{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T07:00:35Z","timestamp":1772521235557,"version":"3.50.1"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"European Union\u2019s HORIZON Research and Innovation Program through the Project ENFIELD","award":["101120657"],"award-info":[{"award-number":["101120657"]}]},{"name":"National Science Center","award":["2024\/53\/B\/ST6\/00021"],"award-info":[{"award-number":["2024\/53\/B\/ST6\/00021"]}]},{"name":"Agencia Nacional de Investigaci\u00f3n y Desarrollo (ANID) Fondecyt Regular","award":["1240293"],"award-info":[{"award-number":["1240293"]}]},{"DOI":"10.13039\/501100011755","name":"Basal National Center for Artificial Intelligence","doi-asserted-by":"publisher","award":["FB210017"],"award-info":[{"award-number":["FB210017"]}],"id":[{"id":"10.13039\/501100011755","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3667092","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:48:59Z","timestamp":1771879739000},"page":"29874-29893","source":"Crossref","is-referenced-by-count":0,"title":["Sparseness-Optimized Feature Importance for Time Series Classification"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8035-2887","authenticated-orcid":false,"given":"Isel","family":"Grau","sequence":"first","affiliation":[{"name":"Information Systems Group, Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1936-3701","authenticated-orcid":false,"given":"Gonzalo","family":"N\u00e1poles","sequence":"additional","affiliation":[{"name":"Department of Intelligent Systems, Tilburg University, Tilburg, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5361-5787","authenticated-orcid":false,"given":"Agnieszka","family":"Jastrzebska","sequence":"additional","affiliation":[{"name":"Faculty of Mathematics and Information Science, Warsaw University of Technology, Warsaw, Poland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1946-0053","authenticated-orcid":false,"given":"Yamisleydi","family":"Salgueiro","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering, Faculty of Engineering, Universidad de Talca, Campus Curicó, Curicó, Chile"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-018-0596-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3649448"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112253"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00844-1"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3207765"},{"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","first-page":"3319","article-title":"Axiomatic attribution for deep networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Sundararajan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-022-00823-6"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-023-00969-x"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00165"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05179-w"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07348-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/icapai49758.2021.9462056"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-019-01389-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-63797-1_20"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2023.3327834"},{"key":"ref20","article-title":"RISE: Randomized input sampling for explanation of black-box models","author":"Petsiuk","year":"2018","journal-title":"arXiv:1806.07421"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534419"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2912823"},{"key":"ref24","first-page":"1","article-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps","volume-title":"Proc. Workshop at Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref25","article-title":"SmoothGrad: Removing noise by adding noise \u00e9","author":"Smilkov","year":"2017","journal-title":"arXiv:1706.03825"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00516"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/FUZZ52849.2023.10309814"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2019.00067"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482446"},{"key":"ref30","first-page":"799","article-title":"What went wrong and when? Instance-wise feature importance for time-series black-box models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Tonekaboni"},{"key":"ref31","first-page":"3449","article-title":"Interpretable explanations of black boxes by meaningful perturbation","volume-title":"Proc. IEEE Int. Conf. Comput. Vis. (ICCV)","author":"Fong"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s21041059"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533293"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDMW51313.2020.00068"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30493-5_43"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.117721"},{"key":"ref37","first-page":"1","article-title":"Semiconductor demand forecasting using long short-term cognitive networks","volume-title":"Proc. 34th Benelux Conf. Artif. Intell. 31st Belgian-Dutch Conf. Mach. Learn.","author":"Grau"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/sym13010110"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207341"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICAwST.2019.8923166"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934267"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6165"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-44070-0_9"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557418"},{"key":"ref45","doi-asserted-by":"crossref","first-page":"292","DOI":"10.1007\/978-3-032-08330-2_14","article-title":"Class-dependent perturbation effects in evaluating time series attributions","volume-title":"Explainable Artificial Intelligence","author":"Baer","year":"2026"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1142\/9789812813305_0005"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2012.737745"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2019.107299"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00710-y"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-024-01022-1"},{"key":"ref51","volume-title":"The UCR Time Series Classification Archive","author":"Dau","year":"2018"},{"key":"ref52","first-page":"1","article-title":"Restricting the flow: Information bottlenecks for attribution","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schulz"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1214\/14-AOS1245"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2001.989531"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"key":"ref56","first-page":"1","article-title":"Should we really use post-hoc tests based on mean-ranks?","volume":"17","author":"Benavoli","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1037\/a0028086"},{"key":"ref58","article-title":"Why do class-dependent evaluation effects occur with time series feature attributions? A synthetic data investigation","author":"Baer","year":"2025","journal-title":"arXiv:2506.11790"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1852102.1852106"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-08327-2_11"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3127"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3548606.3559392"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaaiss.v7i1.36893"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11406121.pdf?arnumber=11406121","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T06:22:40Z","timestamp":1772518960000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11406121\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3667092","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}