T‐VAE: Transformer‐Based Variational AutoEncoder for Perceiving Anomalies in Multivariate Time Series Data
ABSTRACT Anomaly perception in multivariate time series data has crucial applications in various domains such as industrial control and intrusion detection. In real‐world scenarios, the sequence information in multivariate time series data, which encompasses the temporal order and dependencies among...
Saved in:
| Published in: | Expert systems Vol. 42; no. 7 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Oxford
Blackwell Publishing Ltd
01.07.2025
|
| Subjects: | |
| ISSN: | 0266-4720, 1468-0394 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | ABSTRACT
Anomaly perception in multivariate time series data has crucial applications in various domains such as industrial control and intrusion detection. In real‐world scenarios, the sequence information in multivariate time series data, which encompasses the temporal order and dependencies among high‐dimensional samples and features, can be complex and nonlinear. Additionally, the time series data often exhibit high volatility and are interspersed with noise data. These factors make anomaly perception in multivariate time series challenging. Despite the recent development of deep learning methods, only a few are able to address all of these challenges. In this paper, we propose a Transformer‐based Variational AutoEncoder (T‐VAE) for anomaly perception in multivariate time series data. The T‐VAE consists of two sub‐networks, the Representation Network and the Memory Network, and achieves end‐to‐end jointly optimisation. The Representation Network leverages self‐attention mechanisms and residual network structures to capture sequence information and metaphorical patterns from multivariate time series data. The Memory Network employs a Variational AutoEncoder to learn the distribution of normal data. It employs Maximum Mean Discrepancy to approximate the distribution of high‐volatility and noisy data to the distribution of the normal data. We evaluate T‐VAE on five datasets, showing superior performance and validating its effectiveness and robustness through comprehensive ablation studies and sensitivity analyses. |
|---|---|
| AbstractList | Anomaly perception in multivariate time series data has crucial applications in various domains such as industrial control and intrusion detection. In real‐world scenarios, the sequence information in multivariate time series data, which encompasses the temporal order and dependencies among high‐dimensional samples and features, can be complex and nonlinear. Additionally, the time series data often exhibit high volatility and are interspersed with noise data. These factors make anomaly perception in multivariate time series challenging. Despite the recent development of deep learning methods, only a few are able to address all of these challenges. In this paper, we propose a Transformer‐based Variational AutoEncoder (T‐VAE) for anomaly perception in multivariate time series data. The T‐VAE consists of two sub‐networks, the Representation Network and the Memory Network, and achieves end‐to‐end jointly optimisation. The Representation Network leverages self‐attention mechanisms and residual network structures to capture sequence information and metaphorical patterns from multivariate time series data. The Memory Network employs a Variational AutoEncoder to learn the distribution of normal data. It employs Maximum Mean Discrepancy to approximate the distribution of high‐volatility and noisy data to the distribution of the normal data. We evaluate T‐VAE on five datasets, showing superior performance and validating its effectiveness and robustness through comprehensive ablation studies and sensitivity analyses. ABSTRACT Anomaly perception in multivariate time series data has crucial applications in various domains such as industrial control and intrusion detection. In real‐world scenarios, the sequence information in multivariate time series data, which encompasses the temporal order and dependencies among high‐dimensional samples and features, can be complex and nonlinear. Additionally, the time series data often exhibit high volatility and are interspersed with noise data. These factors make anomaly perception in multivariate time series challenging. Despite the recent development of deep learning methods, only a few are able to address all of these challenges. In this paper, we propose a Transformer‐based Variational AutoEncoder (T‐VAE) for anomaly perception in multivariate time series data. The T‐VAE consists of two sub‐networks, the Representation Network and the Memory Network, and achieves end‐to‐end jointly optimisation. The Representation Network leverages self‐attention mechanisms and residual network structures to capture sequence information and metaphorical patterns from multivariate time series data. The Memory Network employs a Variational AutoEncoder to learn the distribution of normal data. It employs Maximum Mean Discrepancy to approximate the distribution of high‐volatility and noisy data to the distribution of the normal data. We evaluate T‐VAE on five datasets, showing superior performance and validating its effectiveness and robustness through comprehensive ablation studies and sensitivity analyses. |
| Author | Jing, Jiwu Long, Chun Li, Chang Kiat, Yeo Chai |
| Author_xml | – sequence: 1 givenname: Chang orcidid: 0009-0009-7695-7814 surname: Li fullname: Li, Chang organization: University of Chinese Academy of Sciences – sequence: 2 givenname: Yeo Chai surname: Kiat fullname: Kiat, Yeo Chai organization: Nanyang Technological University – sequence: 3 givenname: Jiwu surname: Jing fullname: Jing, Jiwu organization: University of Chinese Academy of Sciences – sequence: 4 givenname: Chun surname: Long fullname: Long, Chun email: anquanip@cnic.cn organization: Chinese Academy of Sciences |
| BookMark | eNp9kE1OwzAQRi1UJNrChhNYYoeUYjup7bALJfxIRSC1VLCK3GSKXCV2sZNCdxyBM3IS0pY1sxlp5n0jzeuhjrEGEDqlZEDbuoBPvxkIQoQ8QF0acRmQMI46qEsY50EkGDlCPe-XhBAqBO8iM_35-p4l6SWeOmX8wroKXDu6Uh4KPFNOq1pbo0qcNLVNTW4LcLjF8BO4HPRamzecGFupUoPH2uCHpqz1ehcEPNUV4Am47e5a1eoYHS5U6eHkr_fR8006Hd0F48fb-1EyDnLGmQwiWrAhGyo653NCOAcgOZMyYkIuinkUg1CQw1CGICOpaEzjQhSUMxUKKuMiCvvobH935ex7A77OlrZx7Rs-CxmTsQhjNmyp8z2VO-u9g0W2crpSbpNRkm19Zluf2c5nC9M9_KFL2PxDZunL5HWf-QVqP3vw |
| Cites_doi | 10.14778/3425879.3425885 10.14778/3467861.3467863 10.1016/j.knosys.2020.106622 10.3390/app11073194 10.14778/3514061.3514067 10.1016/j.cose.2023.103094 10.1109/ICDE60146.2024.00050 10.1016/j.ijforecast.2019.07.001 10.14778/3430915.3430918 10.1109/TC.2023.3257518 10.1109/TKDE.2023.3270293 10.5220/0006639801080116 10.1111/iere.12494 10.1145/3292500.3330680 10.18653/v1/2024.findings-acl.590 10.1016/j.ins.2023.119400 10.1016/j.compchemeng.2023.108560 10.3390/jcp2040039 10.1109/ICDM58522.2023.00150 10.14778/3415478.3415514 10.24963/ijcai.2024/818 10.1109/CySWater.2016.7469060 10.1145/3580305.3599295 10.1016/j.cie.2020.106435 10.1609/aaai.v35i5.16523 10.1016/j.inffus.2023.102165 10.1016/j.knosys.2020.105659 10.1016/j.cose.2021.102554 10.1016/j.inffus.2023.101921 10.1007/s00521-024-09962-x 10.1145/3292500.3330672 10.1145/3055366.3055375 10.3390/app13053183 10.18653/v1/P19-1378 10.1145/3219819.3219845 10.1109/JSTSP.2012.2237381 10.1109/ACCESS.2023.3349132 10.1109/JIOT.2019.2958185 10.1609/aaai.v33i01.33011409 10.1109/ICDM50108.2020.00093 10.1109/CCST.2019.8888419 10.1007/s10664-024-10533-w |
| ContentType | Journal Article |
| Copyright | 2025 John Wiley & Sons Ltd. 2025 John Wiley & Sons, Ltd. |
| Copyright_xml | – notice: 2025 John Wiley & Sons Ltd. – notice: 2025 John Wiley & Sons, Ltd. |
| DBID | AAYXX CITATION 7SC 7TB 8FD F28 FR3 JQ2 L7M L~C L~D |
| DOI | 10.1111/exsy.70078 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | CrossRef Technology Research Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1468-0394 |
| EndPage | n/a |
| ExternalDocumentID | 10_1111_exsy_70078 EXSY70078 |
| Genre | researchArticle |
| GrantInformation_xml | – fundername: National Key Research and Development Program of China funderid: 2023YFC3304704 – fundername: Youth Innovation Promotion Association of the Chinese Academy of Sciences funderid: 2023181 |
| GroupedDBID | -~X .3N .4S .DC .GA .Y3 05W 0R~ 10A 1OB 1OC 29G 31~ 33P 3SF 4.4 50Y 50Z 51W 51X 52M 52N 52O 52P 52S 52T 52U 52W 52X 5GY 5HH 5LA 5VS 66C 6TJ 702 77K 7PT 8-0 8-1 8-3 8-4 8-5 8UM 8VB 930 9M8 A03 AAESR AAEVG AAHHS AAHQN AAMNL AANHP AANLZ AAONW AASGY AAXRX AAYCA AAZKR ABCQN ABCUV ABDBF ABDPE ABEML ABLJU ABPVW ACAHQ ACBWZ ACCFJ ACCZN ACFBH ACGFS ACIWK ACNCT ACPOU ACRPL ACSCC ACUHS ACXBN ACXQS ACYXJ ADBBV ADEOM ADIZJ ADKYN ADMGS ADMHC ADMLS ADNMO ADOZA ADXAS ADZMN ADZOD AEEZP AEIGN AEIMD AEMOZ AENEX AEQDE AEUYR AEYWJ AFBPY AFEBI AFFPM AFGKR AFWVQ AFZJQ AGHNM AGQPQ AGYGG AHBTC AHEFC AHQJS AI. AITYG AIURR AIWBW AJBDE AJXKR AKVCP ALAGY ALMA_UNASSIGNED_HOLDINGS ALUQN ALVPJ AMBMR AMYDB ARCSS ASPBG ATUGU AUFTA AVWKF AZBYB AZFZN AZVAB BAFTC BDRZF BFHJK BHBCM BMNLL BMXJE BNHUX BROTX BRXPI BY8 CAG COF CS3 CWDTD D-E D-F DC6 DCZOG DPXWK DR2 DRFUL DRSTM DU5 EAD EAP EBA EBR EBS EBU EDO EJD EMK EST ESX F00 F01 F04 FEDTE FZ0 G-S G.N GODZA H.T H.X HF~ HGLYW HVGLF HZI HZ~ I-F IHE IX1 J0M K1G K48 LATKE LC2 LC3 LEEKS LH4 LITHE LOXES LP6 LP7 LUTES LW6 LYRES MEWTI MK4 MK~ MRFUL MRSTM MSFUL MSSTM MVM MXFUL MXSTM N04 N05 N9A NF~ O66 O9- OIG P2W P2X P4D PALCI PQQKQ Q.N Q11 QB0 QWB R.K RIWAO RJQFR ROL RX1 SAMSI SUPJJ TAE TH9 TN5 TUS UB1 VH1 W8V W99 WBKPD WH7 WIH WIK WLBEL WOHZO WQJ WXSBR WYISQ XG1 ZL0 ZZTAW ~02 ~IA ~WT 77I AAMMB AAYXX AEFGJ AGXDD AIDQK AIDYY AIQQE CITATION O8X 7SC 7TB 8FD F28 FR3 JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c2628-41d2525a1b6b0066ee0c2884278fdb49e7aece583e848a1919d7d162a37189d43 |
| IEDL.DBID | DRFUL |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001509983800003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0266-4720 |
| IngestDate | Sun Nov 09 07:34:05 EST 2025 Sat Nov 29 07:41:52 EST 2025 Tue Jun 17 09:32:47 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c2628-41d2525a1b6b0066ee0c2884278fdb49e7aece583e848a1919d7d162a37189d43 |
| Notes | Funding This work is supported by the National Key Research and Development Program of China (Grant No: 2023YFC3304704), and the Youth Innovation Promotion Association of the Chinese Academy of Sciences (Grant No: 2023181). ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0009-0009-7695-7814 |
| PQID | 3228973925 |
| PQPubID | 32130 |
| PageCount | 12 |
| ParticipantIDs | proquest_journals_3228973925 crossref_primary_10_1111_exsy_70078 wiley_primary_10_1111_exsy_70078_EXSY70078 |
| PublicationCentury | 2000 |
| PublicationDate | July 2025 2025-07-00 20250701 |
| PublicationDateYYYYMMDD | 2025-07-01 |
| PublicationDate_xml | – month: 07 year: 2025 text: July 2025 |
| PublicationDecade | 2020 |
| PublicationPlace | Oxford |
| PublicationPlace_xml | – name: Oxford |
| PublicationTitle | Expert systems |
| PublicationYear | 2025 |
| Publisher | Blackwell Publishing Ltd |
| Publisher_xml | – name: Blackwell Publishing Ltd |
| References | 2019; 7 2023; 13 2023; 35 2019; 3 2023; 36 2024; 104 2019; 33 2020; 143 2023; 100 2023; 127 2020; 36 2020; 14 2020; 13 2011; 12 2024; 12 2024 2023; 646 2024; 36 2013; 7 2024; 182 2022; 113 2021; 14 2021; 35 2021; 11 2021; 212 2020; 195 2023 2022 2018; 1 2021 2020 2022; 35 2019 2018 2017 2016 2014 2022; 2 2021; 62 2023; 72 e_1_2_8_28_1 e_1_2_8_24_1 e_1_2_8_47_1 e_1_2_8_26_1 e_1_2_8_49_1 Zong B. (e_1_2_8_54_1) 2018 Pedregosa F. (e_1_2_8_33_1) 2011 e_1_2_8_3_1 e_1_2_8_5_1 e_1_2_8_7_1 e_1_2_8_9_1 e_1_2_8_20_1 e_1_2_8_43_1 e_1_2_8_45_1 e_1_2_8_41_1 e_1_2_8_17_1 e_1_2_8_19_1 e_1_2_8_13_1 e_1_2_8_36_1 e_1_2_8_15_1 e_1_2_8_38_1 Mao R. (e_1_2_8_29_1) 2024 e_1_2_8_32_1 e_1_2_8_11_1 e_1_2_8_34_1 e_1_2_8_53_1 e_1_2_8_51_1 e_1_2_8_30_1 e_1_2_8_25_1 e_1_2_8_46_1 e_1_2_8_27_1 e_1_2_8_48_1 e_1_2_8_2_1 e_1_2_8_4_1 e_1_2_8_6_1 e_1_2_8_8_1 e_1_2_8_42_1 e_1_2_8_23_1 e_1_2_8_44_1 Li S. (e_1_2_8_22_1) 2019; 3 e_1_2_8_40_1 e_1_2_8_18_1 e_1_2_8_14_1 e_1_2_8_35_1 e_1_2_8_16_1 e_1_2_8_37_1 Li L. (e_1_2_8_21_1) 2022; 35 Song J. (e_1_2_8_39_1) 2023; 36 e_1_2_8_10_1 e_1_2_8_31_1 e_1_2_8_12_1 e_1_2_8_52_1 e_1_2_8_50_1 |
| References_xml | – volume: 143 year: 2020 article-title: An Optimized Model Using LSTM Network for Demand Forecasting publication-title: Computers & Industrial Engineering – start-page: 1 year: 2019 end-page: 8 – volume: 36 start-page: 57947 year: 2023 end-page: 57963 article-title: Memto: Memory‐Guided Transformer for Multivariate Time Series Anomaly Detection publication-title: In Advances in Neural Information Processing Systems – volume: 35 start-page: 6058 issue: 6 year: 2022 end-page: 6072 article-title: Learning Robust Deep State Space for Unsupervised Anomaly Detection in Contaminated Time‐Series publication-title: IEEE Transactions on Knowledge and Data Engineering – start-page: 31 year: 2016 end-page: 36 – volume: 11 start-page: 3194 issue: 7 year: 2021 article-title: Online Forecasting and Anomaly Detection Based on the Arima Model publication-title: Applied Sciences – volume: 14 start-page: 141 issue: 2 year: 2020 end-page: 153 article-title: Real‐Time Distance‐Based Outlier Detection in Data Streams publication-title: Proceedings of the VLDB Endowment – volume: 13 start-page: 2941 issue: 12 year: 2020 end-page: 2944 article-title: Graphan: Graph‐Based Subsequence Anomaly Detection publication-title: Proceedings of the VLDB Endowment – volume: 127 year: 2023 article-title: Gru‐Based Interpretable Multivariate Time Series Anomaly Detection in Industrial Control System publication-title: Computers & Security – volume: 12 start-page: 3768 year: 2024 end-page: 3789 article-title: A Comprehensive Survey of Deep Transfer Learning for Anomaly Detection in Industrial Time Series: Methods, Applications, and Directions publication-title: IEEE Access – year: 2021 – year: 2024 – volume: 1 start-page: 108 year: 2018 end-page: 116 – volume: 2 start-page: 764 issue: 4 year: 2022 end-page: 777 article-title: Detection of SQL Injection Attack Using Machine Learning Techniques: A Systematic Literature Review publication-title: Journal of Cybersecurity and Privacy – volume: 7 start-page: 38 issue: 1 year: 2013 end-page: 49 article-title: Space‐Time Signal Processing for Distributed Pattern Detection in Sensor Networks publication-title: IEEE Journal of Selected Topics in Signal Processing – volume: 12 year: 2011 – volume: 100 year: 2023 article-title: KnowleNet: Knowledge Fusion Network for Multimodal Sarcasm Detection publication-title: Information Fusion – year: 2018 – year: 2014 – volume: 33 start-page: 1409 year: 2019 end-page: 1416 – volume: 7 start-page: 6481 issue: 7 year: 2019 end-page: 6494 article-title: Anomaly Detection for Iot Time‐Series Data: A Survey publication-title: IEEE Internet of Things Journal – start-page: 3888 year: 2019 end-page: 3898 – start-page: 841 year: 2020 end-page: 850 – volume: 113 year: 2022 article-title: Black‐Box Adversarial Attacks on Xss Attack Detection Model publication-title: Computers & Security – start-page: 387 year: 2018 end-page: 395 – volume: 104 year: 2024 article-title: Quantitative Stock Portfolio Optimization by Multi‐Task Learning Risk and Return publication-title: Information Fusion – volume: 35 start-page: 12591 issue: 12 year: 2023 end-page: 12604 article-title: Deep Isolation Forest for Anomaly Detection publication-title: IEEE Transactions on Knowledge and Data Engineering – volume: 13 start-page: 3183 issue: 5 year: 2023 article-title: Machine Learning Techniques to Detect a DDOS Attack in SDN: A Systematic Review publication-title: Applied Sciences – volume: 35 start-page: 4027 year: 2021 end-page: 4035 – volume: 195 year: 2020 article-title: K‐Means‐Based Isolation Forest publication-title: Knowledge‐Based Systems – volume: 646 year: 2023 article-title: Fuzzy Granular Anomaly Detection Using Markov Random Walk publication-title: Information Sciences – volume: 62 start-page: 469 issue: 2 year: 2021 end-page: 520 article-title: Business Cycles, Trend Elimination, and the Hp Filter publication-title: International Economic Review – start-page: 3009 year: 2019 end-page: 3017 – volume: 182 year: 2024 article-title: Time Series Forecasting and Anomaly Detection Using Deep Learning publication-title: Computers & Chemical Engineering – start-page: 2828 year: 2019 end-page: 2837 – year: 2022 – year: 2020 – volume: 14 start-page: 1717 issue: 10 year: 2021 end-page: 1729 article-title: Sand: Streaming Subsequence Anomaly Detection publication-title: Proceedings of the VLDB Endowment – year: 2023 – volume: 72 start-page: 2656 issue: 9 year: 2023 end-page: 2667 article-title: Improving Log‐Based Anomaly Detection by Pre‐Training Hierarchical Transformers publication-title: IEEE Transactions on Computers – volume: 3 start-page: 32 year: 2019 article-title: Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting publication-title: Advances in Neural Information Processing Systems – start-page: 1211 year: 2023 end-page: 1216 – volume: 36 start-page: 1181 issue: 3 year: 2020 end-page: 1191 article-title: Deepar: Probabilistic Forecasting With Autoregressive Recurrent Networks publication-title: International Journal of Forecasting – start-page: 25 year: 2017 end-page: 28 – volume: 212 year: 2021 article-title: Automl: A Survey of the State‐of‐the‐Art publication-title: Knowledge‐Based Systems – year: 2019 – volume: 36 start-page: 16213 issue: 26 year: 2024 end-page: 16231 article-title: Corrector LSTM: Built‐In Training Data Correction for Improved Time‐Series Forecasting publication-title: Neural Computing and Applications – ident: e_1_2_8_45_1 – ident: e_1_2_8_42_1 doi: 10.14778/3425879.3425885 – ident: e_1_2_8_8_1 doi: 10.14778/3467861.3467863 – ident: e_1_2_8_12_1 doi: 10.1016/j.knosys.2020.106622 – ident: e_1_2_8_20_1 doi: 10.3390/app11073194 – ident: e_1_2_8_43_1 doi: 10.14778/3514061.3514067 – ident: e_1_2_8_41_1 doi: 10.1016/j.cose.2023.103094 – volume: 36 start-page: 57947 year: 2023 ident: e_1_2_8_39_1 article-title: Memto: Memory‐Guided Transformer for Multivariate Time Series Anomaly Detection publication-title: In Advances in Neural Information Processing Systems – ident: e_1_2_8_11_1 doi: 10.1109/ICDE60146.2024.00050 – volume-title: Proceedings of the Annual Meeting of the Cognitive Science Society (Cogsci) year: 2024 ident: e_1_2_8_29_1 – ident: e_1_2_8_36_1 doi: 10.1016/j.ijforecast.2019.07.001 – ident: e_1_2_8_19_1 doi: 10.14778/3430915.3430918 – ident: e_1_2_8_32_1 – ident: e_1_2_8_13_1 doi: 10.1109/TC.2023.3257518 – ident: e_1_2_8_47_1 doi: 10.1109/TKDE.2023.3270293 – ident: e_1_2_8_37_1 doi: 10.5220/0006639801080116 – volume-title: Scikit‐Learn: Machine Learning in Python year: 2011 ident: e_1_2_8_33_1 – ident: e_1_2_8_34_1 doi: 10.1111/iere.12494 – ident: e_1_2_8_35_1 doi: 10.1145/3292500.3330680 – ident: e_1_2_8_18_1 – ident: e_1_2_8_26_1 doi: 10.18653/v1/2024.findings-acl.590 – ident: e_1_2_8_23_1 doi: 10.1016/j.ins.2023.119400 – ident: e_1_2_8_15_1 doi: 10.1016/j.compchemeng.2023.108560 – ident: e_1_2_8_4_1 doi: 10.3390/jcp2040039 – ident: e_1_2_8_25_1 doi: 10.1109/ICDM58522.2023.00150 – ident: e_1_2_8_7_1 doi: 10.14778/3415478.3415514 – ident: e_1_2_8_28_1 doi: 10.24963/ijcai.2024/818 – ident: e_1_2_8_30_1 doi: 10.1109/CySWater.2016.7469060 – ident: e_1_2_8_50_1 doi: 10.1145/3580305.3599295 – ident: e_1_2_8_2_1 doi: 10.1016/j.cie.2020.106435 – ident: e_1_2_8_10_1 doi: 10.1609/aaai.v35i5.16523 – volume: 3 start-page: 32 year: 2019 ident: e_1_2_8_22_1 article-title: Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting publication-title: Advances in Neural Information Processing Systems – volume-title: International Conference on Learning Representations year: 2018 ident: e_1_2_8_54_1 – ident: e_1_2_8_24_1 doi: 10.1016/j.inffus.2023.102165 – ident: e_1_2_8_16_1 doi: 10.1016/j.knosys.2020.105659 – ident: e_1_2_8_44_1 doi: 10.1016/j.cose.2021.102554 – ident: e_1_2_8_51_1 doi: 10.1016/j.inffus.2023.101921 – ident: e_1_2_8_6_1 doi: 10.1007/s00521-024-09962-x – ident: e_1_2_8_40_1 doi: 10.1145/3292500.3330672 – ident: e_1_2_8_3_1 doi: 10.1145/3055366.3055375 – ident: e_1_2_8_46_1 – ident: e_1_2_8_5_1 doi: 10.3390/app13053183 – ident: e_1_2_8_27_1 doi: 10.18653/v1/P19-1378 – ident: e_1_2_8_14_1 doi: 10.1145/3219819.3219845 – ident: e_1_2_8_31_1 doi: 10.1109/JSTSP.2012.2237381 – ident: e_1_2_8_48_1 doi: 10.1109/ACCESS.2023.3349132 – ident: e_1_2_8_9_1 doi: 10.1109/JIOT.2019.2958185 – ident: e_1_2_8_52_1 doi: 10.1609/aaai.v33i01.33011409 – ident: e_1_2_8_49_1 – ident: e_1_2_8_53_1 doi: 10.1109/ICDM50108.2020.00093 – ident: e_1_2_8_38_1 doi: 10.1109/CCST.2019.8888419 – ident: e_1_2_8_17_1 doi: 10.1007/s10664-024-10533-w – volume: 35 start-page: 6058 issue: 6 year: 2022 ident: e_1_2_8_21_1 article-title: Learning Robust Deep State Space for Unsupervised Anomaly Detection in Contaminated Time‐Series publication-title: IEEE Transactions on Knowledge and Data Engineering |
| SSID | ssj0001776 |
| Score | 2.3588939 |
| Snippet | ABSTRACT
Anomaly perception in multivariate time series data has crucial applications in various domains such as industrial control and intrusion detection. In... Anomaly perception in multivariate time series data has crucial applications in various domains such as industrial control and intrusion detection. In... |
| SourceID | proquest crossref wiley |
| SourceType | Aggregation Database Index Database Publisher |
| SubjectTerms | Ablation anomaly perception Multivariate analysis Perception Representations Sensitivity analysis Time series time series data transformer variational auto‐encoder Volatility |
| Title | T‐VAE: Transformer‐Based Variational AutoEncoder for Perceiving Anomalies in Multivariate Time Series Data |
| URI | https://onlinelibrary.wiley.com/doi/abs/10.1111%2Fexsy.70078 https://www.proquest.com/docview/3228973925 |
| Volume | 42 |
| WOSCitedRecordID | wos001509983800003&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: PRVWIB databaseName: Wiley Online Library - Journals customDbUrl: eissn: 1468-0394 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001776 issn: 0266-4720 databaseCode: DRFUL dateStart: 19970101 isFulltext: true titleUrlDefault: https://onlinelibrary.wiley.com providerName: Wiley-Blackwell |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NTsJAEJ4gevAi_kYUzSZ6MqmhS2l3jZcqJR4IIQoET822XRIOFtMWojcfwWf0SZxdWsCLifHSNO1us9mZ2flmOj8Al-pPmTBtaQhq2oYVCG4IEeLFRO1PIxoEuoDpsON0u2w04r0S3Ba5MIv6EEuHm5IMfV4rARdBuibk8i19v3aUituATYqMa5Vhs_XYHnSWJ7Hp6OZyaGbgMhxaz8uTqkie1eyfCmmFMtexqlY27cr_lrkLOznIJO6CK_agJON9qBQNHEguzwcQ978-Poeud0P6BX6VCT66Q9UWkSGa0bmrkLizbOrFKv89ITiM9FQ8zEQ5I4gbT18QzMuUTGKi83nneqIkKr2EKPcbvmuJTBzCoO317x-MvAGDEVJbed3MiCIxhRnYSjptKeshZUx15xhHgcWlI2Qom6whmcUEWn48ciIksWigxuOR1TiCcjyN5TEQNJu4Resh4jWOY1mgiiAj_BujIRxya1yFi4IK_uuizoZf2CdqC329hVWoFQTyc1lLfTySGHcQ5zWrcKVJ8csXfG_09KzvTv4y-BS2qWr8q-N0a1DOkpk8g61wnk3S5Dznu2954d18 |
| linkProvider | Wiley-Blackwell |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NTsJAEJ4omuhF_I0o6iZ6MqmhS2m73lAgGJEQBYKnZtsuCQeLoUD05iP4jD6JM0sLeDExXpqm3W02OzM730znB-CC_pRJ01aG5KZtWL4UhpQBXkzU_jzkvq8LmHYbTrPp9nqilcTmUC7MrD7E3OFGkqHPaxJwckgvSbl6i9-vHNJxq7BmIR-VMrBWeax1GvOj2HR0dzm0M3AdDi8k9UkplGcx-6dGWsDMZbCqtU0t-891bsNWAjNZecYXO7Ciol3Ipi0cWCLRexC1vz4-u-XqNWunCFaN8NENKreQddGQTpyFrDwZD6sRZcCPGA5jLYqIGZA7gpWj4QvCeRWzQcR0Ru9UT1SMEkwYOeDwXUWO5T50atX2bd1IWjAYAbfJ72aGHMkpTd8m-bSVKgTcdak_Rz_0LaEcqQJVcovKtVyJtp8InRCJLIuo80RoFQ8gEw0jdQgMDSdh8UKAiE3gWNenMsgIAPtoCgfC6ufgPCWD9zqrtOGlFgptoae3MAf5lEJeIm2xh4eSKxxEeqUcXGpa_PIFr9p7etZ3R38ZfAYb9fZDw2vcNe-PYZNTG2AdtZuHzHg0USewHkzHg3h0mjDhN71Z4Ww |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB60FfFifWK16oKehEizTZOst2pbFEsp2pZ6CptkAz2Ylr7Qmz_B3-gvcWabtPUiiJcQktmw7OzsfDOZB8Al_SmTpq0MyU3bsHwpDCkDvJio_XnIfV8XMO02nGbT7fVEK4nNoVyYeX2IhcONJEOf1yTgahhGK1Ku3sbv1w7puHXIWmVho1xmq0_1TmNxFJuO7i6HdgbOw-HFpD4phfIsR__USEuYuQpWtbap5_45zx3YTmAmq8z3xS6sqXgPcmkLB5ZI9D7E7a-Pz26ldsPaKYJVI3x0i8otZF00pBNnIatMJ4NaTBnwI4ZkrEURMX1yR7BKPHhFOK_GrB8zndE70wMVowQTRg44fFeVE3kAnXqtfXdvJC0YjIDb5HczQ47slKZvk3zaShUD7rrUnyMKfUsoR6pAld2Sci1Xou0nQidEJssS6jwRWqVDyMSDWB0BQ8NJWLwYIGITSOv6VAYZAWCEpnAgrCgPFykbvOG80oaXWii0hJ5ewjwUUg55ibSNPTyUXOEg0ivn4Urz4pcveLXe84u-O_4L8Tlstqp1r_HQfDyBLU5dgHXQbgEyk9FUncJGMJv0x6OzZA9-A3Zu4Oc |
| 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=T%E2%80%90VAE%3A+Transformer%E2%80%90Based+Variational+AutoEncoder+for+Perceiving+Anomalies+in+Multivariate+Time+Series+Data&rft.jtitle=Expert+systems&rft.au=Li%2C+Chang&rft.au=Kiat%2C+Yeo+Chai&rft.au=Jing%2C+Jiwu&rft.au=Long%2C+Chun&rft.date=2025-07-01&rft.issn=0266-4720&rft.eissn=1468-0394&rft.volume=42&rft.issue=7&rft.epage=n%2Fa&rft_id=info:doi/10.1111%2Fexsy.70078&rft.externalDBID=10.1111%252Fexsy.70078&rft.externalDocID=EXSY70078 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0266-4720&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0266-4720&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0266-4720&client=summon |