{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:50:24Z","timestamp":1772121024570,"version":"3.50.1"},"reference-count":41,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,2]]},"DOI":"10.23919\/icact.2018.8323642","type":"proceedings-article","created":{"date-parts":[[2018,4,11]],"date-time":"2018-04-11T21:11:35Z","timestamp":1523481095000},"page":"45-51","source":"Crossref","is-referenced-by-count":89,"title":["Detection of rail surface defects based on CNN image recognition and classification"],"prefix":"10.23919","author":[{"given":"Lidan","family":"Shang","sequence":"first","affiliation":[]},{"given":"Qiushi","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Jianing","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shubin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Weimin","family":"Lei","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref38","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref33","first-page":"1322","article-title":"ADASYN: Adaptive synthetic sampling approach for unbalanced learning","author":"he","year":"2008","journal-title":"IEEE International Joint Conference on Neural Networks (IJCNN)"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority technique","volume":"16","author":"chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"ref30","author":"lecun","year":"2015","journal-title":"LeNet-5 convolutional neural networks [J]"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-005-0467-y"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1109\/TSMCB.2008.2007853","article-title":"Exploratory under Sampling for class imbalance learning","volume":"39","author":"liu","year":"2009","journal-title":"IEEE Transactions on Systems Man and Cybernetics Part B Cybernetics"},{"key":"ref35","article-title":"KNN approach to unbalanced data distributions: A case study involving information extraction","author":"zhang","year":"2003","journal-title":"ICML'2003 Workshop on Learning from Imbalanced Data Sets"},{"key":"ref34","first-page":"179","article-title":"Addressing the curse of unbalanced training sets: One-sided selection","author":"kubat","year":"1997","journal-title":"The 14th International Conference on Machine Learning"},{"key":"ref10","first-page":"51004","article-title":"Diagnosis System of Breast Tumors Based on Migration Learning and Deep Convolution Neural Networks [J]","volume":"55","author":"jinghui","year":"2018","journal-title":"J Optoelectron Laser"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0620-5"},{"key":"ref11","author":"zhang","year":"0","journal-title":"Defense of Fully Connected Layers in Visual Representation Transfer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1002\/joc.658"},{"key":"ref14","first-page":"218","volume":"51","author":"nat","year":"1984","journal-title":"Ultrasonic Testing of Materials [J]"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1046\/j.1460-2695.2003.00668.x"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2015.01.024"},{"key":"ref17","article-title":"Crack detection in rail using infrared methods [J]","volume":"46","author":"greene","year":"2007","journal-title":"Optical Engineering"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.7779\/JKSNT.2012.32.6.696"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1784\/insi.2014.56.7.360"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/72.554195"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2014-64"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref3","first-page":"25","article-title":"Current Situation and Development of Bridge Detection Technology Based on Machine Vision [D]","volume":"12","author":"na","year":"2015","journal-title":"Modern Transportation Technology"},{"key":"ref6","author":"cunningham","year":"2000","journal-title":"Automated Track Inspection Vehicle and Method"},{"key":"ref29","article-title":"ImageNet classification with Deep Convolutional Neural Networks [J]","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems 2012"},{"key":"ref5","first-page":"185","article-title":"Effective adaptive weighted median filter algorithm","volume":"45","author":"xiu-qin","year":"2009","journal-title":"Computer Engineering and Applications"},{"key":"ref8","first-page":"26","volume":"26","author":"zhuang","year":"2015","journal-title":"Survey on transfer learning research Ruan Jian Xue Bao\/Journal of Software"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"key":"ref2","first-page":"168","article-title":"Defect Classification for tire X-ray images using convolutional neural network [M]","volume":"40","author":"xuehong","year":"2017","journal-title":"Electronic Measurement Technology"},{"key":"ref9","author":"yang","year":"0","journal-title":"Research of unbalanced data based on neural networks"},{"key":"ref1","article-title":"Rethinking the inception architecture for computer vision","author":"szegedy","year":"2015"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2017.06.003"},{"key":"ref22","article-title":"Deep inside convolutional networks: visualising image classification models and saliency maps","author":"simonyan","year":"0"},{"key":"ref21","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Advances in Neural Information ProcessingSystems25 CurranAsso-635 ciates Inc"},{"key":"ref24","first-page":"818","article-title":"Visualizing and understanding convolutional networks","author":"zeiler","year":"2014","journal-title":"Proceedings of the European Conference on Computer Vision"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref23","first-page":"647","article-title":"DeCAF:a deep convolutional activation feature for generic visual recognition, 565","author":"donahue","year":"2014","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"}],"event":{"name":"2018 20th International Conference on Advanced Communications Technology (ICACT)","location":"Chuncheon-si Gangwon-do, Korea (South)","start":{"date-parts":[[2018,2,11]]},"end":{"date-parts":[[2018,2,14]]}},"container-title":["2018 20th International Conference on Advanced Communication Technology (ICACT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8318543\/8323471\/08323642.pdf?arnumber=8323642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,24]],"date-time":"2020-08-24T00:58:36Z","timestamp":1598230716000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8323642\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2]]},"references-count":41,"URL":"https:\/\/doi.org\/10.23919\/icact.2018.8323642","relation":{},"subject":[],"published":{"date-parts":[[2018,2]]}}}