{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T10:16:19Z","timestamp":1778408179387,"version":"3.51.4"},"reference-count":50,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,10,12]],"date-time":"2021-10-12T00:00:00Z","timestamp":1633996800000},"content-version":"vor","delay-in-days":284,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computational Intelligence and Neuroscience"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>After the production of printed circuit boards (PCB), PCB manufacturers need to remove defected boards by conducting rigorous testing, while manual inspection is time\u2010consuming and laborious. Many PCB factories employ automatic optical inspection (AOI), but this pixel\u2010based comparison method has a high false alarm rate, thus requiring intensive human inspection to determine whether alarms raised from it resemble true or pseudo defects. In this paper, we propose a new cost\u2010sensitive deep learning model: cost\u2010sensitive siamese network (CSS\u2010Net) based on siamese network, transfer learning and threshold moving methods to distinguish between true and pseudo PCB defects as a cost\u2010sensitive classification problem. We use optimization algorithms such as NSGA\u2010II to determine the optimal cost\u2010sensitive threshold. Results show that our model improves true defects prediction accuracy to 97.60%, and it maintains relatively high pseudo defect prediction accuracy, 61.24% in real\u2010production scenario. Furthermore, our model also outperforms its state\u2010of\u2010the\u2010art competitor models in other comprehensive cost\u2010sensitive metrics, with an average of 33.32% shorter training time.<\/jats:p>","DOI":"10.1155\/2021\/7550670","type":"journal-article","created":{"date-parts":[[2021,10,13]],"date-time":"2021-10-13T17:18:22Z","timestamp":1634145502000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Cost\u2010Sensitive Siamese Network for PCB Defect Classification"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5178-7363","authenticated-orcid":false,"given":"Yilin","family":"Miao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1772-7148","authenticated-orcid":false,"given":"Zhewei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0887-0698","authenticated-orcid":false,"given":"Xiangning","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4307-1514","authenticated-orcid":false,"given":"Jie","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,10,12]]},"reference":[{"key":"e_1_2_8_1_2","doi-asserted-by":"publisher","DOI":"10.3390\/bios10110159"},{"key":"e_1_2_8_2_2","doi-asserted-by":"crossref","unstructured":"WuX. GeY. ZhangQ. andZhangD. Pcb defect detection using deep learning methods Proceedings of the 2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD) May 2021 Dalian China 873\u2013876 https:\/\/doi.org\/10.1109\/cscwd49262.2021.9437846.","DOI":"10.1109\/CSCWD49262.2021.9437846"},{"key":"e_1_2_8_3_2","doi-asserted-by":"crossref","unstructured":"MelnykR. HavrylkoY. andLevusY. Three types of PCB defects and image processing algorithms for their detection Proceedings of the 2021 IEEE XVIIth International Conference on the Perspective Technologies and Methods in MEMS Design (MEMSTECH) May 2021 Polyana Ukraine 197\u2013200 https:\/\/doi.org\/10.1109\/memstech53091.2021.9467917.","DOI":"10.1109\/MEMSTECH53091.2021.9467917"},{"key":"e_1_2_8_4_2","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899x\/767\/1\/012064"},{"key":"e_1_2_8_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106771"},{"key":"e_1_2_8_6_2","doi-asserted-by":"publisher","DOI":"10.3390\/app11093867"},{"key":"e_1_2_8_7_2","unstructured":"ZhugeM. FanD. LiuN. ZhangD. XuD. andShaoL. Salient object detection via integrity learning 2021 https:\/\/arxiv.org\/abs\/2101.07663."},{"key":"e_1_2_8_8_2","doi-asserted-by":"crossref","unstructured":"ZhugeM. GaoD. FanD. JinL. ChenB. ZhouH. andShaoL. Kaleido-BERT: vision-language pre-training on fashion domain Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition 2021 Nashville TN USA 12647\u201312657.","DOI":"10.1109\/CVPR46437.2021.01246"},{"key":"e_1_2_8_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-0826-5_3"},{"key":"e_1_2_8_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.09.358"},{"key":"e_1_2_8_11_2","doi-asserted-by":"crossref","unstructured":"ChenH. WangY. ZhengK. LiW. ChangC.-T. HarrisonA. P. XiaoJ. HagerG. D. LuL. LiaoC.-H. andMiaoS. Anatomy-aware siamese network: exploiting semantic asymmetry for accurate pelvic fracture detection in x-ray images Proceedings of the European Conference on Computer Vision August 2020 Glasgow UK Springer 239\u2013255 https:\/\/doi.org\/10.1007\/978-3-030-58592-1_15.","DOI":"10.1007\/978-3-030-58592-1_15"},{"key":"e_1_2_8_12_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_2_8_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2019.101004"},{"key":"e_1_2_8_14_2","doi-asserted-by":"crossref","unstructured":"DengY.-S. LuoA.-C. andDaiM.-J. Building an automatic defect verification system using deep neural network for pcb defect classification Proceedings of the 2018 4th International Conference on Frontiers of Signal Processing (ICFSP) September 2018 Poitiers France 145\u2013149 https:\/\/doi.org\/10.1109\/icfsp.2018.8552045 2-s2.0-85059989731.","DOI":"10.1109\/ICFSP.2018.8552045"},{"key":"e_1_2_8_15_2","doi-asserted-by":"crossref","unstructured":"TakagiY. SuzukiA. HorioT. OhnoT. KojimaT. TakadaT. IioS. ObayashiK. andOkuyamaM. 4-ch\u2009x\u200910-gb\/s chip-to-chip optical interconnections with optoelectronic packages and optical waveguide separated from PCB Proceedings of the 2010 IEEE CPMT Symposium August 2010 Tokyo Japan IEEE 1\u20134.","DOI":"10.1109\/CPMTSYMPJ.2010.5680206"},{"key":"e_1_2_8_16_2","doi-asserted-by":"crossref","unstructured":"AliqueA. HaberR. E. HaberR. H. RosS. andGonzalezC. A neural network-based model for the prediction of cutting force in milling process. a progress study on a real case Proceedings of the 2000 IEEE International Symposium on Intelligent Control. Held Jointly with the 8th IEEE Mediterranean Conference on Control and Automation July 2000 Patras Greece IEEE 121\u2013125 https:\/\/doi.org\/10.1109\/ISIC.2000.882910.","DOI":"10.1109\/ISIC.2000.882910"},{"key":"e_1_2_8_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115673"},{"key":"e_1_2_8_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpat.2019.102063"},{"key":"e_1_2_8_19_2","doi-asserted-by":"publisher","DOI":"10.5194\/jsss-9-167-2020"},{"key":"e_1_2_8_20_2","doi-asserted-by":"crossref","unstructured":"HuangG. LiuZ. Van Der MaatenL. andWeinbergerK. Q. Densely connected convolutional networks Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition July 2017 Honolulu HI USA 4700\u20134708 https:\/\/doi.org\/10.1109\/cvpr.2017.243 2-s2.0-85035343801.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_8_21_2","doi-asserted-by":"publisher","DOI":"10.17485\/ijst\/2016\/v9i44\/98964"},{"key":"e_1_2_8_22_2","doi-asserted-by":"crossref","unstructured":"ZhangZ. WangX. LiuS. SunL. ChenL. andGuoY. An automatic recognition method for PCB visual defects Proceedings of the 2018 International Conference on Sensing Diagnostics Prognostics and Control (SDPC) August 2018 Xi\u2019an China 138\u2013142 https:\/\/doi.org\/10.1109\/sdpc.2018.8664974 2-s2.0-85064125158.","DOI":"10.1109\/SDPC.2018.8664974"},{"key":"e_1_2_8_23_2","doi-asserted-by":"publisher","DOI":"10.3390\/rs11192252"},{"key":"e_1_2_8_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2020.2971057"},{"key":"e_1_2_8_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.11.028"},{"key":"e_1_2_8_26_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2016 Las Vegas NV USA 770\u2013778 https:\/\/doi.org\/10.1109\/cvpr.2016.90 2-s2.0-84986274465.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09106-y"},{"key":"e_1_2_8_28_2","doi-asserted-by":"crossref","unstructured":"PanZ. BaoX. ZhangY. WangB. AnQ. andLeiB. Siamese network based metric learning for sar target classification Proceedings of the IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium July 2019 Yokohama Japan IEEE 1342\u20131345 https:\/\/doi.org\/10.1109\/igarss.2019.8898210.","DOI":"10.1109\/IGARSS.2019.8898210"},{"key":"e_1_2_8_29_2","doi-asserted-by":"crossref","unstructured":"MohammedR. RawashdehJ. andAbdullahM. Machine learning with oversampling and undersampling techniques: overview study and experimental results Proceedings of the 2020 11th International Conference on Information and Communication Systems (ICICS) April 2020 Irbid Jordan IEEE 243\u2013248 https:\/\/doi.org\/10.1109\/icics49469.2020.239556.","DOI":"10.1109\/ICICS49469.2020.239556"},{"key":"e_1_2_8_30_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.08.035"},{"key":"e_1_2_8_31_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-6602-3_3"},{"key":"e_1_2_8_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103411"},{"key":"e_1_2_8_33_2","doi-asserted-by":"crossref","unstructured":"ZhangX. GweonH. andProvostS. Threshold moving approaches for addressing the class imbalance problem and their application to multi-label classification Proceedings of the 2020 4th International Conference on Advances in Image Processing November 2020 Chengdu China 72\u201377 https:\/\/doi.org\/10.1145\/3441250.3441274.","DOI":"10.1145\/3441250.3441274"},{"key":"e_1_2_8_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2017.2764047"},{"key":"e_1_2_8_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2990567"},{"key":"e_1_2_8_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"e_1_2_8_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2013.2281534"},{"key":"e_1_2_8_38_2","doi-asserted-by":"crossref","unstructured":"DebK.andSundarJ. Reference point based multi-objective optimization using evolutionary algorithms Proceedings of the 8th Annual Conference on Genetic and Evolutionary Computation July 2006 Seattle Washington D. C. USA 635\u2013642 https:\/\/doi.org\/10.1145\/1143997.1144112.","DOI":"10.1145\/1143997.1144112"},{"key":"e_1_2_8_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2018.2855411"},{"key":"e_1_2_8_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2020.2977537"},{"key":"e_1_2_8_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-019-08453-9"},{"key":"e_1_2_8_42_2","doi-asserted-by":"publisher","DOI":"10.1137\/20M1314884"},{"key":"e_1_2_8_43_2","unstructured":"LinM. ChenQ. andYanS. Network in network 2013 http:\/\/arxiv.org\/abs\/1312.4400."},{"key":"e_1_2_8_44_2","article-title":"Predictive accuracy: a misleading performance measure for highly imbalanced data","volume":"12","author":"Akosa J.","year":"2017","journal-title":"Proceedings of the SAS Global Forum"},{"key":"e_1_2_8_45_2","doi-asserted-by":"publisher","DOI":"10.3233\/ifs-162150"},{"key":"e_1_2_8_46_2","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky A.","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_8_47_2","doi-asserted-by":"crossref","unstructured":"ZophB. VasudevanV. ShlensJ. andQuocV. L. Learning transferable architectures for scalable image recognition Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition June 2018 Salt Lake City UT USA 8697\u20138710 https:\/\/doi.org\/10.1109\/cvpr.2018.00907 2-s2.0-85062864819.","DOI":"10.1109\/CVPR.2018.00907"},{"key":"e_1_2_8_48_2","doi-asserted-by":"crossref","unstructured":"ZeilerM. D.andFergusR. Visualizing and understanding convolutional networks Proceedings of the European Conference on Computer Vision September 2014 Zurich Switzerland Springer 818\u2013833 https:\/\/doi.org\/10.1007\/978-3-319-10590-1_53 2-s2.0-84906489074.","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_2_8_49_2","unstructured":"HowardA. G. ZhuM. ChenB. KalenichenkoD. WangW. WeyandT. AndreettoM. andAdamH. Mobilenets: efficient convolutional neural networks for mobile vision applications 2017 http:\/\/arxiv.org\/abs\/1704.04861."},{"key":"e_1_2_8_50_2","unstructured":"TanM.andLeQ. Efficientnet: rethinking model scaling for convolutional neural networks Proceedings of the International Conference on Machine Learning June 2019 Long Beach CA USA PMLR 6105\u20136114."}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/7550670.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/7550670.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/7550670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T11:41:20Z","timestamp":1722944480000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/7550670"}},"subtitle":[],"editor":[{"given":"Rodolfo E.","family":"Haber","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/7550670"],"URL":"https:\/\/doi.org\/10.1155\/2021\/7550670","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"value":"1687-5265","type":"print"},{"value":"1687-5273","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2021-05-29","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"7550670"}}