Improved AutoEncoder With LSTM Module and KL Divergence for Anomaly Detection

The task of anomaly detection is to separate anomalous data from normal data in the dataset. Models such as deep Convolutional AutoEncoder (CAE) and deep support vector data description (SVDD) have been universally used and have demonstrated significant success in detecting anomalies. However, the o...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on instrumentation and measurement Ročník 73; s. 1 - 11
Hlavní autori: Huang, Wei, Zhang, Bingyang, Zhang, Kaituo, Gao, Hua, Wan, Rongchun
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: New York IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:0018-9456, 1557-9662
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The task of anomaly detection is to separate anomalous data from normal data in the dataset. Models such as deep Convolutional AutoEncoder (CAE) and deep support vector data description (SVDD) have been universally used and have demonstrated significant success in detecting anomalies. However, the over-reconstruction ability of CAE network for anomalous data can easily lead to high false-negative rate in detecting anomalous data. On the other hand, the deep support vector data description (Deep SVDD) model has the drawback of feature collapse, which leads to a decrease in detection accuracy for anomalies. To address these problems, we propose the Improved AutoEncoder with LSTM module and Kullback-Leibler divergence (IAE-LSTM-KL) model in this article. An LSTM network is added after the encoder to memorize feature representations of normal data. Meanwhile, the phenomenon of feature collapse can also be mitigated by penalizing the featured input to SVDD module via KL divergence. The efficacy of the IAE-LSTM-KL model is validated through experiments on both synthetic and real-world datasets. Experimental results show that IAE-LSTM-KL model yields higher detection accuracy for anomalies. In addition, it is also found that the IAE-LSTM-KL model demonstrates enhanced robustness to contaminated outliers in the dataset.
AbstractList The task of anomaly detection is to separate anomalous data from normal data in the dataset. Models such as deep Convolutional AutoEncoder (CAE) and deep support vector data description (SVDD) have been universally used and have demonstrated significant success in detecting anomalies. However, the over-reconstruction ability of CAE network for anomalous data can easily lead to high false-negative rate in detecting anomalous data. On the other hand, the deep support vector data description (Deep SVDD) model has the drawback of feature collapse, which leads to a decrease in detection accuracy for anomalies. To address these problems, we propose the Improved AutoEncoder with LSTM module and Kullback-Leibler divergence (IAE-LSTM-KL) model in this article. An LSTM network is added after the encoder to memorize feature representations of normal data. Meanwhile, the phenomenon of feature collapse can also be mitigated by penalizing the featured input to SVDD module via KL divergence. The efficacy of the IAE-LSTM-KL model is validated through experiments on both synthetic and real-world datasets. Experimental results show that IAE-LSTM-KL model yields higher detection accuracy for anomalies. In addition, it is also found that the IAE-LSTM-KL model demonstrates enhanced robustness to contaminated outliers in the dataset.
Author Wan, Rongchun
Zhang, Kaituo
Zhang, Bingyang
Gao, Hua
Huang, Wei
Author_xml – sequence: 1
  givenname: Wei
  orcidid: 0000-0002-6684-5642
  surname: Huang
  fullname: Huang, Wei
  organization: College of Computer Science, Zhejiang University of Technology, Hangzhou, China
– sequence: 2
  givenname: Bingyang
  orcidid: 0009-0004-3268-6278
  surname: Zhang
  fullname: Zhang, Bingyang
  organization: College of Computer Science, Zhejiang University of Technology, Hangzhou, China
– sequence: 3
  givenname: Kaituo
  orcidid: 0009-0004-6976-1884
  surname: Zhang
  fullname: Zhang, Kaituo
  organization: College of Computer Science, Zhejiang University of Technology, Hangzhou, China
– sequence: 4
  givenname: Hua
  orcidid: 0000-0002-4078-3527
  surname: Gao
  fullname: Gao, Hua
  email: ghua@zjut.edu.cn
  organization: College of Computer Science, Zhejiang University of Technology, Hangzhou, China
– sequence: 5
  givenname: Rongchun
  orcidid: 0009-0008-4747-2247
  surname: Wan
  fullname: Wan, Rongchun
  organization: Zhejiang HOUDAR Intelligent Technology Company Ltd., Hangzhou, China
BookMark eNp9kD1PwzAQhi1UJNrCzsBgiTnFH7GTjFVboCIRA0WMkWNfIFVqFyep1H9PonZADEx3w_vcvXomaGSdBYRuKZlRSpKHzTqbMcLCGQ8lSTi9QGMqRBQkUrIRGhNC4yAJhbxCk6bZEkIiGUZjlK13e-8OYPC8a93KamfA44-q_cLp2ybDmTNdDVhZg19SvKwO4D_BasCl83hu3U7VR7yEFnRbOXuNLktVN3BznlP0_rjaLJ6D9PVpvZingWYJawMQsaKJMX0FBRo0MzTRYWFIyWOmKA0piYt-KRRVoAwvRRRxAYpxykpRxHyK7k93--7fHTRtvnWdt_3LnPe4EJKEQ0qeUtq7pvFQ5rpq1dCz9aqqc0ryQV3eq8sHdflZXQ-SP-DeVzvlj_8hdyekAoBfcRkTERH-A9SGepA
CODEN IEIMAO
CitedBy_id crossref_primary_10_1016_j_measurement_2025_118236
crossref_primary_10_3390_s25010067
crossref_primary_10_1016_j_eswa_2025_129663
Cites_doi 10.48550/arXiv.1312.6114
10.5555/3045118.3045167
10.1109/CVPRW56347.2022.00080
10.1109/access.2018.2816564
10.1023/B:MACH.0000008084.60811.49
10.1109/CVPR.2019.00057
10.1145/3292500.3330701
10.1109/cvpr.2018.00684
10.1109/CVPR.2017.76
10.1109/TETCI.2017.2772792
10.1007/978-3-642-21735-7_7
10.1109/CVPR.2019.00982
10.1109/ICCV48922.2021.01333
10.1109/TIM.2021.3098381
10.1109/CVPR52729.2023.00381
10.1109/ICCV.2019.00179
10.1162/neco.1997.9.8.1735
10.1002/int.22582
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
RIA
RIE
AAYXX
CITATION
7SP
7U5
8FD
L7M
DOI 10.1109/TIM.2024.3460931
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Electronic Library (IEL)
CrossRef
Electronics & Communications Abstracts
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
DatabaseTitle CrossRef
Solid State and Superconductivity Abstracts
Technology Research Database
Advanced Technologies Database with Aerospace
Electronics & Communications Abstracts
DatabaseTitleList
Solid State and Superconductivity Abstracts
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore (IEEE/IET Electronic Library - IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Physics
EISSN 1557-9662
EndPage 11
ExternalDocumentID 10_1109_TIM_2024_3460931
10680570
Genre orig-research
GrantInformation_xml – fundername: National Key Research and Development Program of China
  grantid: 2022YFE0198900
– fundername: National Natural Science Foundation of China
  grantid: 61771430
  funderid: 10.13039/501100001809
GroupedDBID -~X
0R~
29I
4.4
5GY
5VS
6IK
85S
8WZ
97E
A6W
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACGFO
ACIWK
ACNCT
AENEX
AETIX
AGQYO
AGSQL
AHBIQ
AI.
AIBXA
AKJIK
AKQYR
ALLEH
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CS3
DU5
EBS
EJD
F5P
HZ~
H~9
IAAWW
IBMZZ
ICLAB
IDIHD
IFIPE
IFJZH
IPLJI
JAVBF
LAI
M43
O9-
OCL
P2P
RIA
RIE
RNS
TN5
TWZ
VH1
VJK
AAYXX
CITATION
7SP
7U5
8FD
L7M
ID FETCH-LOGICAL-c292t-e58a19dd764aecec2d19c4bd0f382a114108b2a1ba1aead3f57735ea2312f5b83
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001336063600022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0018-9456
IngestDate Mon Jun 30 10:19:36 EDT 2025
Tue Nov 18 22:34:17 EST 2025
Sat Nov 29 04:38:53 EST 2025
Wed Aug 27 02:20:02 EDT 2025
IsPeerReviewed true
IsScholarly true
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-c292t-e58a19dd764aecec2d19c4bd0f382a114108b2a1ba1aead3f57735ea2312f5b83
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-4078-3527
0009-0008-4747-2247
0009-0004-3268-6278
0009-0004-6976-1884
0000-0002-6684-5642
PQID 3114556048
PQPubID 85462
PageCount 11
ParticipantIDs crossref_citationtrail_10_1109_TIM_2024_3460931
crossref_primary_10_1109_TIM_2024_3460931
ieee_primary_10680570
proquest_journals_3114556048
PublicationCentury 2000
PublicationDate 20240000
2024-00-00
20240101
PublicationDateYYYYMMDD 2024-01-01
PublicationDate_xml – year: 2024
  text: 20240000
PublicationDecade 2020
PublicationPlace New York
PublicationPlace_xml – name: New York
PublicationTitle IEEE transactions on instrumentation and measurement
PublicationTitleAbbrev TIM
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 ref13
ref14
Vincent (ref8) 2010; 11
ref11
ref10
ref2
Kingma (ref25) 2014
ref1
Krizhevsky (ref15) 2009
ref17
ref19
ref18
Falcon (ref26) 2019
Maas (ref24); 30
van den Oord (ref9); 30
ref23
ref20
ref22
ref21
ref27
ref7
ref4
ref3
Xiao (ref16) 2017
Golan (ref5)
ref6
Ruff (ref12)
References_xml – ident: ref7
  doi: 10.48550/arXiv.1312.6114
– volume-title: arXiv:1708.07747
  year: 2017
  ident: ref16
  article-title: Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms
– ident: ref23
  doi: 10.5555/3045118.3045167
– ident: ref20
  doi: 10.1109/CVPRW56347.2022.00080
– volume: 11
  start-page: 1
  issue: 12
  year: 2010
  ident: ref8
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: J. Mach. Learn. Res.
– ident: ref2
  doi: 10.1109/access.2018.2816564
– ident: ref11
  doi: 10.1023/B:MACH.0000008084.60811.49
– ident: ref22
  doi: 10.1109/CVPR.2019.00057
– volume-title: PyTorch Lightning
  year: 2019
  ident: ref26
– ident: ref27
  doi: 10.1145/3292500.3330701
– volume-title: Learning Multiple Layers of Features From Tiny Images
  year: 2009
  ident: ref15
– ident: ref18
  doi: 10.1109/cvpr.2018.00684
– ident: ref4
  doi: 10.1109/CVPR.2017.76
– volume: 30
  start-page: 1
  volume-title: 31st Conf. Neural. Inf. Proc. Syst.
  ident: ref9
  article-title: Neural discrete representation learning
– ident: ref1
  doi: 10.1109/TETCI.2017.2772792
– ident: ref6
  doi: 10.1007/978-3-642-21735-7_7
– start-page: 4393
  volume-title: Proc. Int. Conf. Mach. Learn.
  ident: ref12
  article-title: Deep one-class classification
– ident: ref17
  doi: 10.1109/CVPR.2019.00982
– ident: ref19
  doi: 10.1109/ICCV48922.2021.01333
– ident: ref21
  doi: 10.1109/TIM.2021.3098381
– ident: ref3
  doi: 10.1109/CVPR52729.2023.00381
– volume: 30
  start-page: 1
  volume-title: Proc. 30th Int. Conf. Mach. Learn. (ICML)
  ident: ref24
  article-title: Rectifier nonlinearities improve neural network acoustic models
– ident: ref10
  doi: 10.1109/ICCV.2019.00179
– ident: ref14
  doi: 10.1162/neco.1997.9.8.1735
– start-page: 9781
  volume-title: Proc. 32nd Int. Conf. Neural Inf. Process. Syst.
  ident: ref5
  article-title: Deep anomaly detection using geometric transformations
– ident: ref13
  doi: 10.1002/int.22582
– volume-title: arXiv:1412.6980
  year: 2014
  ident: ref25
  article-title: Adam: A method for stochastic optimization
SSID ssj0007647
Score 2.4187915
Snippet The task of anomaly detection is to separate anomalous data from normal data in the dataset. Models such as deep Convolutional AutoEncoder (CAE) and deep...
SourceID proquest
crossref
ieee
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1
SubjectTerms Accuracy
Anomalies
Anomaly detection
autoencoder
Data analysis
Data models
Datasets
deep support vector data description (Deep SVDD)
Feature extraction
hypersphere collapse
Long short term memory
LSTM
Mathematical models
Modules
Training
Vectors
Title Improved AutoEncoder With LSTM Module and KL Divergence for Anomaly Detection
URI https://ieeexplore.ieee.org/document/10680570
https://www.proquest.com/docview/3114556048
Volume 73
WOSCitedRecordID wos001336063600022&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: PRVIEE
  databaseName: IEEE Xplore (IEEE/IET Electronic Library - IEL)
  customDbUrl:
  eissn: 1557-9662
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0007647
  issn: 0018-9456
  databaseCode: RIE
  dateStart: 19630101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8QwFA4qCnpwF8eNHLx4qDZN2rTHwQVFRwRH9FayvOLA2MpMR_Df-5J2RBEFLyWHJJT38pYveQshhwpRleEFYhOtTSBEEQc6TkyAll5JkCrkXPlmE_L2Nn16yu7aZHWfCwMAPvgMjt3Qv-XbykzcVRlKeJKif4EIfVbKpEnW-lS7MhFNgUyGEoxuwfRNMsxO-lc9RIKROOYiQQTPvtkg31Tlhyb25uVi5Z8_tkqWWz-SdhvGr5EZKNfJ0pfqgutkwUd3mvEG6TVXB2Bpd1JX56XLYx_Rx0H9TG_u-z3aq-xkCFSVll7f0DMXquFrdFL0aGm3rF7U8J2eQe3DtspN8nBx3j-9DNo-CoGJsqgOIE4Vy6xFCikwYCLLMiO0DQueRoq5SM9U40ArpvBg8SKWkseg0PWLilinfIvMlVUJ24RyBiDimONXo-uRpSbTUhYh00LYhLMOOZlSNjdtkXHX62KYe7ARZjnyIne8yFtedMjR54rXpsDGH3M3He2_zGvI3iF7U-7lrQiOc85cDfYENdTOL8t2yaLbvblQ2SNz9WgC-2TevNWD8ejAn64PClHKoQ
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT9wwEB4hSgU9FApU3RZaH3rhEIhj53VcFRCr3ayQuhXcIj8mYqVtgnazlfrvO3ayiKpqpV4iH2w5mvE8PnseAJ8VoSojKsImWptAyioOdJyYgCy9SjFVoRDKN5tIp9Ps_j6_7ZPVfS4MIvrgMzx3Q_-WbxuzdldlJOFJRv4FIfQXrnVWn671pHjTRHYlMjnJMDkGm1fJML-YjQrCgpE8FzIhDM9_s0K-rcofutgbmOv9__y1A3jde5Js2LH-DWxhfQivntUXPISXPr7TrI6g6C4P0LLhum2uapfJvmR38_aBTb7OClY0dr1ApmrLxhN26YI1fJVORj4tG9bNd7X4yS6x9YFb9TF8u76afbkJ-k4KgYnyqA0wzhTPrSUKKTRoIstzI7UNK5FFirtYz0zTQCuu6GiJKk5TEaMi5y-qYp2Jt7BdNzW-AyY4ooxjQV9NzkeemVynaRVyLaVNBB_AxYaypenLjLtuF4vSw40wL4kXpeNF2fNiAGdPKx67Ehv_mHvsaP9sXkf2AZxsuFf2QrgqBXdV2BPSUe__suwT7N7Mikk5GU3HH2DP7dRdr5zAdrtc4ynsmB_tfLX86E_aL8aIzeo
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=Improved+AutoEncoder+With+LSTM+Module+and+KL+Divergence+for+Anomaly+Detection&rft.jtitle=IEEE+transactions+on+instrumentation+and+measurement&rft.au=Huang%2C+Wei&rft.au=Zhang%2C+Bingyang&rft.au=Zhang%2C+Kaituo&rft.au=Gao%2C+Hua&rft.date=2024&rft.issn=0018-9456&rft.eissn=1557-9662&rft.volume=73&rft.spage=1&rft.epage=11&rft_id=info:doi/10.1109%2FTIM.2024.3460931&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIM_2024_3460931
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9456&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9456&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9456&client=summon