{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,31]],"date-time":"2026-10-31T03:22:41Z","timestamp":1793416961080,"version":"4.5.0"},"reference-count":38,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T00:00:00Z","timestamp":1767657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100017592","name":"Key Science and Technology Program of Shaanxi Province","doi-asserted-by":"publisher","award":["2023-YBGY-342"],"award-info":[{"award-number":["2023-YBGY-342"]}],"id":[{"id":"10.13039\/501100017592","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073256"],"award-info":[{"award-number":["62073256"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>During the process of defect detection in Micro-Electro-Mechanical Systems (MEMSs), there are many problems with the metallographic images, such as complex backgrounds, strong texture interference, and blurred defect edges. As a result, bond wire breaks and internal cavity contaminants are difficult to effectively identify, which seriously affects the reliability of the whole machine. To solve this problem, this paper proposes a MEMS small-object defect detection method, YOLO-DST (Dynamic Channel\u2013Spatial Modeling and Triplet Attention-based YOLO), based on dynamic channel\u2013spatial blocks and multi-attention fusion. Based on the YOLOv8s framework, the proposed method integrates dynamic channel\u2013space blocks into the backbone and detection head to enhance feature representation across multiple defect scales. The neck of the network integrates multiple triple attention mechanisms, effectively suppressing the background interference caused by complex metallographic textures. Combined with the small-object perception enhancement network based on a Transformer, this method improves the capture ability and stability of the model for the detection of bond wire breaks and internal cavity contaminants. In the verification stage, a MEMS small-object defect dataset covering typical metallographic imaging was constructed. Through comparative experiments with the existing mainstream detection models, the results showed that YOLO-DST achieved better performance in indicators such as Precision and mAP@50%.<\/jats:p>","DOI":"10.3390\/s26020369","type":"journal-article","created":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:49:46Z","timestamp":1767707386000},"page":"369","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["YOLO-DST: MEMS Small-Object Defect Detection Method Based on Dynamic Channel\u2013Spatial Modeling and Multi-Attention Fusion"],"prefix":"10.3390","volume":"26","author":[{"given":"Qianwen","family":"Su","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering, Xi\u2019an Technological University, Xi\u2019an 710021, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0110-9898","authenticated-orcid":false,"given":"Hanshan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering, Xi\u2019an Technological University, Xi\u2019an 710021, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1049","DOI":"10.1016\/S0026-2714(03)00119-7","article-title":"MEMS Reliability from a Failure Mechanisms Perspective","volume":"43","year":"2003","journal-title":"Microelectron. Reliab."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"937","DOI":"10.1016\/j.microrel.2009.06.014","article-title":"MEMS Reliability: Where Are We Now?","volume":"49","author":"Tanner","year":"2009","journal-title":"Microelectron. Reliab."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"482","DOI":"10.1109\/TDMR.2012.2191291","article-title":"MEMS Reliability Review","volume":"12","author":"Huang","year":"2012","journal-title":"IEEE Trans. Device Mater. Reliab."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"A14","DOI":"10.1364\/PRJ.441215","article-title":"Wafer-level Hermetically Sealed Silicon Photonic MEMS","volume":"10","author":"Jo","year":"2022","journal-title":"Photonics Res."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Chen, J., Wen, X., Huang, Q., Ren, W., Liu, R., and He, C. (2024). Characterization of Sand and Dust Pollution Degradation Based on Sensitive Structure of Microelectromechanical System Flow Sensor. Micromachines, 15.","DOI":"10.3390\/mi15050574"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhan, D., Huang, R., Yi, K., Yang, X., Shi, Z., Lin, R., Lin, J., and Wang, H. (2023). Convolutional Neural Network Defect Detection Algorithm for Wire Bonding X-Ray Images. Micromachines, 14.","DOI":"10.3390\/mi14091737"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Wu, S., Zhu, Y., and Liang, P. (2024). DSCU-Net: MEMS Defect Detection Using Dense Skip-Connection U-Net. Symmetry, 16.","DOI":"10.3390\/sym16030300"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"183192","DOI":"10.1109\/ACCESS.2020.3029127","article-title":"A Review and Analysis of Automatic Optical Inspection and Quality Monitoring Methods in Electronics Industry","volume":"8","author":"Mousavi","year":"2020","journal-title":"IEEE Access"},{"key":"ref_9","unstructured":"Yang, M., Castellani, M., Landot, R., Beyeler, F., and Nelson, B.J. (February, January 31). Automated Optical Inspection Method for MEMS Fabrication. Proceedings of the IEEE International Conference on Micro Electro Mechanical Systems (MEMS), Hong Kong, China."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Aryan, P., Sampath, S., and Sohn, H. (2018). An Overview of Non-Destructive Testing Methods for Integrated Circuit Packaging Inspection. Sensors, 18.","DOI":"10.3390\/s18071981"},{"key":"ref_11","unstructured":"Ng, H.F., Ong, S.H., Foong, K.W.C., Goh, P.S., and Nowinski, W.L. (2006, January 26\u201328). Medical image segmentation using K-means clustering and improved watershed algorithm. Proceedings of the 2006 IEEE Southwest Symposium on Image Analysis and Interpretation, Denver, CO, USA."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"683334","DOI":"10.1117\/12.759560","article-title":"Study on Defect Detection of IC Wafer Based on Morphology","volume":"6833","author":"Hou","year":"2007","journal-title":"Proc. SPIE"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.mejo.2010.01.015","article-title":"Defect Detection of IC Wafer Based on Two-Dimension Wavelet Transform","volume":"41","author":"Liu","year":"2010","journal-title":"Microelectron. J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"798161","DOI":"10.1155\/S1110865702204035","article-title":"Wafer Defect Detection Using Directional Morphological Gradient Techniques","volume":"2002","author":"Qu","year":"2002","journal-title":"EURASIP J. Adv. Signal Process."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"90691R","DOI":"10.1117\/12.2050105","article-title":"A Geometrical Defect Detection Method for Non-Silicon MEMS Part Based on HU Moment Invariants of Skeleton Image","volume":"9069","author":"Cheng","year":"2014","journal-title":"Proc. SPIE"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.patrec.2003.09.005","article-title":"Flat Image Recognition in the Process of Microdevice Assembly","volume":"25","author":"Baidyk","year":"2004","journal-title":"Pattern Recognit. Lett."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"126323","DOI":"10.1109\/ACCESS.2023.3331152","article-title":"Crack Defect Detection Processing Algorithm and Method of MEMS Devices Based on Image Processing Technology","volume":"11","author":"Zheng","year":"2023","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Amini, A., Kanfoud, J., and Gan, T.H. (2021). An Artificial-Intelligence-Driven Predictive Model for Surface Defect Detections in Medical MEMS. Sensors, 21.","DOI":"10.3390\/s21186141"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Shi, Z., Zhao, H., Li, Y., Liu, Q., Song, K., Zhang, H., and Wang, Y. (2022). Defect Detection of MEMS Based on Data Augmentation, WGAN-DIV-DC, and a YOLOv5 Model. Sensors, 22.","DOI":"10.3390\/s22239400"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"111696","DOI":"10.1016\/j.mee.2021.111696","article-title":"Inspecting and Classifying Physical Failures in MEMS Substrates during Fabrication Using Computer Vision","volume":"254","author":"Raveendran","year":"2022","journal-title":"Microelectron. Eng."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Deng, M., Zhang, Q., Zhang, K., Li, H., Zhang, Y., and Cao, W. (2022). A Novel Defect Inspection System Using Convolutional Neural Network for MEMS Pressure Sensors. J. Imaging, 8.","DOI":"10.3390\/jimaging8100268"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"103158","DOI":"10.1016\/j.mex.2025.103158","article-title":"Deep Learning Driven Silicon Wafer Defect Segmentation and Classification","volume":"14","author":"Ingle","year":"2025","journal-title":"MethodsX"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1109\/TSM.2019.2902657","article-title":"Convolutional Neural Network for Wafer Surface Defect Classification and the Detection of Unknown Defect Class","volume":"32","author":"Cheon","year":"2019","journal-title":"IEEE Trans. Semicond. Manuf."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"L\u00f3pez de la Rosa, F., S\u00e1nchez-Reolid, R., G\u00f3mez-Sirvent, J.L., Morales, R., and Fern\u00e1ndez-Caballero, A. (2021). A Review on Machine and Deep Learning for Semiconductor Defect Classification in Scanning Electron Microscope Images. Appl. Sci., 11.","DOI":"10.3390\/app11209508"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Chien, J.-C., Wu, M.-T., and Lee, J.-D. (2020). Inspection and Classification of Semiconductor Wafer Surface Defects Using CNN Deep Learning Networks. Appl. Sci., 10.","DOI":"10.3390\/app10155340"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1109\/TSM.2020.2994357","article-title":"A Deep Convolutional Neural Network for Wafer Defect Identification on an Imbalanced Dataset in Semiconductor Manufacturing Processes","volume":"33","author":"Saqlain","year":"2020","journal-title":"IEEE Trans. Semicond. Manuf."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2300971","DOI":"10.1002\/adts.202300971","article-title":"TD-YOLO: A Lightweight Detection Algorithm for Tiny Defects in High-Resolution PCBs","volume":"7","author":"Ling","year":"2024","journal-title":"Adv. Theory Simul."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kim, J., Ko, J., Choi, H., and Kim, H. (2021). Printed Circuit Board Defect Detection Using Deep Learning via a Skip-Connected Convolutional Autoencoder. Sensors, 21.","DOI":"10.3390\/s21154968"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Feng, B., and Cai, J. (2023). PCB Defect Detection via Local Detail and Global Dependency Information. Sensors, 23.","DOI":"10.3390\/s23187755"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tang, W., Deng, Y., and Luo, X. (2025). RST-YOLOv8: An Improved Chip Surface Defect Detection Model Based on YOLOv8. Sensors, 25.","DOI":"10.3390\/s25133859"},{"key":"ref_31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., and Polosukhin, I. (2017, January 4\u20139). Attention Is All You Need. Proceedings of the 31st Conference on Neural Information Processing Systems (NeurIPS), Long Beach, CA, USA."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Gu, Y., Ren, C., Chen, Q., Bai, H., Huang, Z., and Zou, L. (2024). A Conditionally Parameterized Feature Fusion U-Net for Building Change Detection. Sustainability, 16.","DOI":"10.3390\/su16219232"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1007\/s10462-025-11326-3","article-title":"Don\u2019t Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning","volume":"58","author":"Apicella","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Gerz, F., and Jelali, M. (SSRN Electron. J., 2025). Towards Reliable Data Augmentation in Machine Learning: Practices to Prevent Data Leakage, SSRN Electron. J., in press.","DOI":"10.2139\/ssrn.5636100"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 11\u201314). SSD: Single Shot Multibox Detector. Proceedings of the European Conference on Computer Vision (ECCV), Amsterdam, The Netherlands.","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Girshick, R. (2015, January 7\u201313). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Santiago, Chile.","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref_37","unstructured":"Ge, Z., Liu, S., Wang, F., Li, Z., and Sun, J. (2021). YOLOX: Exceeding YOLO Series in 2021. arXiv."},{"key":"ref_38","unstructured":"Li, X., Chen, S., Huang, Z., Zhang, S., Qiao, Y., and Dong, C. (2023). RT-DETR: Real-Time Detection Transformer. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/369\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T05:16:50Z","timestamp":1767849410000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/369"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,6]]},"references-count":38,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26020369"],"URL":"https:\/\/doi.org\/10.3390\/s26020369","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,6]]}}}