{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T23:25:31Z","timestamp":1783553131744,"version":"3.55.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3591554","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T18:06:50Z","timestamp":1753207610000},"page":"130098-130109","source":"Crossref","is-referenced-by-count":2,"title":["SHAP-Based Feature Selection for Enhanced Unsupervised Labeling"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2403-7763","authenticated-orcid":false,"given":"Mary Anne","family":"Walauskis","sequence":"first","affiliation":[{"name":"College of Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taghi M.","family":"Khoshgoftaar","sequence":"additional","affiliation":[{"name":"College of Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"673","article-title":"Classifying unstructured clinical notes via automatic weak supervision","volume-title":"Proc. 7th Mach. Learn. Healthcare Conf.","author":"Gao"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10515-024-00435-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64148-1_13"},{"key":"ref4","first-page":"478","article-title":"Unsupervised deep embedding for clustering analysis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xie"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwt032"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3136625"},{"key":"ref7","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lundberg"},{"key":"ref8","volume-title":"Credit Card Fraud Detection","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.17"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-6346-1_10"},{"issue":"5","key":"ref11","doi-asserted-by":"crossref","first-page":"611","DOI":"10.3390\/e24050611","article-title":"Cluster-based improved isolation forest","volume":"24","author":"Shao","year":"2022","journal-title":"Entropy"},{"issue":"1","key":"ref12","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.datak.2007.01.002","article-title":"Investigating diversity of clustering methods: An empirical comparison","volume":"63","author":"Gelbard","year":"2007","journal-title":"Data Knowl. Eng."},{"key":"ref13","volume-title":"Criminal Resource Manual: 976. Health Care Fraud Generally","year":"2025"},{"key":"ref14","volume-title":"Victims of Identity Theft, 2021"},{"key":"ref15","volume-title":"Credit Card Fraud Report","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI62512.2024.00042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-025-01120-x"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-024-01041-1"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/10255842.2023.2263125"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10044-024-01340-6"},{"issue":"3","key":"ref21","doi-asserted-by":"crossref","first-page":"856","DOI":"10.1016\/j.bbe.2022.06.007","article-title":"Diagnosis of Parkinson\u2019s disease based on SHAP value feature selection","volume":"42","author":"Liu","year":"2022","journal-title":"Biocybern. Biomed. Eng."},{"issue":"6","key":"ref22","doi-asserted-by":"crossref","first-page":"305","DOI":"10.3390\/systems11060305","article-title":"Credit card fraud detection based on unsupervised attentional anomaly detection network","volume":"11","author":"Jiang","year":"2023","journal-title":"Systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/RAICS51191.2020.9332497"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SRDS.2016.019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICEEM52022.2021.9480639"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06497-5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/BIGSARDATA59007.2023.10294846"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078195"},{"key":"ref29","volume-title":"Sklearn.Preprocessing.Normalize","year":"2024"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109924"},{"key":"ref31","volume-title":"Pandas.Dataframe.Samples\u2014Pandas Documentation","year":"2024"},{"key":"ref32","article-title":"Efficient tabular data preprocessing of ML pipelines","author":"Zhu","year":"2024","journal-title":"arXiv:2409.14912"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.38124\/ijisrt\/ijisrt24oct1507"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-017-4566-4"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.procs.2020.04.017","article-title":"Clustering cloud workloads: K-means vs Gaussian mixture model","volume":"171","author":"Patel","year":"2020","journal-title":"Proc. Comput. Sci."},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ojsp.2020.3039330"},{"key":"ref37","volume-title":"Nystroem","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI56018.2022.00202"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3631326"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88942-5_6"},{"issue":"1","key":"ref41","first-page":"4","article-title":"Choosing the right metrics: A study of performance measurement for binary classification in imbalanced and big data","volume-title":"Int. FLAIRS Conf. Proc.","volume":"38","author":"Walauskis"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1186\/s13104-022-06096-y"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s13748-016-0094-0"},{"key":"ref45","article-title":"Anomaly detection using unsupervised machine learning algorithms: A simulation study","volume":"26","author":"Agyemang","year":"2024","journal-title":"Sci. Afr."},{"key":"ref46","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.patcog.2016.03.028","article-title":"High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning","volume":"58","author":"Erfani","year":"2016","journal-title":"Pattern Recognit."}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11088106.pdf?arnumber=11088106","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T05:01:36Z","timestamp":1753765296000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11088106\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3591554","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}