Concept Drift Detection via Equal Intensity k-Means Space Partitioning

The data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time passes. Such a distribution change in streaming data is called concept drift. Numerous histogram-based distribution change detection methods hav...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on cybernetics Ročník 51; číslo 6; s. 3198 - 3211
Hlavní autori: Liu, Anjin, Lu, Jie, Zhang, Guangquan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: United States IEEE 01.06.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
ISSN:2168-2267, 2168-2275, 2168-2275
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time passes. Such a distribution change in streaming data is called concept drift. Numerous histogram-based distribution change detection methods have been proposed to detect drift. Most histograms are developed on the grid-based or tree-based space partitioning algorithms which makes the space partitions arbitrary, unexplainable, and may cause drift blind spots. There is a need to improve the drift detection accuracy for the histogram-based methods with the unsupervised setting. To address this problem, we propose a cluster-based histogram, called equal intensity <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula>-means space partitioning (EI-kMeans). In addition, a heuristic method to improve the sensitivity of drift detection is introduced. The fundamental idea of improving the sensitivity is to minimize the risk of creating partitions in distribution offset regions. Pearson's chi-square test is used as the statistical hypothesis test so that the test statistics remain independent of the sample distribution. The number of bins and their shapes, which strongly influence the ability to detect drift, are determined dynamically from the sample based on an asymptotic constraint in the chi-square test. Accordingly, three algorithms are developed to implement concept drift detection, including a greedy centroids initialization algorithm, a cluster amplify-shrink algorithm, and a drift detection algorithm. For drift adaptation, we recommend retraining the learner if a drift is detected. The results of experiments on the synthetic and real-world datasets demonstrate the advantages of EI-kMeans and show its efficacy in detecting concept drift.
AbstractList The data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time passes. Such a distribution change in streaming data is called concept drift. Numerous histogram-based distribution change detection methods have been proposed to detect drift. Most histograms are developed on the grid-based or tree-based space partitioning algorithms which makes the space partitions arbitrary, unexplainable, and may cause drift blind spots. There is a need to improve the drift detection accuracy for the histogram-based methods with the unsupervised setting. To address this problem, we propose a cluster-based histogram, called equal intensity [Formula Omitted]-means space partitioning (EI-kMeans). In addition, a heuristic method to improve the sensitivity of drift detection is introduced. The fundamental idea of improving the sensitivity is to minimize the risk of creating partitions in distribution offset regions. Pearson’s chi-square test is used as the statistical hypothesis test so that the test statistics remain independent of the sample distribution. The number of bins and their shapes, which strongly influence the ability to detect drift, are determined dynamically from the sample based on an asymptotic constraint in the chi-square test. Accordingly, three algorithms are developed to implement concept drift detection, including a greedy centroids initialization algorithm, a cluster amplify–shrink algorithm, and a drift detection algorithm. For drift adaptation, we recommend retraining the learner if a drift is detected. The results of experiments on the synthetic and real-world datasets demonstrate the advantages of EI-kMeans and show its efficacy in detecting concept drift.
The data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time passes. Such a distribution change in streaming data is called concept drift. Numerous histogram-based distribution change detection methods have been proposed to detect drift. Most histograms are developed on the grid-based or tree-based space partitioning algorithms which makes the space partitions arbitrary, unexplainable, and may cause drift blind spots. There is a need to improve the drift detection accuracy for the histogram-based methods with the unsupervised setting. To address this problem, we propose a cluster-based histogram, called equal intensity <inline-formula> <tex-math notation="LaTeX">k </tex-math></inline-formula>-means space partitioning (EI-kMeans). In addition, a heuristic method to improve the sensitivity of drift detection is introduced. The fundamental idea of improving the sensitivity is to minimize the risk of creating partitions in distribution offset regions. Pearson's chi-square test is used as the statistical hypothesis test so that the test statistics remain independent of the sample distribution. The number of bins and their shapes, which strongly influence the ability to detect drift, are determined dynamically from the sample based on an asymptotic constraint in the chi-square test. Accordingly, three algorithms are developed to implement concept drift detection, including a greedy centroids initialization algorithm, a cluster amplify-shrink algorithm, and a drift detection algorithm. For drift adaptation, we recommend retraining the learner if a drift is detected. The results of experiments on the synthetic and real-world datasets demonstrate the advantages of EI-kMeans and show its efficacy in detecting concept drift.
The data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time passes. Such a distribution change in streaming data is called concept drift. Numerous histogram-based distribution change detection methods have been proposed to detect drift. Most histograms are developed on the grid-based or tree-based space partitioning algorithms which makes the space partitions arbitrary, unexplainable, and may cause drift blind spots. There is a need to improve the drift detection accuracy for the histogram-based methods with the unsupervised setting. To address this problem, we propose a cluster-based histogram, called equal intensity k -means space partitioning (EI-kMeans). In addition, a heuristic method to improve the sensitivity of drift detection is introduced. The fundamental idea of improving the sensitivity is to minimize the risk of creating partitions in distribution offset regions. Pearson's chi-square test is used as the statistical hypothesis test so that the test statistics remain independent of the sample distribution. The number of bins and their shapes, which strongly influence the ability to detect drift, are determined dynamically from the sample based on an asymptotic constraint in the chi-square test. Accordingly, three algorithms are developed to implement concept drift detection, including a greedy centroids initialization algorithm, a cluster amplify-shrink algorithm, and a drift detection algorithm. For drift adaptation, we recommend retraining the learner if a drift is detected. The results of experiments on the synthetic and real-world datasets demonstrate the advantages of EI-kMeans and show its efficacy in detecting concept drift.
The data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time passes. Such a distribution change in streaming data is called concept drift. Numerous histogram-based distribution change detection methods have been proposed to detect drift. Most histograms are developed on the grid-based or tree-based space partitioning algorithms which makes the space partitions arbitrary, unexplainable, and may cause drift blind spots. There is a need to improve the drift detection accuracy for the histogram-based methods with the unsupervised setting. To address this problem, we propose a cluster-based histogram, called equal intensity k -means space partitioning (EI-kMeans). In addition, a heuristic method to improve the sensitivity of drift detection is introduced. The fundamental idea of improving the sensitivity is to minimize the risk of creating partitions in distribution offset regions. Pearson's chi-square test is used as the statistical hypothesis test so that the test statistics remain independent of the sample distribution. The number of bins and their shapes, which strongly influence the ability to detect drift, are determined dynamically from the sample based on an asymptotic constraint in the chi-square test. Accordingly, three algorithms are developed to implement concept drift detection, including a greedy centroids initialization algorithm, a cluster amplify-shrink algorithm, and a drift detection algorithm. For drift adaptation, we recommend retraining the learner if a drift is detected. The results of experiments on the synthetic and real-world datasets demonstrate the advantages of EI-kMeans and show its efficacy in detecting concept drift.The data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time passes. Such a distribution change in streaming data is called concept drift. Numerous histogram-based distribution change detection methods have been proposed to detect drift. Most histograms are developed on the grid-based or tree-based space partitioning algorithms which makes the space partitions arbitrary, unexplainable, and may cause drift blind spots. There is a need to improve the drift detection accuracy for the histogram-based methods with the unsupervised setting. To address this problem, we propose a cluster-based histogram, called equal intensity k -means space partitioning (EI-kMeans). In addition, a heuristic method to improve the sensitivity of drift detection is introduced. The fundamental idea of improving the sensitivity is to minimize the risk of creating partitions in distribution offset regions. Pearson's chi-square test is used as the statistical hypothesis test so that the test statistics remain independent of the sample distribution. The number of bins and their shapes, which strongly influence the ability to detect drift, are determined dynamically from the sample based on an asymptotic constraint in the chi-square test. Accordingly, three algorithms are developed to implement concept drift detection, including a greedy centroids initialization algorithm, a cluster amplify-shrink algorithm, and a drift detection algorithm. For drift adaptation, we recommend retraining the learner if a drift is detected. The results of experiments on the synthetic and real-world datasets demonstrate the advantages of EI-kMeans and show its efficacy in detecting concept drift.
Author Lu, Jie
Zhang, Guangquan
Liu, Anjin
Author_xml – sequence: 1
  givenname: Anjin
  orcidid: 0000-0002-0733-7138
  surname: Liu
  fullname: Liu, Anjin
  email: anjin.liu@uts.edu.au
  organization: Centre for Artificial Intelligence, University of Technology Sydney, Ultimo, NSW, Australia
– sequence: 2
  givenname: Jie
  orcidid: 0000-0003-0690-4732
  surname: Lu
  fullname: Lu, Jie
  email: jie.lu@uts.edu.au
  organization: Centre for Artificial Intelligence, University of Technology Sydney, Ultimo, NSW, Australia
– sequence: 3
  givenname: Guangquan
  orcidid: 0000-0003-3960-0583
  surname: Zhang
  fullname: Zhang, Guangquan
  email: guangquan.zhang@uts.edu.au
  organization: Centre for Artificial Intelligence, University of Technology Sydney, Ultimo, NSW, Australia
BackLink https://www.ncbi.nlm.nih.gov/pubmed/32324590$$D View this record in MEDLINE/PubMed
BookMark eNp9kUtrGzEURkVwSRw3P6AEwkA23Yyr0WukZeI8anBpoemiKyFr7hQlY40jaQL599Vg1wsvqoUkxDlXl_udo4nvPSD0qcLzqsLqy9Pi9-2cYILnREmqBDlBU1IJWRJS88nhLuozdBHjM85L5iclT9EZJZQwrvAUPSx6b2Gbirvg2rxDAptc74s3Z4r718F0xdIn8NGl9-Kl_AbGx-Ln1lgofpiQ3Mg6_-cj-tCaLsLF_pyhXw_3T4uv5er743JxsyotZSqVqgZpBWcGUw7YVAJDyxlR1nLckGqNobFtI4VSDVGMSitZA7JthYDa8EbRGfq8q7sN_esAMemNixa6znjoh6gJVUxKJbI8Q9dH6HM_BJ-704QTqRhTuM7U1Z4a1hto9Da4jQnv-t-EMlDtABv6GAO0B6TCegxCj0HoMQi9DyI79ZFjXTLjqFIwrvuvebkzHQAcfsqNCoo5_Qs_fJMr
CODEN ITCEB8
CitedBy_id crossref_primary_10_1007_s13042_023_01810_z
crossref_primary_10_1016_j_knosys_2021_107443
crossref_primary_10_2139_ssrn_5368329
crossref_primary_10_1007_s11227_023_05729_8
crossref_primary_10_1016_j_eswa_2022_119273
crossref_primary_10_1109_JIOT_2023_3286185
crossref_primary_10_1109_TIE_2023_3319732
crossref_primary_10_1016_j_asoc_2024_111452
crossref_primary_10_1016_j_engappai_2024_107979
crossref_primary_10_1109_MNET_129_2200417
crossref_primary_10_3390_smartcities7060133
crossref_primary_10_1016_j_asoc_2025_113903
crossref_primary_10_32604_cmc_2024_045932
crossref_primary_10_1016_j_ins_2022_12_085
crossref_primary_10_1016_j_jacr_2022_05_030
crossref_primary_10_1109_TCYB_2021_3109796
crossref_primary_10_7717_peerj_cs_2286
crossref_primary_10_1016_j_knosys_2024_111596
crossref_primary_10_3390_smartcities4010021
crossref_primary_10_1016_j_dajour_2023_100178
crossref_primary_10_3390_fi16030094
crossref_primary_10_1109_TCYB_2025_3587025
crossref_primary_10_1109_TCYB_2021_3109066
crossref_primary_10_1007_s10994_022_06177_w
crossref_primary_10_1109_TCYB_2025_3569816
crossref_primary_10_1007_s13042_022_01630_7
crossref_primary_10_1109_TCSS_2024_3442238
crossref_primary_10_1109_TNNLS_2021_3122531
crossref_primary_10_1109_TKDE_2024_3460404
crossref_primary_10_1016_j_cose_2024_104121
crossref_primary_10_1109_TCYB_2024_3429459
crossref_primary_10_1016_j_asoc_2024_112051
crossref_primary_10_1016_j_patcog_2022_109113
crossref_primary_10_1016_j_comnet_2024_110290
crossref_primary_10_1109_TITS_2021_3137446
crossref_primary_10_1016_j_procs_2023_10_293
crossref_primary_10_1109_TFUZZ_2020_3016040
crossref_primary_10_7717_peerj_cs_1863
crossref_primary_10_1016_j_engappai_2024_109311
crossref_primary_10_1016_j_ipm_2022_102911
crossref_primary_10_1109_TSMC_2021_3102978
crossref_primary_10_1109_TCYB_2023_3265926
crossref_primary_10_1109_TKDE_2023_3344602
crossref_primary_10_1109_TNNLS_2023_3294846
crossref_primary_10_1109_TCYB_2021_3051406
crossref_primary_10_1016_j_knosys_2024_111681
Cites_doi 10.1145/361002.361007
10.24963/ijcai.2017/317
10.1109/TKDE.2014.2345380
10.1007/978-3-319-46227-1_7
10.1016/j.artint.2014.01.001
10.1016/j.artint.2015.09.009
10.1145/2523813
10.1016/j.neucom.2017.01.078
10.1145/3357384.3357946
10.1007/978-3-319-26989-4_4
10.1109/TNNLS.2020.2978523
10.1214/aos/1176344722
10.1109/TNNLS.2015.2512714
10.1109/TNNLS.2013.2239309
10.1016/j.patcog.2011.06.019
10.1109/TKDE.2005.48
10.1007/BF00288933
10.1109/TKDE.2016.2526675
10.1109/ICDM.2019.00021
10.1109/TKDE.2014.2345382
10.1109/TKDE.2017.2772239
10.1109/TNNLS.2013.2248094
10.1145/2939672.2939836
10.1109/BigData47090.2019.9006285
10.1109/TNNLS.2012.2236570
10.1109/TCYB.2016.2612686
10.1109/MCI.2015.2471196
10.3233/IDA-2007-11406
10.1109/TSMCA.2012.2224338
10.1016/j.eswa.2017.04.008
10.1109/TSMC.2017.2682502
10.1137/1.9781611972771.42
10.1016/j.patcog.2017.11.009
10.1016/j.eswa.2017.08.023
10.1109/IJCNN.2017.7966060
10.1109/TNNLS.2020.2973293
10.1109/TNNLS.2016.2619909
10.1109/TKDE.2013.34
10.1109/5326.983933
10.1201/9781315140919
10.1109/TNNLS.2017.2771290
10.1109/TKDE.2011.58
10.1109/TFUZZ.2019.2910714
10.1109/TKDE.2018.2876857
ContentType Journal Article
Copyright Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID 97E
RIA
RIE
AAYXX
CITATION
NPM
7SC
7SP
7TB
8FD
F28
FR3
H8D
JQ2
L7M
L~C
L~D
7X8
DOI 10.1109/TCYB.2020.2983962
DatabaseName IEEE All-Society Periodicals Package (ASPP) 2005–Present
IEEE All-Society Periodicals Package (ASPP) 1998–Present
IEEE Xplore
CrossRef
PubMed
Computer and Information Systems Abstracts
Electronics & Communications Abstracts
Mechanical & Transportation Engineering Abstracts
Technology Research Database
ANTE: Abstracts in New Technology & Engineering
Engineering Research Database
Aerospace Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
MEDLINE - Academic
DatabaseTitle CrossRef
PubMed
Aerospace Database
Technology Research Database
Computer and Information Systems Abstracts – Academic
Mechanical & Transportation Engineering Abstracts
Electronics & Communications 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
MEDLINE - Academic
DatabaseTitleList Aerospace Database

PubMed
MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: RIE
  name: IEEE Xplore
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
– sequence: 3
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Sciences (General)
EISSN 2168-2275
EndPage 3211
ExternalDocumentID 32324590
10_1109_TCYB_2020_2983962
9076305
Genre orig-research
Journal Article
GrantInformation_xml – fundername: Australian Research Council through the Discovery Project
  grantid: DP190101733
  funderid: 10.13039/501100000923
GroupedDBID 0R~
4.4
6IK
97E
AAJGR
AARMG
AASAJ
AAWTH
ABAZT
ABQJQ
ABVLG
ACIWK
AENEX
AGQYO
AGSQL
AHBIQ
AKJIK
AKQYR
ALMA_UNASSIGNED_HOLDINGS
ATWAV
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
EBS
EJD
HZ~
IFIPE
IPLJI
JAVBF
M43
O9-
OCL
PQQKQ
RIA
RIE
RNS
AAYXX
CITATION
NPM
RIG
7SC
7SP
7TB
8FD
F28
FR3
H8D
JQ2
L7M
L~C
L~D
7X8
ID FETCH-LOGICAL-c349t-97e8c654a035e0a160ef5429cc50d21b0edcfd8699d29438c84de8ff66e7a5d93
IEDL.DBID RIE
ISICitedReferencesCount 79
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000652065400029&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2168-2267
2168-2275
IngestDate Sun Sep 28 00:40:23 EDT 2025
Tue Oct 28 07:42:42 EDT 2025
Thu Apr 03 07:00:18 EDT 2025
Tue Nov 18 22:22:12 EST 2025
Sat Nov 29 02:02:30 EST 2025
Wed Aug 27 02:30:24 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 6
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-c349t-97e8c654a035e0a160ef5429cc50d21b0edcfd8699d29438c84de8ff66e7a5d93
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ORCID 0000-0003-3960-0583
0000-0002-0733-7138
0000-0003-0690-4732
PMID 32324590
PQID 2528944907
PQPubID 85422
PageCount 14
ParticipantIDs crossref_citationtrail_10_1109_TCYB_2020_2983962
ieee_primary_9076305
proquest_journals_2528944907
pubmed_primary_32324590
proquest_miscellaneous_2394889694
crossref_primary_10_1109_TCYB_2020_2983962
PublicationCentury 2000
PublicationDate 2021-06-01
PublicationDateYYYYMMDD 2021-06-01
PublicationDate_xml – month: 06
  year: 2021
  text: 2021-06-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Piscataway
PublicationTitle IEEE transactions on cybernetics
PublicationTitleAbbrev TCYB
PublicationTitleAlternate IEEE Trans Cybern
PublicationYear 2021
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 ref35
ref13
ref34
ref12
ref37
ref15
ref36
ref14
ref31
ref30
ref11
ref32
ref10
ref2
ref39
ref17
ref38
ref16
ref19
ref18
boracchi (ref1) 2018
ref46
ref24
ref23
ref48
ref26
ref47
ref25
ref20
ref42
ref41
ref22
ref21
ref43
ref28
ref27
ref29
ref8
ref7
haque (ref33) 2016
ref9
ref4
ref3
ref6
ref5
ref40
box (ref45) 1978; 1
dasu (ref44) 2006
References_xml – ident: ref43
  doi: 10.1145/361002.361007
– ident: ref25
  doi: 10.24963/ijcai.2017/317
– start-page: 1652
  year: 2016
  ident: ref33
  article-title: SAND: Semi-supervised adaptive novel class detection and classification over data stream
  publication-title: Proc AAAI Conf Artif Intell
– ident: ref6
  doi: 10.1109/TKDE.2014.2345380
– ident: ref41
  doi: 10.1007/978-3-319-46227-1_7
– ident: ref13
  doi: 10.1016/j.artint.2014.01.001
– ident: ref24
  doi: 10.1016/j.artint.2015.09.009
– ident: ref23
  doi: 10.1145/2523813
– ident: ref28
  doi: 10.1016/j.neucom.2017.01.078
– ident: ref29
  doi: 10.1145/3357384.3357946
– ident: ref9
  doi: 10.1007/978-3-319-26989-4_4
– ident: ref32
  doi: 10.1109/TNNLS.2020.2978523
– ident: ref48
  doi: 10.1214/aos/1176344722
– ident: ref26
  doi: 10.1109/TNNLS.2015.2512714
– ident: ref46
  doi: 10.1109/TNNLS.2013.2239309
– ident: ref20
  doi: 10.1016/j.patcog.2011.06.019
– ident: ref37
  doi: 10.1109/TKDE.2005.48
– start-page: 638
  year: 2018
  ident: ref1
  article-title: QuantTree: Histograms for change detection in multivariate data streams
  publication-title: Proc Int Conf Mach Learn
– ident: ref17
  doi: 10.1007/BF00288933
– volume: 1
  year: 1978
  ident: ref45
  publication-title: Statistics for Experimenters An Introduction to Design Data Analysis and Model Building
– ident: ref5
  doi: 10.1109/TKDE.2016.2526675
– ident: ref22
  doi: 10.1109/ICDM.2019.00021
– ident: ref40
  doi: 10.1109/TKDE.2014.2345382
– ident: ref35
  doi: 10.1109/TKDE.2017.2772239
– ident: ref42
  doi: 10.1109/TNNLS.2013.2248094
– ident: ref15
  doi: 10.1145/2939672.2939836
– ident: ref39
  doi: 10.1109/BigData47090.2019.9006285
– ident: ref34
  doi: 10.1109/TNNLS.2012.2236570
– ident: ref19
  doi: 10.1109/TCYB.2016.2612686
– ident: ref27
  doi: 10.1109/MCI.2015.2471196
– ident: ref38
  doi: 10.3233/IDA-2007-11406
– ident: ref21
  doi: 10.1109/TSMCA.2012.2224338
– ident: ref31
  doi: 10.1016/j.eswa.2017.04.008
– ident: ref11
  doi: 10.1109/TSMC.2017.2682502
– ident: ref10
  doi: 10.1137/1.9781611972771.42
– ident: ref14
  doi: 10.1016/j.patcog.2017.11.009
– ident: ref36
  doi: 10.1016/j.eswa.2017.08.023
– ident: ref18
  doi: 10.1109/IJCNN.2017.7966060
– ident: ref8
  doi: 10.1109/TNNLS.2020.2973293
– start-page: 1
  year: 2006
  ident: ref44
  article-title: An information-theoretic approach to detecting changes in multi-dimensional data streams
  publication-title: Proc 28th Symp Interface Stat Comput Sci Appl
– ident: ref7
  doi: 10.1109/TNNLS.2016.2619909
– ident: ref2
  doi: 10.1109/TKDE.2013.34
– ident: ref12
  doi: 10.1109/5326.983933
– ident: ref16
  doi: 10.1201/9781315140919
– ident: ref30
  doi: 10.1109/TNNLS.2017.2771290
– ident: ref3
  doi: 10.1109/TKDE.2011.58
– ident: ref47
  doi: 10.1109/TFUZZ.2019.2910714
– ident: ref4
  doi: 10.1109/TKDE.2018.2876857
SSID ssj0000816898
Score 2.5282936
Snippet The data stream poses additional challenges to statistical classification tasks because distributions of the training and target samples may differ as time...
SourceID proquest
pubmed
crossref
ieee
SourceType Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 3198
SubjectTerms Algorithms
Centroids
Change detection
Change detection algorithms
Chi-square test
Clustering algorithms
Clusters
Concept drift
data stream
Data transmission
Detection algorithms
Drift
Greedy algorithms
Heuristic algorithms
Heuristic methods
Histograms
multivariate two-sample test
Partitioning
Partitioning algorithms
Sensitivity
space partition
Statistical methods
Statistical tests
Training
Title Concept Drift Detection via Equal Intensity k-Means Space Partitioning
URI https://ieeexplore.ieee.org/document/9076305
https://www.ncbi.nlm.nih.gov/pubmed/32324590
https://www.proquest.com/docview/2528944907
https://www.proquest.com/docview/2394889694
Volume 51
WOSCitedRecordID wos000652065400029&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
  customDbUrl:
  eissn: 2168-2275
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000816898
  issn: 2168-2267
  databaseCode: RIE
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://ieeexplore.ieee.org/
  providerName: IEEE
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3daxQxEA-1-OCL9ks9-0EEH9pi2mySzSaP9drDF0vBFs6nJZfMwqHsyd1ewf_eSTa3-FAFX5bAzm5CZpLMTGbmR8iHUgU8Z4JjXglgSvmSOekE86IJWjQzW4mQwCaq21szndq7LfJxyIUBgBR8Bhexme7yw8Kvo6vsEg05LWPB0mdVVfW5WoM_JQFIJOhbgQ2GWkWVLzELbi_vx98-oTEo-IWwqBLoCGIjozJRxs34jxMpQaz8XdtMp87k1f-Nd4e8zNolverFYZdsQbtHdvP6XdHTXGT6bJ9Mxn2-Ir1ezht8Qpdislr6OHf0JqZa0hzd3v2i39kXwCONfkUDG-hdlLbsxz0gD5Ob-_FnljEVmJfKdsxWYLwuleOyBO4KzaGJkFXelzyIYsYh-CYYbW0QVknjjQpgmkZrqFwZrHxNtttFC28JdYVTYSZFAQZQDbNWuMapmXFOaYm9jQjfzGvtc8HxiHvxo06GB7d15EoduVJnrozI-fDJz77axr-I9-OUD4R5tkfkaMO8Oq_HVS1KNCyVQpIReT-8xpUUr0dcC4s10kiLu5nVFkf-pmf68O-NrLx7us9D8kLEWJfknTki291yDcfkuX_s5qvlCYrr1Jwkcf0NbEfiYw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3daxQxEB9KFfRFrdV6tWoEH1RMm83Xbh717FGxPQqeUJ-WXDILh7JX7vYK_vcm2dzigwq-LIGd3YTMJPORyfwAXinpg57xljrJkUrpFLXCcup44zVv5qbkPoFNlNNpdXVlLnfg3XAXBhFT8hkex2Y6y_dLt4mhspPgyGkRC5beUlLyor-tNURUEoREAr_loUGDXVHmY8yCmZPZ-NuH4A5ydsxNMAp0hLER0ZxQcTv-TSclkJW_25tJ70zu_9-IH8C9bF-S971A7MEOtg9hL6_gNXmdy0y_2YfJuL-xSD6uFk14Ypeyslpys7DkNF62JDm_vftJvtMLDEqNfAkuNpLLKG85kvsIvk5OZ-MzmlEVqBPSdNSUWDmtpGVCIbOFZthE0CrnFPO8mDP0rvGVNsZzI0XlKumxahqtsbTKG_EYdttli0-A2MJKPxe8wAqDIWYMt42V88paqUXobQRsO6-1yyXHI_LFjzq5HszUkSt15EqduTKCt8Mn1329jX8R78cpHwjzbI_gaMu8Oq_Idc1VcC2lDCQjeDm8DmspHpDYFpebQCNM2M-MNmHkBz3Th39vZeXwz32-gDtns4vz-vzT9PNTuMtj5kuK1RzBbrfa4DO47W66xXr1PAntLwZC5MI
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=Concept+Drift+Detection+via+Equal+Intensity+k-Means+Space+Partitioning&rft.jtitle=IEEE+transactions+on+cybernetics&rft.au=Liu%2C+Anjin&rft.au=Lu%2C+Jie&rft.au=Zhang%2C+Guangquan&rft.date=2021-06-01&rft.issn=2168-2275&rft.eissn=2168-2275&rft.volume=51&rft.issue=6&rft.spage=3198&rft_id=info:doi/10.1109%2FTCYB.2020.2983962&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2168-2267&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2168-2267&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2168-2267&client=summon