{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:59:31Z","timestamp":1776891571370,"version":"3.51.2"},"reference-count":23,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Basic Research Program-General Projects-Surface Projects of Shaanxi Provincial Department of Science and Technology","award":["2025JC-YBMS-746"],"award-info":[{"award-number":["2025JC-YBMS-746"]}]},{"name":"Scientific Research Plan Project of the Education Department of Shaanxi Province-Youth Innovation Team Project","award":["23JP071"],"award-info":[{"award-number":["23JP071"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>The detection of defects in Printed Circuit Boards (PCBs) is a critical yet challenging task in industrial quality control, characterized by the prevalence of small targets and complex backgrounds. While deep learning models like YOLOv5 have shown promise, they often lack the ability to quantify predictive uncertainty, leading to overconfident errors in challenging scenarios\u2014a major source of false alarms and reduced reliability in automated manufacturing inspection lines. From a Bayesian perspective, this overconfidence signifies a failure in probabilistic calibration, which is crucial for trustworthy automated inspection. To address this, we propose MFE-YOLO, a Bayesian-enhanced detection framework built upon YOLOv5 that systematically integrates uncertainty-aware mechanisms to improve both accuracy and operational reliability in real-world settings. First, we construct a multi-background PCB defect dataset with diverse substrate colors and shapes, enhancing the model\u2019s ability to generalize beyond the single-background bias of existing data. Second, we integrate the Convolutional Block Attention Module (CBAM), reinterpreted through a Bayesian lens as a feature-wise uncertainty weighting mechanism, to suppress background interference and amplify salient defect features. Third, we propose a novel FIoU loss function, redesigned within a probabilistic framework to improve bounding box regression accuracy and implicitly capture localization uncertainty, particularly for small defects. Extensive experiments demonstrate that MFE-YOLO achieves state-of-the-art performance, with mAP@0.5 and mAP@0.5:0.95 values of 93.9% and 59.6%, respectively, outperforming existing detectors, including YOLOv8 and EfficientDet. More importantly, the proposed framework yields better-calibrated confidence scores, significantly reducing false alarms and enabling more reliable human-in-the-loop verification. This work provides a deployable, uncertainty-aware solution for high-throughput PCB inspection, advancing toward trustworthy and efficient quality control in modern manufacturing environments.<\/jats:p>","DOI":"10.3390\/e28020174","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T15:38:12Z","timestamp":1770046692000},"page":"174","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MFE-YOLO: A Multi-Scale Feature Enhanced Network for PCB Defect Detection with Cross-Group Attention and FIoU Loss"],"prefix":"10.3390","volume":"28","author":[{"given":"Ruohai","family":"Di","sequence":"first","affiliation":[{"name":"School of Cross-Innovation, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Hao","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineering, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Hanxiao","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineering, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Zhigang","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineering, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Lei","family":"Shu","sequence":"additional","affiliation":[{"name":"School of Cross-Innovation, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Rui","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Cross-Innovation, Xi\u2019an Technological University, Xi\u2019an 710021, China"}]},{"given":"Ruoyu","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Aerospace, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Nabiullina, R., Golovin, S., Kirichenko, E., Petrushan, M., Logvinov, A., Kaplya, M., Sedova, D., and Rodkin, S. (2025). 3D Bioprinting of Cultivated Meat Followed by the Development of a Fine-Tuned YOLO Model for the Detection and Counting of Lipoblasts, Fibroblasts, and Myogenic Cells. Front. Biosci., 30.","DOI":"10.31083\/FBL36266"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"115681","DOI":"10.1016\/j.fct.2025.115681","article-title":"Biomonitoring and exposure predictors of 29 dioxin, furan, and dl-PCB congeners in newborn meconium from Spain","volume":"205","author":"Lacomba","year":"2025","journal-title":"Food Chem. Toxicol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Lan, H.W., Luo, J., Zhang, H., and Yan, X. (2025). CM-YOLO: A Multimodal PCB Defect Detection Method Based on Cross-Modal Feature Fusion. Sensors, 25.","DOI":"10.3390\/s25134108"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Yin, X.P., Zhao, Z.K., and Weng, L.G. (2025). MAS-YOLO: A Lightweight Detection Algorithm for PCB Defect Detection Based on Improved YOLOv12. Appl. Sci., 15.","DOI":"10.3390\/app15116238"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Perdigones, F., Gim\u00e9nez-G\u00f3mez, P., Mu\u00f1oz-Berbel, X., and Aracil, C. (2025). Optical Detection Techniques for Biomedical Sensing: A Review of Printed Circuit Board (PCB)-Based Lab-on-Chip Systems. Micromachines, 16.","DOI":"10.3390\/mi16050564"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"107336","DOI":"10.1016\/j.aquatox.2025.107336","article-title":"Dioxin and PCB levels in sea trout with ulcerative disease syndrome","volume":"283","author":"Mikolajczyk","year":"2025","journal-title":"Aquat. Toxicol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"056203","DOI":"10.1088\/1361-6501\/adcb5e","article-title":"Front-end feature extraction module and dynamic detection head for PCB defect detection","volume":"36","author":"Fu","year":"2025","journal-title":"Meas. Sci. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yuan, T.Z., Jiao, Z.K., and Diao, N.Z. (2025). YOLO-SSW: An Improved Detection Method for Printed Circuit Board Surface Defects. Mathematics, 13.","DOI":"10.3390\/math13030435"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2564","DOI":"10.1109\/TASE.2023.3263887","article-title":"Accurate Vision-Based PCB Positioning Using Cosine-Convolutional Neural Networks","volume":"21","author":"Solorzano","year":"2024","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"213904","DOI":"10.1063\/5.0198731","article-title":"A compact-size and high-power energy harvester using stacked flexible-PCB coils for rotational shaft applications","volume":"124","author":"Hoang","year":"2024","journal-title":"Appl. Phys. Lett."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"14274","DOI":"10.1109\/TPEL.2023.3288993","article-title":"2-D Analytical Copper Loss Model for PCB and Copper Foil Magnetics with Arbitrary Air Gaps","volume":"38","author":"Yu","year":"2023","journal-title":"IEEE Trans. Power Electron."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kuznetsov, Y.V., Baev, A.B., Konovalyuk, M.A., and Gorbunova, A.A. (2023). Blind Separation of the Measured Mixed Cyclostationary Waveforms in Transmission Lines of the PCB. Electronics, 12.","DOI":"10.3390\/electronics12153272"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"115901","DOI":"10.1016\/j.envres.2023.115901","article-title":"Characterization of PCDD\/F and dl-PCB levels in air in Gipuzkoa (Basque Country, Spain)","volume":"228","author":"Barroeta","year":"2023","journal-title":"Environ. Res."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2439","DOI":"10.1007\/s42835-025-02181-x","article-title":"Analysis and Design of Current Recovery Circuit for PCB-Embedded Pick-Up Coil Current Sensor in GaN HEMT Power Semiconductor","volume":"20","author":"Han","year":"2025","journal-title":"J. Electr. Eng. Technol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"84334","DOI":"10.1007\/s11356-023-28216-2","article-title":"Analysis of hydrochemical characteristics and assessment of organic pollutants (PAH and PCB) in El Fahs plain aquifer, northeast of Tunisia","volume":"30","author":"Farhat","year":"2023","journal-title":"Environ. Sci. Pollut. Res."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"115236","DOI":"10.1016\/j.marpolbul.2023.115236","article-title":"Chlorinated pesticides and PCB residues in the Egyptian Western Desert oases sediments","volume":"193","author":"Said","year":"2023","journal-title":"Mar. Pollut. Bull."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"797","DOI":"10.18280\/ts.400241","article-title":"Comparison of Object Region Segmentation Algorithms of PCB Defect Detection","volume":"40","author":"Zhang","year":"2023","journal-title":"Trait. Signal"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Tan, M., Pang, R., and Le, Q.V. (2020, January 13\u201319). EfficientDet: Scalable and Efficient Object Detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. (2020). End-to-End Object Detection with Transformers. European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and Efficient IOU Loss for Accurate Bounding Box Regression","volume":"506","author":"Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_21","unstructured":"Gevorgyan, Z. (2022). SIoU Loss: More Powerful Learning for Bounding Box Regression. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"166037","DOI":"10.1016\/j.scitotenv.2023.166037","article-title":"The biological invasion of an apex predator amplifies PCB transfer in a large lake food web","volume":"902","author":"Frossard","year":"2023","journal-title":"Sci. Total Environ."},{"key":"ref_23","unstructured":"Jocher, G., Chaurasia, A., and Qiu, J. (2023, January 23). Ultralytics YOLOv8. Available online: https:\/\/github.com\/ultralytics\/ultralytics."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/2\/174\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T15:42:19Z","timestamp":1770046939000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/28\/2\/174"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":23,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["e28020174"],"URL":"https:\/\/doi.org\/10.3390\/e28020174","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]}}}