{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T03:50:20Z","timestamp":1761709820163,"version":"3.41.2"},"reference-count":36,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,3,3]],"date-time":"2021-03-03T00:00:00Z","timestamp":1614729600000},"content-version":"vor","delay-in-days":61,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002383","name":"King Saud University","doi-asserted-by":"publisher","award":["RG-1439-035"],"award-info":[{"award-number":["RG-1439-035"]}],"id":[{"id":"10.13039\/501100002383","id-type":"DOI","asserted-by":"publisher"}]}],"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>Noise in training data increases the tendency of many machine learning methods to overfit the training data, which undermines the performance. Outliers occur in big data as a result of various factors, including human errors. In this work, we present a novel discriminator model for the identification of outliers in the training data. We propose a systematic approach for creating training datasets to train the discriminator based on a small number of genuine instances (trusted data). The noise discriminator is a convolutional neural network (CNN). We evaluate the discriminator\u2019s performance using several benchmark datasets and with different noise ratios. We inserted random noise in each dataset and trained discriminators to clean them. Different discriminators were trained using different numbers of genuine instances with and without data augmentation. We compare the performance of the proposed noise\u2010discriminator method with seven other methods proposed in the literature using several benchmark datasets. Our empirical results indicate that the proposed method is very competitive to the other methods. It actually outperforms them for pair noise.<\/jats:p>","DOI":"10.1155\/2021\/8811147","type":"journal-article","created":{"date-parts":[[2021,3,4]],"date-time":"2021-03-04T06:05:05Z","timestamp":1614837905000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Convolutional Neural Network\u2010Based Discriminator for Outlier Detection"],"prefix":"10.1155","volume":"2021","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6510-9475","authenticated-orcid":false,"given":"Fahad","family":"Alharbi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2457-9961","authenticated-orcid":false,"given":"Khalil","family":"El Hindi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9406-6809","authenticated-orcid":false,"given":"Saad","family":"Al Ahmadi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hussien","family":"Alsalamn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,3,3]]},"reference":[{"volume-title":"Semi-Supervised Learning Literature Survey","year":"2005","author":"Zhu X. J.","key":"e_1_2_9_1_2"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.606"},{"key":"e_1_2_9_3_2","doi-asserted-by":"publisher","DOI":"10.25079\/ukhjse.v3n2y2019.pp31-40"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-47952-1_6"},{"volume-title":"Machine Learning","year":"1997","author":"Mitchell T. M.","key":"e_1_2_9_5_2"},{"key":"e_1_2_9_6_2","unstructured":"AlganG.andUlusoyI. Image classification with deep learning in the presence of noisy labels: a survey 2019 http:\/\/arxiv.org\/abs\/1912.05170."},{"key":"e_1_2_9_7_2","unstructured":"GoodfellowI. J. Pouget-abadieJ. MirzaM.et al. Generative adversarial nets Proceedings of the Advances in Neural Information Processing Systems 2014 Montreal Canada 2672\u20132680."},{"key":"e_1_2_9_8_2","unstructured":"MnihV.andHintonG. Learning to label aerial images from noisy data Proceedings of the 29th International Conference on Machine Learning 2012 Edinburgh UK 567\u2013574."},{"key":"e_1_2_9_9_2","unstructured":"ReedS. E.andLeeH. Training deep neural networks on noisy labels with bootstrapping 2014 1\u201311 http:\/\/arxiv.org\/abs\/1412.6596."},{"key":"e_1_2_9_10_2","doi-asserted-by":"publisher","DOI":"10.14311\/nnw.2011.21.019"},{"key":"e_1_2_9_11_2","unstructured":"El HindiK.andAL-AkhrasM. Eliminating border instance to avoid overfitting Proceedings of the Intelligent Systems and Agents 2009 Algarve Portugal 93\u201399."},{"key":"e_1_2_9_12_2","unstructured":"ZengX.andMartinezT. A noise filtering method using neural networks Proceedings of the 2003 IEEE International. Workshop on Soft Computing Techniques in Instrumentation Measurement and Related Applications (SCIMA 2003) 2003 Provo UT USA 26\u201331."},{"key":"e_1_2_9_13_2","unstructured":"SukhbaatarS.andFergusR. Learning from noisy labels with deep neural networks 2014 http:\/\/arxiv.org\/abs\/1406.2080."},{"key":"e_1_2_9_14_2","unstructured":"HintonG. VinyalsO. andDeanJ. Distilling the knowledge in a neural network 2015 http:\/\/arxiv.org\/abs\/1503.02531."},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"LiY. YangJ. andSongY. Learning from noisy labels with distillation Proceedings of the IEEE International Conference on Computer Vision October 2017 Venice Italy 1910\u20131918.","DOI":"10.1109\/ICCV.2017.211"},{"key":"e_1_2_9_16_2","unstructured":"HendrycksD. MazeikaM. WilsonD. andGimpelK. Using trusted data to train deep networks on labels corrupted by severe noise Proceedings of the Conference on Neural Information Processing Systems (NeurIPS) December 2018 Montreal Canada 10456\u201310465."},{"volume-title":"UCI Machine Learning Repository: Optical Recognition of Handwritten Digits Data Set","year":"2020","key":"e_1_2_9_17_2"},{"key":"e_1_2_9_18_2","unstructured":"KrizhevskyA.andHintonG. Learning multiple layers of features from tiny images 2009 University of Toronto Toronto Canada Tech. Report."},{"key":"e_1_2_9_19_2","unstructured":"NetzerY. WangT. CoatesT. BissaccoA. WuB. andNgA. Y. Reading digits in natural images with unsupervised feature learning Proceedings of the NIPS Workshop on Deep Learning and Unsupervised Feature Learning December 2011 Granada Spain."},{"key":"e_1_2_9_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101759"},{"key":"e_1_2_9_21_2","doi-asserted-by":"crossref","unstructured":"XiaoT. XiaT. YangY. HuangC. andWangX. Learning from massive noisy labeled data for image classification Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) June 2015 Boston MA USA 2691\u20132699 https:\/\/doi.org\/10.1109\/CVPR.2015.7298885 2-s2.0-84959207049.","DOI":"10.1109\/CVPR.2015.7298885"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"WeiH. FengL. ChenX. andAnB. Combating noisy labels by agreement\u202f: a joint training method with co-regularization 2020 http:\/\/arxiv.org\/abs\/2003.02752.","DOI":"10.1109\/CVPR42600.2020.01374"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.3019465"},{"volume-title":"Dynamic Noise Identification and Elimination during Neural Networks Training","year":"2020","author":"Alharbi F.","key":"e_1_2_9_24_2"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"volume-title":"Deep Learning","year":"2016","author":"Goodfellow I.","key":"e_1_2_9_26_2"},{"key":"e_1_2_9_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2016.2584107"},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"HeK. ZhangX. RenS. andSunJ. Deep residual learning for image recognition Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 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_9_29_2","unstructured":"HanB. YaoQ. YuX.et al. Co-teaching\u202f: robust training of deep neural networks with extremely noisy labels Proceedings of the Advances in Neural Information Processing Systems December 2018 Montreal Canada 8527\u20138537."},{"key":"e_1_2_9_30_2","unstructured":"Van RooyenB. MenonA. andWilliamsonR. C. Learning with symmetric label noise: the importance of being unhinged Proceedings of the Advances in Neural Information Processing Systems December 2015 Montreal Canada 10\u201318."},{"key":"e_1_2_9_31_2","unstructured":"GoldbergerJ.andBen-reuvenE. Training deep neural-networks using a noise adaptation layer Proceedings of the International Conference on Learning Representations April 2017 Toulon France."},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"PatriniG. RozzaA. MenonA. K. NockR. andQuL. Making deep neural networks robust to label noise\u202f: a loss correction approach Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) July 2017 Honolulu HI USA https:\/\/doi.org\/10.1109\/CVPR.2017.240 2-s2.0-85042632149.","DOI":"10.1109\/CVPR.2017.240"},{"key":"e_1_2_9_33_2","unstructured":"MalachE.andShalev-ShwartzS. Decoupling \u2018 When to update \u2019 from \u2018 How to update Proceedings of the Neural Information Processing Systems 2017 Long Beach CA USA 960\u2013970."},{"key":"e_1_2_9_34_2","unstructured":"JiangL. ZhouZ. LeungT. LiL.-J. andFei-FeiL. MentorNet\u202f: learning data-driven curriculum for very deep neural networks on norrupted labels Proceedings of the International Conference on Machine Learning July 2018 Stockholm Sweden 2304\u20132313."},{"key":"e_1_2_9_35_2","unstructured":"XiaoH. RasulK. andVollgrafR. Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms 2017 http:\/\/arxiv.org\/abs\/1708.07747."},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"StallkampJ. SchlipsingM. SalmenJ. andIgelC. The German traffic sign recognition benchmark: a multi-class classification competition Proceedings of the 2011 International Joint Conference on Neural Networks July 2011 San Jose CA USA 1453\u20131460 https:\/\/doi.org\/10.1109\/IJCNN.2011.6033395 2-s2.0-80054726665.","DOI":"10.1109\/IJCNN.2011.6033395"}],"container-title":["Computational Intelligence and Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/8811147.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/cin\/2021\/8811147.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/8811147","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T11:49:55Z","timestamp":1722944995000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/8811147"}},"subtitle":[],"editor":[{"given":"Qiangqiang","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/8811147"],"URL":"https:\/\/doi.org\/10.1155\/2021\/8811147","archive":["Portico"],"relation":{},"ISSN":["1687-5265","1687-5273"],"issn-type":[{"type":"print","value":"1687-5265"},{"type":"electronic","value":"1687-5273"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-03-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-02-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-03-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8811147"}}