao
MSMaoxuan Sun
Maoxuan Sun
KHKunyu He
Kunyu He
MWMeng Wang
Meng Wang
For the problems of inaccurate recognition and the high missed detection rate of existing mask detection algorithms in actual scenes, a novel mask detection algorithm based on the YOLO-GBC network is proposed. Specifically, in the backbone network part, the global attention mechanism (GAM) is integrated to improve the ability to extract key information through cross-latitude information interaction. The cross-layer cascade method is adopted to improve the feature pyramid structure to achieve effective bidirectional cross-scale connection and weighted feature fusion. The sampling method of content-aware reassembly of features (CARAFE) is integrated into the feature pyramid network to fully retain the semantic information and global features of the feature map. NMS is replaced with Soft-NMS to improve model prediction frame accuracy by confidence decay method. The experimental results show that the average accuracy (mAP) of the YOLO-GBC reached 91.2% in the mask detection data set, which is 2.3% higher than the baseline YOLOv5, and the detection speed reached 64FPS. The accuracy and recall have also been improved to varying degrees, increasing the detection task of correctly wearing masks.

17 February 2023 in Sustainability
Verified
Journal Article
Open access
PDF file
MSmaoxuan sun
maoxuan sun
MSMaoxuan Sun
Maoxuan Sun
YCYuan Cao
Yuan Cao
KHKunyu He
Kunyu He
BZBei Zhang Zhang
Bei Zhang Zhang
MWMeng Wang
Meng Wang
This article proposes a lightweight YOLO-ACG detection algorithm that balances accuracy and speed, which improves on the classification errors and missed detections present in existing steel plate defect detection algorithms. To highlight the key elements of the desired area of surface flaws in steel plates, a void space convolutional pyramid pooling model is applied to the backbone network. This model improves the fusion of high- and low-level semantic information by designing feature pyramid networks with embedded spatial attention. According to the experimental findings, the suggested detection algorithm enhances the mapped value by about 4% once compared to the YOLOv4-Ghost detection algorithm on the homemade data set. Additionally, the real-time detection speed reaches about 103FPS, which is about 7FPS faster than the YOLOv4-Ghost detection algorithm, and the detection capability of steel surface defects is significantly enhanced to meet the needs of real-time detection of realistic scenes in the mobile terminal.

14 January 2025 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
YCYuan Cao
Yuan Cao
BZBei Zhang
Bei Zhang
CWChangqing Wang
Changqing Wang
MWMeng Wang
Meng Wang