Self-Supervised Learning-Based Time Series Classification via Hierarchical Sparse Convolutional Masked-Autoencoder
In recent years, the use of time series analysis has become widespread, prompting researchers to explore methods to improve classification. Time series self-supervised learning has emerged as a significant area of study, aiming to uncover patterns in unlabeled data for richer information. Contrastiv...
Uložené v:
| Vydané v: | IEEE open journal of signal processing Ročník 5; s. 964 - 975 |
|---|---|
| Hlavní autori: | , , , , |
| Médium: | Journal Article |
| Jazyk: | English |
| Vydavateľské údaje: |
New York
IEEE
2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Predmet: | |
| ISSN: | 2644-1322, 2644-1322 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | In recent years, the use of time series analysis has become widespread, prompting researchers to explore methods to improve classification. Time series self-supervised learning has emerged as a significant area of study, aiming to uncover patterns in unlabeled data for richer information. Contrastive self-supervised learning, particularly, has gained attention for time series classification. However, it introduces inductive bias by generating positive and negative samples. Another approach involves Masked Autoencoders (MAE), which are effective for various data types. However, due to their reliance on the Transformer architecture, they demand significant computational resources during the pre-training phase. Recently, inspired by the remarkable advancements achieved by convolutional networks in the domain of time series forecasting, we aspire to employ convolutional networks utilizing a strategy of mask recovery for pre-training time series models. This study introduces a novel model termed Hierarchical Sparse Convolutional Masked-Autoencoder, "HSC-MAE", which seamlessly integrates convolutional operations with the MAE architecture to adeptly capture time series features across varying scales. Furthermore, the HSC-MAE model incorporates dedicated decoders that amalgamate global and local information, enhancing its capacity to comprehend intricate temporal patterns. To gauge the effectiveness of the proposed approach, an extensive array of experiments was conducted across nine distinct datasets. The experimental outcomes stand as a testament to the efficacy of HSC-MAE in effectively mitigating the aforementioned challenges. |
|---|---|
| AbstractList | In recent years, the use of time series analysis has become widespread, prompting researchers to explore methods to improve classification. Time series self-supervised learning has emerged as a significant area of study, aiming to uncover patterns in unlabeled data for richer information. Contrastive self-supervised learning, particularly, has gained attention for time series classification. However, it introduces inductive bias by generating positive and negative samples. Another approach involves Masked Autoencoders (MAE), which are effective for various data types. However, due to their reliance on the Transformer architecture, they demand significant computational resources during the pre-training phase. Recently, inspired by the remarkable advancements achieved by convolutional networks in the domain of time series forecasting, we aspire to employ convolutional networks utilizing a strategy of mask recovery for pre-training time series models. This study introduces a novel model termed Hierarchical Sparse Convolutional Masked-Autoencoder, "HSC-MAE", which seamlessly integrates convolutional operations with the MAE architecture to adeptly capture time series features across varying scales. Furthermore, the HSC-MAE model incorporates dedicated decoders that amalgamate global and local information, enhancing its capacity to comprehend intricate temporal patterns. To gauge the effectiveness of the proposed approach, an extensive array of experiments was conducted across nine distinct datasets. The experimental outcomes stand as a testament to the efficacy of HSC-MAE in effectively mitigating the aforementioned challenges. |
| Author | Xu, Kele Wang, Xu Ding, Bo Feng, Dawei Yu, Ting |
| Author_xml | – sequence: 1 givenname: Ting orcidid: 0009-0004-4451-2275 surname: Yu fullname: Yu, Ting organization: College of Computer, National University of Defense Technology, Changsha, China – sequence: 2 givenname: Kele orcidid: 0000-0001-5997-5169 surname: Xu fullname: Xu, Kele email: xukelele@163.com organization: College of Computer, National University of Defense Technology, Changsha, China – sequence: 3 givenname: Xu orcidid: 0009-0007-0006-7781 surname: Wang fullname: Wang, Xu organization: College of Computer, National University of Defense Technology, Changsha, China – sequence: 4 givenname: Bo orcidid: 0000-0002-1236-8318 surname: Ding fullname: Ding, Bo organization: College of Computer, National University of Defense Technology, Changsha, China – sequence: 5 givenname: Dawei orcidid: 0000-0002-7587-8905 surname: Feng fullname: Feng, Dawei organization: College of Computer, National University of Defense Technology, Changsha, China |
| BookMark | eNpNUV1v1DAQtFCRKEd_QCUeIvGcw59x_FhO0BYdKlLaZ2vPXhcfaXzYyUn8-yZchfq0u6OZHe3Oe3I2pAEJuWR0zRg1n---dz_XnHK5FlKoRos35Jw3UtZMcH72qn9HLkrZU0q5YmwGzknusA91Nx0wH2NBX20R8hCHx_oLLON9fMKqwxyxVJseSokhOhhjGqpjhOomYobsfs1YX3UHyAWrTRqOqZ8Wzgz-gPIbfX01jQkHlzzmD-RtgL7gxUtdkYdvX-83N_X27vp2c7WtnVBqrB2VaKTWCtjOK4rCGPCyASF23nktHARFZYPQhrBTTClPpQFoAjAFqnViRW5Pe32CvT3k-AT5r00Q7T8g5UcLeYyuR6ubIKihTAvkkretCU6JEKQzujU4P3RFPp12HXL6M2EZ7T5Neb6v2FmoDedcLyx2YrmcSskY_rsyapek7JKUXZKyL0nNmo8nTUTEV_yGydlbPAM4ZJHV |
| CODEN | IOJSAF |
| Cites_doi | 10.1007/s11704-015-4478-2 10.5555/3524938.3525087 10.1007/s10618-014-0361-2 10.1109/ICCV48922.2021.00986 10.1016/j.psychres.2021.114135 10.1145/130385.130401 10.1109/JIOT.2021.3098464 10.1145/3394486.3403118 10.1007/s10618-022-00844-1 10.1109/CVPR42600.2020.00975 10.1007/s10618-020-00710-y 10.1109/TGRS.2024.3409378 10.1145/3447548.3467401 10.1016/j.aiopen.2021.08.002 10.1609/aaai.v37i4.25575 10.1145/3442381.3449903 10.1109/ICSE48619.2023.00207 10.1007/s11431-020-1647-3 10.1109/TITS.2021.3125737 10.1609/aaai.v36i8.20881 10.24963/ijcai.2021/324 10.1007/BF01074755 10.1016/j.scitotenv.2018.10.344 10.1109/CVPR52729.2023.01548 10.1109/TKDE.2020.3001195 10.48550/arXiv.1810.04805 10.1007/s10618-019-00617-3 10.1109/TIT.1967.1053964 10.1016/j.neunet.2021.01.001 10.1007/s10618-020-00701-z 10.1109/ICDAR.1995.598994 10.1109/CVPR52688.2022.01167 10.1109/CVPR52688.2022.01553 10.1109/ICDM.2016.0133 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024 |
| DBID | 97E ESBDL RIA RIE AAYXX CITATION 7SP 8FD L7M DOA |
| DOI | 10.1109/OJSP.2024.3435673 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE Xplore Open Access Journals (WRLC) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef Electronics & Communications Abstracts Technology Research Database Advanced Technologies Database with Aerospace DOAJ Open Access Full Text |
| DatabaseTitle | CrossRef Technology Research Database Advanced Technologies Database with Aerospace Electronics & Communications Abstracts |
| DatabaseTitleList | Technology Research Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Open Access Full Text url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: RIE name: IEEE/IET Electronic Library url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2644-1322 |
| EndPage | 975 |
| ExternalDocumentID | oai_doaj_org_article_76f3090173e242889fc53ff4c9789e67 10_1109_OJSP_2024_3435673 10614789 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National University of Defense Technology grantid: ZZCX-ZZGC-01-04 funderid: 10.13039/501100007085 |
| GroupedDBID | 0R~ 97E AAJGR ABAZT ABVLG ALMA_UNASSIGNED_HOLDINGS BEFXN BFFAM BGNUA BKEBE BPEOZ EBS ESBDL GROUPED_DOAJ JAVBF M~E OCL OK1 RIA RIE AAYXX CITATION 7SP 8FD L7M |
| ID | FETCH-LOGICAL-c355t-c04e94775a1bd50e399ad46a33bdcd73caf5046ea8ffb5155d049aa6fa15a58c3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001300981500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2644-1322 |
| IngestDate | Mon Dec 08 04:16:32 EST 2025 Mon Jun 30 09:49:31 EDT 2025 Sat Nov 29 06:20:00 EST 2025 Wed Aug 27 02:02:21 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| License | https://creativecommons.org/licenses/by-nc-nd/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c355t-c04e94775a1bd50e399ad46a33bdcd73caf5046ea8ffb5155d049aa6fa15a58c3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-1236-8318 0000-0001-5997-5169 0000-0002-7587-8905 0009-0004-4451-2275 0009-0007-0006-7781 |
| OpenAccessLink | https://doaj.org/article/76f3090173e242889fc53ff4c9789e67 |
| PQID | 3097922277 |
| PQPubID | 5075785 |
| PageCount | 12 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_76f3090173e242889fc53ff4c9789e67 ieee_primary_10614789 proquest_journals_3097922277 crossref_primary_10_1109_OJSP_2024_3435673 |
| PublicationCentury | 2000 |
| PublicationDate | 20240000 2024-00-00 20240101 2024-01-01 |
| PublicationDateYYYYMMDD | 2024-01-01 |
| PublicationDate_xml | – year: 2024 text: 20240000 |
| PublicationDecade | 2020 |
| PublicationPlace | New York |
| PublicationPlace_xml | – name: New York |
| PublicationTitle | IEEE open journal of signal processing |
| PublicationTitleAbbrev | OJSP |
| PublicationYear | 2024 |
| Publisher | IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref12 ref15 ref11 ref10 Franceschi (ref13) 2019; 32 Gong (ref21) 2023 ref16 ref19 ref18 Nie (ref40) 2023 Mizrahi (ref9) 2024; 36 Woo (ref42) 2021 Tian (ref47) 2023 ref45 ref48 ref43 Cheng (ref20) 2023 ref49 ref8 ref7 Anguita (ref51) 2013; 3 ref4 ref3 ref5 Quinlan (ref6) 2014 ref35 ref34 ref37 ref36 ref31 ref30 ref33 ref32 Dong (ref46) 2023 Malhotra (ref39) 2017 ref2 ref38 d. Maaten (ref52) 2008; 9 Bagnall (ref50) 2018 ref24 ref23 ref26 Fan (ref41) 2020 ref25 ref22 Hyvarinen (ref44) 2017 ref28 Tonekaboni (ref14) 2021 ref27 ref29 Wu (ref1) 2013 Zhang (ref17) 2022; 35 |
| References_xml | – ident: ref30 doi: 10.1007/s11704-015-4478-2 – start-page: 558 volume-title: Proc. Int. Conf. Mach. Learn. year: 2013 ident: ref1 article-title: Dynamic covariance models for multivariate financial time series – ident: ref37 doi: 10.5555/3524938.3525087 – volume: 9 start-page: 2579 issue: 11 year: 2008 ident: ref52 article-title: Visualizing data using t-SNE publication-title: J. Mach. Learn. Res. – ident: ref23 doi: 10.1007/s10618-014-0361-2 – ident: ref38 doi: 10.1109/ICCV48922.2021.00986 – year: 2017 ident: ref39 article-title: TimeNet: Pre-trained deep recurrent neural network for time series classification publication-title: Esann – ident: ref35 doi: 10.1016/j.psychres.2021.114135 – ident: ref7 doi: 10.1145/130385.130401 – ident: ref33 doi: 10.1109/JIOT.2021.3098464 – ident: ref34 doi: 10.1145/3394486.3403118 – ident: ref31 doi: 10.1007/s10618-022-00844-1 – ident: ref36 doi: 10.1109/CVPR42600.2020.00975 – ident: ref29 doi: 10.1007/s10618-020-00710-y – ident: ref22 doi: 10.1109/TGRS.2024.3409378 – volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref42 article-title: Cost: Contrastive learning of disentangled seasonal-trend representations for time series forecasting – start-page: 29996 volume-title: Proc. Int. Conf. Adv. Neural Inf. Process. Syst. year: 2023 ident: ref46 article-title: SimMTM: A simple pre-training framework for masked time-series modeling – ident: ref19 doi: 10.1145/3447548.3467401 – volume-title: Proc. Int. Conf. Learn. Representations year: 2021 ident: ref14 article-title: Unsupervised representation learning for time series with temporal neighborhood coding – volume: 35 start-page: 3988 volume-title: Proc. Int. Conf. Adv. Neural Inf. Process. Syst. year: 2022 ident: ref17 article-title: Self-supervised contrastive pre-training for time series via time-frequency consistency – volume: 32 start-page: 4652 volume-title: Proc. Int. Conf. Adv. Neural Inf. Process. Syst. year: 2019 ident: ref13 article-title: Unsupervised scalable representation learning for multivariate time series – year: 2023 ident: ref21 article-title: PatchMixer: A patch-mixing architecture for long-term time series forecasting publication-title: arXiv:2310.00655 – ident: ref8 doi: 10.1016/j.aiopen.2021.08.002 – volume: 3 year: 2013 ident: ref51 article-title: A public domain dataset for human activity recognition using smartphones publication-title: Esann – year: 2020 ident: ref41 article-title: Self-supervised time series representation learning by inter-intra relational reasoning publication-title: arXiv:2011.13548 – volume-title: C4. 5: Programs for Machine Learning year: 2014 ident: ref6 – ident: ref45 doi: 10.1609/aaai.v37i4.25575 – volume-title: Proc. 11th Int. Conf. Learn. Representations year: 2023 ident: ref47 article-title: Designing BERT for convolutional networks: Sparse and hierarchical masked modeling – ident: ref43 doi: 10.1145/3442381.3449903 – ident: ref11 doi: 10.1109/ICSE48619.2023.00207 – ident: ref12 doi: 10.1007/s11431-020-1647-3 – ident: ref4 doi: 10.1109/TITS.2021.3125737 – volume: 36 volume-title: Proc. Int. Conf. Adv. Neural Inf. Process. Syst. year: 2024 ident: ref9 article-title: 4 M: Massively multimodal masked modeling – ident: ref16 doi: 10.1609/aaai.v36i8.20881 – ident: ref15 doi: 10.24963/ijcai.2021/324 – ident: ref24 doi: 10.1007/BF01074755 – ident: ref2 doi: 10.1016/j.scitotenv.2018.10.344 – ident: ref48 doi: 10.1109/CVPR52729.2023.01548 – volume-title: Proc. Int. Conf. Learn. Representations year: 2023 ident: ref40 article-title: A time series is worth 64 words: Long-term forecasting with transformers – ident: ref3 doi: 10.1109/TKDE.2020.3001195 – ident: ref18 doi: 10.48550/arXiv.1810.04805 – ident: ref27 doi: 10.1007/s10618-019-00617-3 – ident: ref5 doi: 10.1109/TIT.1967.1053964 – ident: ref32 doi: 10.1016/j.neunet.2021.01.001 – year: 2018 ident: ref50 article-title: The UEA multivariate time series classification archive, 2018 publication-title: Statistics – ident: ref26 doi: 10.1007/s10618-020-00701-z – start-page: 460 volume-title: Proc. 20th Int. Conf. Artif. Intell. Statist. year: 2017 ident: ref44 article-title: Nonlinear ICA of temporally dependent stationary sources – year: 2023 ident: ref20 article-title: TimeMAE: Self-supervised representations of time series with decoupled masked autoencoders publication-title: arXiv:2303.00320 – ident: ref28 doi: 10.1109/ICDAR.1995.598994 – ident: ref49 doi: 10.1109/CVPR52688.2022.01167 – ident: ref10 doi: 10.1109/CVPR52688.2022.01553 – ident: ref25 doi: 10.1109/ICDM.2016.0133 |
| SSID | ssj0002511132 |
| Score | 2.2423368 |
| Snippet | In recent years, the use of time series analysis has become widespread, prompting researchers to explore methods to improve classification. Time series... |
| SourceID | doaj proquest crossref ieee |
| SourceType | Open Website Aggregation Database Index Database Publisher |
| StartPage | 964 |
| SubjectTerms | Classification Computer architecture Convolution Convolutional neural networks Decoders Decoding Effectiveness Machine learning Self-supervised learning Task analysis Time series Time series analysis Time series classification time series pre-training Transformers |
| SummonAdditionalLinks | – databaseName: IEEE/IET Electronic Library dbid: RIE link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LbxMxELZoxQEOPIsaKMgHTkhud9fr17GtqCokSqWA1Jvl2GMUUSVRNsnvZ8brVkWIA7ddax-WPz--b-yZYexjcMgKUteLNqiEAkVHYVUyAlzCBQP5RteNySbM1ZW9uXHX1Vm9-MIAQDl8Bsd0Wfby0zJuyVR2UuSLsW6P7RmjR2ete4MKcWWUVnXnsm3cybcv02tUgF1_LJEUaCP_WHtKiP6aU-WvibisLhfP_7NeL9izSiP56Yj7S_YIFq_Y0wfBBV-z9RRus5huVzQbDJB4DaX6U5wFuiXnD07GMRh4SY1Jh4YKTnw3D_xyTq7JJVPKLZ-uUP8CP18udrWrYuHXMPyCJE63myVFw0ywPmA_Lj5_P78UNcOCiMgzNiI2PThERIV2llQDyFZC6nWQcpZiMjKGrFBAQ7A5zygZTEJBEYLOoVVB2SjfsP3FcgGHjCOz6W0MsbVR9cnqWdDRNRaHe-O6KNsJ-3TX9n41BtLwRYA0zhNQnoDyFagJOyN07h-kGNilAJvd1yHljc6yQTpjJCDPsNblqGTOfURh7ECbCTsgqB78bURpwo7uwPZ1wA4ev2Qc-QWbt_947R17QlUczS9HbH-z3sJ79jjuNvNh_aH0xd-RRt3d priority: 102 providerName: IEEE |
| Title | Self-Supervised Learning-Based Time Series Classification via Hierarchical Sparse Convolutional Masked-Autoencoder |
| URI | https://ieeexplore.ieee.org/document/10614789 https://www.proquest.com/docview/3097922277 https://doaj.org/article/76f3090173e242889fc53ff4c9789e67 |
| Volume | 5 |
| WOSCitedRecordID | wos001300981500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Open Access Full Text customDbUrl: eissn: 2644-1322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511132 issn: 2644-1322 databaseCode: DOA dateStart: 20200101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2644-1322 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002511132 issn: 2644-1322 databaseCode: M~E dateStart: 20200101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3PT9swFLYQ4sAOiAHTCqzygdMkjySOY_vYIhCaBKtUJnGzXP-YKlBbNW2P_O17zzFTEQcuu0SKE8XJe35-3-f4vUfIhdWACnxVs9IKDwSlcUwJL1nQHhwG4I2q6opNyPt79fioR1ulvnBPWJceuBPcpWwiL8BpSR7AmyiloxM8xtoB_dGhSXHkhdRbZArnYATOwLPyb8yy0Je_fo5HQAer-gcHhNBI_sYRpXz9ucDKu1k5uZqbQ3KQMSIddO_2meyE2RH5tJU58Jgsx-E5svF6gabeBk9zntQ_bGjxFCM7KK58hZamupe4IygpgW6mlt5OMe44lUF5puMFkNtAr-azTR6H0Hhn26fg2WC9mmOqSx-WJ-T3zfXD1S3L5ROYAxCxYq6ogwZxC1tOvCgCQBHr68ZyPvHOS-5sFMCOg1UxTrDSiwe2YG0TbSmsUI5_Ibuz-Sx8JRRgS62cdaVyovaqmdjG6UKBLRe6crzske-vsjSLLkuGSeyi0AYFb1DwJgu-R4Yo7X83YoLr1ABqN1nt5iO198gJ6mqrN8AZcKlHzl-VZ7I1tgaeJDUG_crT_9H3GdnH7-kWYs7J7mq5Dt_Intuspu2ynwYiHO9ervspnPAvXLThPg |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LbxMxELZKiwQceLYiUMAHTkhud9f22j62FVWANlRKkXqzHHtcRa2SKJvk9zP2ulUR4sBt19qH5c-P7xt7Zgj57AyygtAIVjsZUKC0nmkZFAMTcMFAvtE0fbIJNRrpqytzUZzVsy8MAOTDZ3CQLvNefpj7dTKVHWb5orR5RHakEE3Vu2vdm1QSW0ZxVfYu68oc_vw-vkAN2IgDjrSgVfyP1ScH6S9ZVf6aivP6cvriP2v2kjwvRJIe9ci_Ilswe02ePQgv-IYsx3Ab2Xi9SPNBB4GWYKrX7Nil2-T-QZN5DDqak2OmY0MZKbqZOjqcJufknCvllo4XqICBnsxnm9JZsfDcdTcQ2NF6NU_xMAMsd8mv06-XJ0NWciwwj0xjxXwlwCAm0tWTICtAvuKCaB3nk-CD4t5FiRIanI5xktLBBJQUzrXR1dJJ7fke2Z7NZ_CWUOQ2Qnvna-2lCLqduNabSuOAr0zjeT0gX-7a3i76UBo2S5DK2ASUTUDZAtSAHCd07h9MUbBzATa7LYPKqjbyCgmN4oBMQ2sTveQxCo_S2ECrBmQ3QfXgbz1KA7J_B7YtQ7az-CVlkmeweveP1z6RJ8PL8zN79m304z15mqrbG2P2yfZquYYP5LHfrKbd8mPul78BPoLhJA |
| 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=Self-Supervised+Learning-Based+Time+Series+Classification+via+Hierarchical+Sparse+Convolutional+Masked-Autoencoder&rft.jtitle=IEEE+open+journal+of+signal+processing&rft.au=Yu%2C+Ting&rft.au=Xu%2C+Kele&rft.au=Wang%2C+Xu&rft.au=Ding%2C+Bo&rft.date=2024&rft.issn=2644-1322&rft.eissn=2644-1322&rft.volume=5&rft.spage=964&rft.epage=975&rft_id=info:doi/10.1109%2FOJSP.2024.3435673&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_OJSP_2024_3435673 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2644-1322&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2644-1322&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2644-1322&client=summon |