{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:11:30Z","timestamp":1777705890191,"version":"3.51.4"},"reference-count":12,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IFS"],"published-print":{"date-parts":[[2022,4,28]]},"abstract":"<jats:p>Classification algorithms are widely applied to predict failures and detect anomalies in various application areas. It is common to assume that the data and labels are correct when training, but this is challenging to guarantee in the real world. If there are erroneous labels in the training data, a model can easily overfit to these, resulting in poor performance. How to handle label noise has been previously researched, however, few works focus on label noise in anomaly detection. In this work, we propose LDAAD, a novel algorithm framework for label de-noising for anomaly detection that combines unsupervised learning and semi-supervised learning methods. Specifically, we apply anomaly detection to partition the training data into low-risk and high-risk sets. We subsequently build upon ideas from cross-validation and train multiple classification models on segments of the low-risk data. The models are used both to relabel the samples in the high-risk set and to filter the low-risk samples. Finally, we merge the two sets to obtain a final sample set with more confident labels. We evaluate LDAAD on multiple real-world datasets and show that LDAAD achieves robust results that outperform the benchmark methods. Specifically, LDAAD achieves a 5% accuracy improvement over the second-best method for symmetric noise while having a minimal detrimental impact when no label noise is present.<\/jats:p>","DOI":"10.3233\/jifs-212096","type":"journal-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T13:12:37Z","timestamp":1648559557000},"page":"5627-5637","source":"Crossref","is-referenced-by-count":1,"title":["LDAAD: An effective label de-noising approach for anomaly detection"],"prefix":"10.1177","volume":"42","author":[{"given":"Lujia","family":"Pan","sequence":"first","affiliation":[{"name":"NSKeyLab, Xi\u2019an Jiaotong University, Xi\u2019an, China"},{"name":"Noah\u2019s Ark Lab, Huawei Technologies, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcus","family":"Kalander","sequence":"additional","affiliation":[{"name":"Noah\u2019s Ark Lab, Huawei Technologies, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pinghui","family":"Wang","sequence":"additional","affiliation":[{"name":"NSKeyLab, Xi\u2019an Jiaotong University, Xi\u2019an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"issue":"1\u20134","key":"10.3233\/JIFS-212096_ref1","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1007\/s00170-019-03557-w","article-title":"A deep learning approach foranomaly detection based on SAE and LSTM in mechanical equipment","volume":"103","author":"Li","year":"2019","journal-title":"The International Journal of Advanced Manufacturing Technology"},{"issue":"3","key":"10.3233\/JIFS-212096_ref3","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1109\/TNSM.2019.2927886","article-title":"Ahybrid deep learning-based model for anomaly detection in clouddatacenter networks","volume":"16","author":"Garg","year":"2019","journal-title":"IEEE Transactions on Network and ServiceManagement"},{"issue":"5","key":"10.3233\/JIFS-212096_ref4","doi-asserted-by":"crossref","first-page":"2505","DOI":"10.1109\/TSG.2017.2703842","article-title":"Real-time detection of false datainjection attacks in smart grid: A deep learning-based intelligentmechanism","volume":"8","author":"He","year":"2017","journal-title":"IEEE Transactions on Smart Grid"},{"key":"10.3233\/JIFS-212096_ref5","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.cose.2015.09.005","article-title":"Intelligent financial fraud detection:a comprehensive review","volume":"57","author":"West","year":"2016","journal-title":"Computers & Security"},{"issue":"5","key":"10.3233\/JIFS-212096_ref6","doi-asserted-by":"crossref","first-page":"845","DOI":"10.1109\/TNNLS.2013.2292894","article-title":"Classification in the presence oflabel noise: a survey","volume":"25","author":"Fr\u00e9nay","year":"2013","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"2010","key":"10.3233\/JIFS-212096_ref17","first-page":"2973","article-title":"Semi-supervised noveltydetection","volume":"11","author":"Blanchard","journal-title":"The Journal of Machine Learning Research"},{"key":"10.3233\/JIFS-212096_ref20","doi-asserted-by":"crossref","first-page":"106969","DOI":"10.1016\/j.comnet.2019.106969","article-title":"Proactive microwave link anomaly detection in cellular datanetworks","volume":"167","author":"Pan","year":"2020","journal-title":"Computer Networks"},{"key":"10.3233\/JIFS-212096_ref21","doi-asserted-by":"crossref","first-page":"100059","DOI":"10.1016\/j.iot.2019.100059","article-title":"Attack and anomalydetection in IoT sensors in IoT sites using machine learningapproaches","volume":"7","author":"Hasan","year":"2019","journal-title":"Internet of Things"},{"key":"10.3233\/JIFS-212096_ref23","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.neucom.2014.09.081","article-title":"Making risk minimizationtolerant to label noise","volume":"160","author":"Ghosh","year":"2015","journal-title":"Neurocomputing"},{"key":"10.3233\/JIFS-212096_ref32","unstructured":"Chen Y. , Garcia E.K. , Gupta M.R. , Rahimi A. and Cazzanti L. , Similarity-based classification: Concepts and algorithms, Journal of Machine Learning Research 10(3) (2009)."},{"issue":"3","key":"10.3233\/JIFS-212096_ref33","first-page":"12","article-title":"N-baiot\u2014network-based detectionof iot botnet attacks using deep autoencoders","volume":"17","author":"Meidan","year":"2018","journal-title":"IEEE PervasiveComputing"},{"issue":"1","key":"10.3233\/JIFS-212096_ref36","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JIFS-212096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:45:31Z","timestamp":1777455931000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/JIFS-212096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,28]]},"references-count":12,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/jifs-212096","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,28]]}}}