Dissimilarity-Preserving Representation Learning for One-Class Time Series Classification
We propose to embed time series in a latent space where pairwise Euclidean distances (EDs) between samples are equal to pairwise dissimilarities in the original space, for a given dissimilarity measure. To this end, we use auto-encoder (AE) and encoder-only neural networks to learn elastic dissimila...
Saved in:
| Published in | IEEE transaction on neural networks and learning systems Vol. 35; no. 10; pp. 13951 - 13962 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
IEEE
01.10.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 2162-237X 2162-2388 2162-2388 |
| DOI | 10.1109/TNNLS.2023.3273503 |
Cover
| Abstract | We propose to embed time series in a latent space where pairwise Euclidean distances (EDs) between samples are equal to pairwise dissimilarities in the original space, for a given dissimilarity measure. To this end, we use auto-encoder (AE) and encoder-only neural networks to learn elastic dissimilarity measures, e.g., dynamic time warping (DTW), that are central to time series classification (Bagnall et al., 2017). The learned representations are used in the context of one-class classification (Mauceri et al., 2020) on the datasets of UCR/UEA archive (Dau et al., 2019). Using a 1-nearest neighbor (1NN) classifier, we show that learned representations allow classification performance that is close to that of raw data, but in a space of substantially lower dimensionality. This implies substantial and compelling savings in terms of computational and storage requirements for nearest neighbor time series classification. |
|---|---|
| AbstractList | We propose to embed time series in a latent space where pairwise Euclidean distances (EDs) between samples are equal to pairwise dissimilarities in the original space, for a given dissimilarity measure. To this end, we use auto-encoder (AE) and encoder-only neural networks to learn elastic dissimilarity measures, e.g., dynamic time warping (DTW), that are central to time series classification (Bagnall et al., 2017). The learned representations are used in the context of one-class classification (Mauceri et al., 2020) on the datasets of UCR/UEA archive (Dau et al., 2019). Using a 1-nearest neighbor (1NN) classifier, we show that learned representations allow classification performance that is close to that of raw data, but in a space of substantially lower dimensionality. This implies substantial and compelling savings in terms of computational and storage requirements for nearest neighbor time series classification. We propose to embed time series in a latent space where pairwise Euclidean distances (EDs) between samples are equal to pairwise dissimilarities in the original space, for a given dissimilarity measure. To this end, we use auto-encoder (AE) and encoder-only neural networks to learn elastic dissimilarity measures, e.g., dynamic time warping (DTW), that are central to time series classification (Bagnall et al., 2017). The learned representations are used in the context of one-class classification (Mauceri et al., 2020) on the datasets of UCR/UEA archive (Dau et al., 2019). Using a 1-nearest neighbor (1NN) classifier, we show that learned representations allow classification performance that is close to that of raw data, but in a space of substantially lower dimensionality. This implies substantial and compelling savings in terms of computational and storage requirements for nearest neighbor time series classification.We propose to embed time series in a latent space where pairwise Euclidean distances (EDs) between samples are equal to pairwise dissimilarities in the original space, for a given dissimilarity measure. To this end, we use auto-encoder (AE) and encoder-only neural networks to learn elastic dissimilarity measures, e.g., dynamic time warping (DTW), that are central to time series classification (Bagnall et al., 2017). The learned representations are used in the context of one-class classification (Mauceri et al., 2020) on the datasets of UCR/UEA archive (Dau et al., 2019). Using a 1-nearest neighbor (1NN) classifier, we show that learned representations allow classification performance that is close to that of raw data, but in a space of substantially lower dimensionality. This implies substantial and compelling savings in terms of computational and storage requirements for nearest neighbor time series classification. |
| Author | Sweeney, James McDermott, James Mauceri, Stefano Nicolau, Miguel |
| Author_xml | – sequence: 1 givenname: Stefano orcidid: 0000-0001-9795-5310 surname: Mauceri fullname: Mauceri, Stefano email: stefano.mauceri1@huawei-partners.com organization: Huawei Ireland Research Center, Dublin 2, Ireland – sequence: 2 givenname: James orcidid: 0000-0002-5649-3233 surname: Sweeney fullname: Sweeney, James email: james.a.sweeney@ul.ie organization: Faculty of Science and Engineering, University of Limerick, Limerick, Ireland – sequence: 3 givenname: Miguel orcidid: 0000-0002-1981-1300 surname: Nicolau fullname: Nicolau, Miguel email: miguel.nicolau@ucd.ie organization: School of Business, University College Dublin, Dublin 4, Ireland – sequence: 4 givenname: James orcidid: 0000-0002-1402-6995 surname: McDermott fullname: McDermott, James email: james.mcdermott@universityofgalway.ie organization: School of Computer Science, University of Galway, Galway, Ireland |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37204959$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkMlKA0EQhhtRNEZfQETm6GVid_U2fZS4QkhEI-hp6PTUSMsssXsi5O3NpliXWvj-OnzHZL9pGyTkjNEBY9RcTcfj0csAKPABB80l5XukB0xBCjzL9v9m_XZETmP8pKtSVCphDskR10CFkaZH3m98jL72lQ2-W6ZPASOGb998JM84Xy9NZzvfNskIbWjW97INyaTBdFjZGJOprzF5weAxJpuLL73bJE7IQWmriKe73ievd7fT4UM6mtw_Dq9HqQMtu7TQTrlSYebAUsysLGSRCcFnVohZYbQ16EqjJQgutJZOMUCaMQvWOQtG8T653P6dh_ZrgbHLax8dVpVtsF3EHDKmtBJayRV6sUMXsxqLfB58bcMy_9WxAmALuNDGGLD8QxjN19rzjfZ8rT3faV-Fzrchj4j_AgwMSM1_AOFbfsk |
| CODEN | ITNNAL |
| Cites_doi | 10.1145/2500489 10.1007/s10710-021-09403-x 10.1007/s10618-010-0179-5 10.1109/TNNLS.2020.3025813 10.1007/s10618-016-0483-9 10.1016/j.micpro.2021.104374 10.1007/s00453-022-00968-2 10.1109/CVPR.2006.100 10.1007/s10618-020-00685-w 10.1109/ICASSP.2018.8461684 10.1007/978-3-319-72926-8_48 10.1201/b11431 10.1007/978-3-540-33037-0_14 10.1109/TCSVT.2017.2711015 10.1016/0893-6080(89)90020-8 10.1371/journal.pone.0254841 10.1016/j.is.2015.04.007 10.1109/CVPR.2016.90 10.1109/ACCESS.2019.2916828 10.1109/TNNLS.2019.2935975 10.1016/j.patcog.2019.107122 10.1109/LGRS.2019.2909218 10.1109/CVPR.2015.7298682 10.1145/3182382 10.1109/IJCNN48605.2020.9206721 10.1007/s10479-012-1077-6 10.1007/978-3-319-68765-0_17 10.1145/1390156.1390294 10.1007/978-3-642-30504-7_8 10.1109/TNNLS.2020.3027736 10.3390/cryptography5040028 10.1109/TNNLS.2020.3044215 10.1609/aaai.v31i1.11231 10.1109/JAS.2019.1911747 10.1007/978-3-319-18032-8_42 10.1007/s10618-020-00710-y 10.1109/TKDE.2012.88 10.1016/j.patcog.2017.10.013 10.48550/arXiv.1312.6114 10.1007/978-3-319-05278-6 10.1109/ACCESS.2021.3101741 10.1109/GlobalSIP.2017.8308653 10.24963/ijcai.2019/394 10.1007/s10618-019-00619-1 10.1145/3318464.3389760 10.1016/j.eswa.2014.11.007 10.1109/IJCNN48605.2020.9206860 10.1109/ICCAIRO.2017.17 10.1109/tnnls.2022.3183252 10.1007/s10618-013-0322-1 10.1109/IJCNN.2017.7966039 10.1109/TCYB.2015.2426723 10.1109/TPAMI.2016.2644615 10.1109/CVPR.2015.7298594 10.1142/9789812797926_0003 10.48550/ARXIV.1706.03762 10.1007/s10618-018-0596-4 |
| ContentType | Journal Article |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7X8 |
| DOI | 10.1109/TNNLS.2023.3273503 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed MEDLINE - Academic |
| DatabaseTitleList | PubMed MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2162-2388 |
| EndPage | 13962 |
| ExternalDocumentID | 37204959 10_1109_TNNLS_2023_3273503 10129257 |
| Genre | orig-research Journal Article |
| GrantInformation_xml | – fundername: ICON plc |
| GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION NPM RIG 7X8 |
| ID | FETCH-LOGICAL-c275t-d7c6cf6e8c2a0e8a5d5d8443ba44bd97a9ecf9752434775c612e081a2acca2963 |
| IEDL.DBID | RIE |
| ISSN | 2162-237X 2162-2388 |
| IngestDate | Thu Oct 02 07:44:33 EDT 2025 Mon Jul 21 05:49:04 EDT 2025 Wed Oct 01 00:45:13 EDT 2025 Wed Aug 27 02:33:14 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 10 |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c275t-d7c6cf6e8c2a0e8a5d5d8443ba44bd97a9ecf9752434775c612e081a2acca2963 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| ORCID | 0000-0002-1402-6995 0000-0001-9795-5310 0000-0002-5649-3233 0000-0002-1981-1300 |
| PMID | 37204959 |
| PQID | 2816764765 |
| PQPubID | 23479 |
| PageCount | 12 |
| ParticipantIDs | crossref_primary_10_1109_TNNLS_2023_3273503 ieee_primary_10129257 pubmed_primary_37204959 proquest_miscellaneous_2816764765 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2024-10-01 |
| PublicationDateYYYYMMDD | 2024-10-01 |
| PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | IEEE transaction on neural networks and learning systems |
| PublicationTitleAbbrev | TNNLS |
| PublicationTitleAlternate | IEEE Trans Neural Netw Learn Syst |
| PublicationYear | 2024 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| References | Qiu (ref6) 2018 ref13 ref12 ref15 Dumoulin (ref57) 2016 ref59 ref14 ref58 ref53 ref52 ref11 ref10 ref54 ref17 ref16 ref19 ref18 Dey (ref70) 2019 Che (ref30) Goodfellow (ref55) 2016 ref50 Kingma (ref63) 2014 ref46 ref45 ref48 Le (ref34) ref41 Sak (ref25) 2014 ref44 Tobias Springenberg (ref56) 2014 ref49 ref8 ref7 ref9 ref4 ref3 ref5 ref40 ref36 ref31 ref74 ref33 ref32 ref2 ref1 ref39 ref38 ref71 ref73 ref72 Abid (ref43) Pei (ref35) 2016 ref24 ref68 ref23 ref67 ref26 ref69 ref20 ref64 ref22 ref66 ref21 Glorot (ref62) Abadi (ref65) 2015 ref28 ref27 Baldi (ref51) ref29 McFee (ref42) Salakhutdinov (ref37) ref60 Sehwag (ref75) 2021 van der Maaten (ref47) 2008; 9 ref61 |
| References_xml | – year: 2014 ident: ref56 article-title: Striving for simplicity: The all convolutional net publication-title: arXiv:1412.6806 – ident: ref66 doi: 10.1145/2500489 – ident: ref49 doi: 10.1007/s10710-021-09403-x – year: 2018 ident: ref6 article-title: Learning correlation space for time series publication-title: arXiv:1802.03628 – ident: ref58 doi: 10.1007/s10618-010-0179-5 – start-page: 1 volume-title: Proc. KDD Workshop Mining Learn. Time Ser. ident: ref30 article-title: Decade: A deep metric learning model for multivariate time series – ident: ref26 doi: 10.1109/TNNLS.2020.3025813 – volume-title: Wearable and Implantable Medical Devices: Applications and Challenges year: 2019 ident: ref70 – ident: ref1 doi: 10.1007/s10618-016-0483-9 – year: 2014 ident: ref25 article-title: Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition publication-title: arXiv:1402.1128 – ident: ref71 doi: 10.1016/j.micpro.2021.104374 – year: 2021 ident: ref75 article-title: SSD: A unified framework for self-supervised outlier detection publication-title: arXiv:2103.12051 – ident: ref53 doi: 10.1007/s00453-022-00968-2 – ident: ref39 doi: 10.1109/CVPR.2006.100 – start-page: 249 volume-title: Proc. 13th Int. Conf. Artif. Intell. Statist. ident: ref62 article-title: Understanding the difficulty of training deep feedforward neural networks – ident: ref7 doi: 10.1007/s10618-020-00685-w – ident: ref40 doi: 10.1109/ICASSP.2018.8461684 – start-page: 775 volume-title: Proc. 27th Int. Conf. Mach. Learn. (ICML) ident: ref42 article-title: Metric learning to rank – ident: ref13 doi: 10.1007/978-3-319-72926-8_48 – ident: ref14 doi: 10.1201/b11431 – year: 2016 ident: ref57 article-title: A guide to convolution arithmetic for deep learning publication-title: arXiv:1603.07285 – ident: ref10 doi: 10.1007/978-3-540-33037-0_14 – ident: ref15 doi: 10.1109/TCSVT.2017.2711015 – ident: ref12 doi: 10.1016/0893-6080(89)90020-8 – ident: ref28 doi: 10.1371/journal.pone.0254841 – ident: ref5 doi: 10.1016/j.is.2015.04.007 – ident: ref18 doi: 10.1109/CVPR.2016.90 – ident: ref64 doi: 10.1109/ACCESS.2019.2916828 – ident: ref50 doi: 10.1109/TNNLS.2019.2935975 – ident: ref2 doi: 10.1016/j.patcog.2019.107122 – ident: ref33 doi: 10.1109/LGRS.2019.2909218 – ident: ref41 doi: 10.1109/CVPR.2015.7298682 – ident: ref22 doi: 10.1145/3182382 – ident: ref23 doi: 10.1109/IJCNN48605.2020.9206721 – year: 2016 ident: ref35 article-title: Modeling time series similarity with Siamese recurrent networks publication-title: arXiv:1603.04713 – ident: ref8 doi: 10.1007/s10479-012-1077-6 – volume: 9 start-page: 2579 year: 2008 ident: ref47 article-title: Visualizing data using t-SNE publication-title: J. Mach. Learn. Res. – ident: ref44 doi: 10.1007/978-3-319-68765-0_17 – year: 2014 ident: ref63 article-title: Adam: A method for stochastic optimization publication-title: arXiv:1412.6980 – ident: ref52 doi: 10.1145/1390156.1390294 – ident: ref24 doi: 10.1007/978-3-642-30504-7_8 – ident: ref32 doi: 10.1109/TNNLS.2020.3027736 – ident: ref72 doi: 10.3390/cryptography5040028 – start-page: 107 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref34 article-title: Supervised autoencoders: Improving generalization performance with unsupervised regularizers – ident: ref27 doi: 10.1109/TNNLS.2020.3044215 – ident: ref21 doi: 10.1609/aaai.v31i1.11231 – ident: ref3 doi: 10.1109/JAS.2019.1911747 – ident: ref36 doi: 10.1007/978-3-319-18032-8_42 – ident: ref20 doi: 10.1007/s10618-020-00710-y – ident: ref54 doi: 10.1109/TKDE.2012.88 – ident: ref19 doi: 10.1016/j.patcog.2017.10.013 – ident: ref61 doi: 10.48550/arXiv.1312.6114 – ident: ref69 doi: 10.1007/978-3-319-05278-6 – ident: ref74 doi: 10.1109/ACCESS.2021.3101741 – ident: ref67 doi: 10.1109/GlobalSIP.2017.8308653 – ident: ref46 doi: 10.24963/ijcai.2019/394 – ident: ref16 doi: 10.1007/s10618-019-00619-1 – ident: ref9 doi: 10.1145/3318464.3389760 – start-page: 412 volume-title: Proc. Artif. Intell. Statist. ident: ref37 article-title: Learning a nonlinear embedding by preserving class neighbourhood structure – ident: ref73 doi: 10.1016/j.eswa.2014.11.007 – ident: ref29 doi: 10.1109/IJCNN48605.2020.9206860 – ident: ref38 doi: 10.1109/ICCAIRO.2017.17 – start-page: 37 volume-title: Proc. ICML Workshop Unsupervised Transf. Learn. ident: ref51 article-title: Autoencoders, unsupervised learning, and deep architectures – ident: ref31 doi: 10.1109/tnnls.2022.3183252 – ident: ref45 doi: 10.1007/s10618-013-0322-1 – volume-title: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems year: 2015 ident: ref65 – ident: ref17 doi: 10.1109/IJCNN.2017.7966039 – start-page: 10547 volume-title: Proc. Adv. Neural Inf. Process. Syst. ident: ref43 article-title: Learning a warping distance from unlabeled time series using sequence autoencoders – ident: ref48 doi: 10.1109/TCYB.2015.2426723 – ident: ref59 doi: 10.1109/TPAMI.2016.2644615 – ident: ref60 doi: 10.1109/CVPR.2015.7298594 – ident: ref11 doi: 10.1142/9789812797926_0003 – ident: ref68 doi: 10.48550/ARXIV.1706.03762 – ident: ref4 doi: 10.1007/s10618-018-0596-4 – volume-title: Deep Learning year: 2016 ident: ref55 |
| SSID | ssj0000605649 |
| Score | 2.4921029 |
| Snippet | We propose to embed time series in a latent space where pairwise Euclidean distances (EDs) between samples are equal to pairwise dissimilarities in the... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Publisher |
| StartPage | 13951 |
| SubjectTerms | Approximation algorithms Autoencoders Autoencoders (AEs) Convolutional neural networks Neural networks one-class classification Representation learning Time measurement Time series analysis time series classification |
| Title | Dissimilarity-Preserving Representation Learning for One-Class Time Series Classification |
| URI | https://ieeexplore.ieee.org/document/10129257 https://www.ncbi.nlm.nih.gov/pubmed/37204959 https://www.proquest.com/docview/2816764765 |
| Volume | 35 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 2162-2388 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000605649 issn: 2162-237X databaseCode: RIE dateStart: 20120101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwEB6VPfUCtOWxpa1ciRtKCI4f8RG1rFaIbiVgpeUUOc6AECKLyu6lv54ZJ0ErpJW4RVEcJ56x_c14Zj6Aw6wqkBZGyz6AKlHaZYkLHEylPBeUUkpZznf-MzHjqTqf6VmXrB5zYRAxBp9hypfxLL-ehyW7yo65FpUjHduADVuYNlnr1aGSETA3Ee7KEyMTmdtZnySTuePryeTiKmWu8DSnHVtnTKATGVoclyld2ZMiycp6vBn3ndEWTPovbsNNHtLlokrD_zfFHN_9S9uw2SFQcdqqzCf4gM1n2OrZHUQ32b_AzW-Syf3jPZm-hNQTjtXgdaW5E5cxerZLWmpEV6L1ThD-FX8bTCLRpuDkEsHON3wW8Q4HJcUWOzAdnV3_GicdEUMSpNWLpLbBhFuDRZA-w8LrWteFUnnllapqZ73DcOuslipX1upAqAkJanjpST8kTfFdGDTzBvdBqNzXbJVag1YZ7T0GQilV4ainkHk_hKNeFOVTW2-jjHZK5soow5JlWHYyHMIOD-nKk-1oDuFnL76SpgufgfgG58vnUhYnxhpljR7CXivX19a9Onxd89YD-EidqzaU7xsMFv-W-J0gyaL6EVXxBSXG2kE |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1LT9wwEB4VeoALtDyXvlyptyohOH7Ex6ot2pYlldpFWk6R4wwIVc0i2L3w6zvjJAghIXGLotixPWP78_ibGYBPWV0gLYyWbQB1orTLEheYTKU8B5RSSln2dz4tzfhM_ZzpWe-sHn1hEDGSzzDlx3iX38zDkk1lhxyLypGOrcBLTbXozl3r3qSSETQ3EfDKIyMTmdvZ4CaTucNpWU7-pJwtPM1pz9YZp9CJOVocByp9sCvFNCtPI8648xxvQjm0uSOc_E2XizoNd4_COT67U69go8eg4kunNK_hBbZbsDnkdxD9dN-G828klat_V3T4JayeMFuDV5b2UvyO_NnebakVfZDWS0EIWPxqMYmpNgW7lwg2v-GtiG-YlhRL7MDZ8ffp13HSp2JIgrR6kTQ2mHBhsAjSZ1h43eimUCqvvVJ146x3GC6c1VLlylodCDchgQ0vPWmIpEm-C6vtvMV9ECr3DZ9LrUGrjPYeA-GUunD0p5B5P4LPgyiq6y7iRhVPKpmrogwrlmHVy3AEOzykD77sRnMEHwfxVTRh-BbEtzhf3layODLWKGv0CPY6ud6XHtTh4IlaP8DaeHo6qSY_ypM3sE4NUR2x7y2sLm6W-I4AyqJ-H9XyP70j3Y4 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Dissimilarity-Preserving+Representation+Learning+for+One-Class+Time+Series+Classification&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Mauceri%2C+Stefano&rft.au=Sweeney%2C+James&rft.au=Nicolau%2C+Miguel&rft.au=McDermott%2C+James&rft.date=2024-10-01&rft.eissn=2162-2388&rft.volume=35&rft.issue=10&rft.spage=13951&rft_id=info:doi/10.1109%2FTNNLS.2023.3273503&rft_id=info%3Apmid%2F37204959&rft.externalDocID=37204959 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon |