{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T04:40:27Z","timestamp":1777696827499,"version":"3.51.4"},"reference-count":49,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["12473105,12473106, 62306205"],"award-info":[{"award-number":["12473105,12473106, 62306205"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Projects of Science and Technology Cooperation and Exchange of Shanxi Province","award":["202204041101037, 202204041101033"],"award-info":[{"award-number":["202204041101037, 202204041101033"]}]},{"name":"the Fundamental Research Program of Shanxi Province","award":["2022030212 22189"],"award-info":[{"award-number":["2022030212 22189"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Data Analysis: An International Journal"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>\n                    Prototypes help to explain the predictions of deep classification models for time series. However, most models learn prototypes by randomly initializing an uncertain number of low-discriminative prototypes, which may lead to unstable models and unreliable results. To address these issues, we propose a new class\n                    <jats:bold>D<\/jats:bold>\n                    iscriminative\n                    <jats:bold>P<\/jats:bold>\n                    rototype\n                    <jats:bold>L<\/jats:bold>\n                    earning\n                    <jats:bold>Net<\/jats:bold>\n                    work (DPL-Net), which learns an appropriate number of class-discriminative prototypes, thus improving classification performance. Specifically, the proposed\n                    <jats:bold>P<\/jats:bold>\n                    rototype\n                    <jats:bold>I<\/jats:bold>\n                    nitialization\n                    <jats:bold>M<\/jats:bold>\n                    echanism (PIM) introduces a new proximity metric based on the silhouette coefficient and statistical metrics. It facilitates the automatic determination of the class-discriminative prototypes for each class. Then, the encoder layer encodes the prototypes derived from PIM and the input series using one-dimensional convolutional neural networks (1D-CNN). Finally, the prototype classification layer optimizes the prototypes according to the regularization terms, while simultaneously classifying the input sequence based on its similarity to the updated prototypes. The comparison experiments are conducted on 26 UCR datasets compared with 10 baselines. The results show that our proposed approach achieves the best accuracy on 11 datasets. Specifically, our method outperforms PIP, CSSL, and LSS by an average of 16.33%, 9.77% and 5.96% on 22, 14 and 16 datasets, respectively. The interpretability experimental results and the application analysis on spectral data indicate that the learned prototypes can provide reasonable explanations for the classification results of the model.\n                  <\/jats:p>","DOI":"10.1177\/1088467x251319188","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T03:39:52Z","timestamp":1740627592000},"page":"1419-1437","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable deep classification of time series based on class discriminative prototype learning"],"prefix":"10.1177","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1021-0744","authenticated-orcid":false,"given":"Yupeng","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electronic Information Engineer, Taiyuan University of Science and Technology, ShanXi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6945-8093","authenticated-orcid":false,"given":"Jianghui","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Taiyuan University of Science and Technology, ShanXi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3280-7584","authenticated-orcid":false,"given":"Haifeng","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Taiyuan University of Science and Technology, ShanXi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6511-0898","authenticated-orcid":false,"given":"Chenhui","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Electronic Information Engineer, Taiyuan University of Science and Technology, ShanXi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3694-2040","authenticated-orcid":false,"given":"Min","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Taiyuan University of Science and Technology, ShanXi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0820-5046","authenticated-orcid":false,"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Taiyuan University of Science and Technology, ShanXi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ran","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Taiyuan University of Science and Technology, ShanXi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xujun","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Taiyuan University of Science and Technology, ShanXi, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"},{"key":"e_1_3_4_3_2","doi-asserted-by":"crossref","unstructured":"Huang C et\u00a0al. Deep prototypical networks for imbalanced time series classification under data scarcity. In: Proceedings of the 28th ACM international conference on information and knowledge management 2019 pp.2141\u20132144. DOI: 10.1145\/3357384.3358162.","DOI":"10.1145\/3357384.3358162"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2020.3027279"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-016-0483-9"},{"key":"e_1_3_4_6_2","first-page":"179","volume-title":"data big data appl power syst","author":"Susto G","year":"2018","unstructured":"Susto G, Cenedese A, Terzi M. Chapter 9 - Time-series classification methods: review and applications to power systems. In: data big data appl power syst. Elsevier, 2018, pp.179\u2013220."},{"key":"e_1_3_4_7_2","doi-asserted-by":"crossref","unstructured":"Wang Z Yan W Oates T. Time series classification from scratch with deep neural networks: a strong baseline. In: 2017 International joint conference on neural networks (IJCNN) 2017 pp.1578\u20131585.","DOI":"10.1109\/IJCNN.2017.7966039"},{"key":"e_1_3_4_8_2","doi-asserted-by":"crossref","unstructured":"Tang W Liu L Long G. Interpretable Time-series classification on Few-shot samples. In: 2020 International joint conference on neural networks (IJCNN) 2020 pp.1\u20138. UK: Glasgow. DOI: 10.1109\/IJCNN48605.2020.9206860.","DOI":"10.1109\/IJCNN48605.2020.9206860"},{"key":"e_1_3_4_9_2","doi-asserted-by":"crossref","unstructured":"Li O et\u00a0al. Deep learning for case-based reasoning through prototypes: a neural network that explains its predictions. In: Proceedings of the AAAI conference on artificial intelligence 2018 (Vol. 32 No. 1) pp.166\u2013185. DOI: 10.1609\/aaai.v32i1.11771.","DOI":"10.1609\/aaai.v32i1.11771"},{"key":"e_1_3_4_10_2","doi-asserted-by":"crossref","unstructured":"Ming Y et\u00a0al. Interpretable and steerable sequence learning via prototypes. In: Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining 2019 pp.903\u2013913. DOI: 10.1145\/3292500.3330908.","DOI":"10.1145\/3292500.3330908"},{"key":"e_1_3_4_11_2","doi-asserted-by":"crossref","unstructured":"Guillem\u00e9 M et\u00a0al. Agnostic local explanation for time series classification. In: IEEE 31st international conference on tools with artificial intelligence (ICTAI) 2019 pp.432\u2013439. DOI: 10.1109\/ICTAI.2019.00067.","DOI":"10.1109\/ICTAI.2019.00067"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2018.04.005"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2018.2864702"},{"key":"e_1_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.aei.2023.102024"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10304-3"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3561048"},{"key":"e_1_3_4_18_2","doi-asserted-by":"crossref","unstructured":"Ribeiro MT et\u00a0al. \u201cWhy should i trust you?\u201d Explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining 2016 pp.1135\u20131144.","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_4_19_2","first-page":"4765","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Scott M","year":"2017","unstructured":"Scott M, Su-In L. A unified approach to interpreting model predictions. Adv Neural Inf Process Syst 2017; 30: 4765\u20134774.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110309"},{"key":"e_1_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6579\/aaf34d"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2744158"},{"key":"e_1_3_4_23_2","doi-asserted-by":"crossref","unstructured":"Grabocka J et\u00a0al. Learning time-series shapelets. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining 2014 pp.392\u2013401. DOI: 10.1145\/2623330.2623613.","DOI":"10.1145\/2623330.2623613"},{"key":"e_1_3_4_24_2","doi-asserted-by":"crossref","unstructured":"Shah M et\u00a0al. Learning DTW-shapelets for time-series classification. In: Proceedings of the 3rd IKDD conference on data science 2016 pp.1\u20138. DOI: 10.1145\/2888451.2888456.","DOI":"10.1145\/2888451.2888456"},{"key":"e_1_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.2995870"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.03.063"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04422-2"},{"key":"e_1_3_4_28_2","doi-asserted-by":"crossref","unstructured":"Ma D et\u00a0al. Modeling multivariate time series via prototype learning: a multi-level attention-based perspective. In: IEEE international conference on bioinformatics and biomedicine (BIBM) 2020 pp.687\u2013693. DOI: 10.1109\/BIBM49941.2020.9313406.","DOI":"10.1109\/BIBM49941.2020.9313406"},{"key":"e_1_3_4_29_2","doi-asserted-by":"crossref","unstructured":"Ma D et\u00a0al. Interpretable multivariate time series classification based on prototype learning. In: Green pervasive and cloud computing: 15th International conference GPC 2020 Xi\u2019an China November 13\u201315 2020 Proceedings 15 pp.205\u2013216. DOI: 10.1007\/978-3-030-64243-3_16.","DOI":"10.1007\/978-3-030-64243-3_16"},{"key":"e_1_3_4_30_2","unstructured":"Ghosal G Abbasi-Asl R. Multi-modal prototype learning for interpretable multivariable time series classification. arXiv preprint arXiv:2106.09636 2021 p.113435. DOI: 10.48550\/arXiv.2106.09636."},{"key":"e_1_3_4_31_2","doi-asserted-by":"crossref","unstructured":"Zhang X et\u00a0al. TAPNET: multivariate time series classification with attentional prototypical network. In: Proceedings of the AAAI conference on artificial intelligence 2020 (Vol. 34 No. 04) pp.1149\u20131163. DOI: 10.1609\/aaai.v34i04.6165.","DOI":"10.1609\/aaai.v34i04.6165"},{"key":"e_1_3_4_32_2","doi-asserted-by":"crossref","unstructured":"Chang X Tung F Mori G. Learning discriminative prototypes with dynamic time warping. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition 2021 pp.8395\u20138404.","DOI":"10.1109\/CVPR46437.2021.00829"},{"key":"e_1_3_4_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2021.3129957"},{"key":"e_1_3_4_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107098"},{"key":"e_1_3_4_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.09.044"},{"key":"e_1_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109974"},{"key":"e_1_3_4_37_2","doi-asserted-by":"crossref","unstructured":"Deng H et\u00a0al. Robust shapelets learning: transform-invariant prototypes. In: Pattern recognition and computer vision: first chinese conference PRCV 2018 Guangzhou China 2018 pp.491\u2013502.","DOI":"10.1007\/978-3-030-03338-5_41"},{"key":"e_1_3_4_38_2","doi-asserted-by":"crossref","unstructured":"Zheng G et\u00a0al. Efficient shift-invariant dictionary learning. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining 2016 pp.2095\u20132104.","DOI":"10.1145\/2939672.2939824"},{"key":"e_1_3_4_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110943"},{"key":"e_1_3_4_40_2","unstructured":"Li B et\u00a0al. Prototypes as explanation for time series anomaly detection. In: arxiv preprint arxiv:2307.01601 2023."},{"key":"e_1_3_4_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3335962"},{"key":"e_1_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3373782"},{"key":"e_1_3_4_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-021-00740-0"},{"key":"e_1_3_4_44_2","unstructured":"Kingma DP Ba J. ADAM: a method for stochastic optimization 2014. 10.48550\/arXiv.1412.6980."},{"key":"e_1_3_4_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2015.02.005"},{"key":"e_1_3_4_46_2","unstructured":"Bagnall A et\u00a0al. A tale of two toolkits report the third: on the usage and performance of HIVE-COTE v1.0. arXiv preprint arXiv:2004.06069 2020."},{"key":"e_1_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-020-00701-z"},{"key":"e_1_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1093\/mnras\/stac3292"},{"key":"e_1_3_4_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3522592"},{"key":"e_1_3_4_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911747"}],"container-title":["Intelligent Data Analysis: An International Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X251319188","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/1088467X251319188","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/1088467X251319188","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:21:04Z","timestamp":1777454464000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/1088467X251319188"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":49,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/1088467X251319188"],"URL":"https:\/\/doi.org\/10.1177\/1088467x251319188","relation":{},"ISSN":["1088-467X","1571-4128"],"issn-type":[{"value":"1088-467X","type":"print"},{"value":"1571-4128","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,27]]}}}