An iterative boosting-based ensemble for streaming data classification

•The IBS ensemble bases on iteratively applying boosting to learn from data stream.•IBS adjusts to new concept by gathering knowledge according to its current accuracy.•Adding more base learners when accuracy is low helps IBS recover fast from drifts.•IBS join features from batch and online algorith...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Information fusion Ročník 45; s. 66 - 78
Hlavní autori: Bertini Junior, João Roberto, Nicoletti, Maria do Carmo
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 01.01.2019
Predmet:
ISSN:1566-2535, 1872-6305
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract •The IBS ensemble bases on iteratively applying boosting to learn from data stream.•IBS adjusts to new concept by gathering knowledge according to its current accuracy.•Adding more base learners when accuracy is low helps IBS recover fast from drifts.•IBS join features from batch and online algorithms, as fast learning and flexibility.•Results show IBS is effective and low cost to handle classification in data stream. Among the many issues related to data stream applications, those involved in predictive tasks such as classification and regression, play a significant role in Machine Learning (ML). The so-called ensemble-based approaches have characteristics that can be appealing to data stream applications, such as easy updating and high flexibility. In spite of that, some of the current approaches consider unsuitable ways of updating the ensemble along with the continuous stream processing, such as growing it indefinitely or deleting all its base learners when trying to overcome a concept drift. Such inadequate actions interfere with two inherent characteristics of data streams namely, its possible infinite length and its need for prompt responses. In this paper, a new ensemble-based algorithm, suitable for classification tasks, is proposed. It relies on applying boosting to new batches of data aiming at maintaining the ensemble by adding a certain number of base learners, which is established as a function of the current ensemble accuracy rate. The updating mechanism enhances the model flexibility, allowing the ensemble to gather knowledge fast to quickly overcome high error rates, due to concept drift, while maintaining satisfactory results by slowing down the updating rate in stable concepts. Results comparing the proposed ensemble-based algorithm against eight other ensembles found in the literature show that the proposed algorithm is very competitive when dealing with data stream classification.
AbstractList •The IBS ensemble bases on iteratively applying boosting to learn from data stream.•IBS adjusts to new concept by gathering knowledge according to its current accuracy.•Adding more base learners when accuracy is low helps IBS recover fast from drifts.•IBS join features from batch and online algorithms, as fast learning and flexibility.•Results show IBS is effective and low cost to handle classification in data stream. Among the many issues related to data stream applications, those involved in predictive tasks such as classification and regression, play a significant role in Machine Learning (ML). The so-called ensemble-based approaches have characteristics that can be appealing to data stream applications, such as easy updating and high flexibility. In spite of that, some of the current approaches consider unsuitable ways of updating the ensemble along with the continuous stream processing, such as growing it indefinitely or deleting all its base learners when trying to overcome a concept drift. Such inadequate actions interfere with two inherent characteristics of data streams namely, its possible infinite length and its need for prompt responses. In this paper, a new ensemble-based algorithm, suitable for classification tasks, is proposed. It relies on applying boosting to new batches of data aiming at maintaining the ensemble by adding a certain number of base learners, which is established as a function of the current ensemble accuracy rate. The updating mechanism enhances the model flexibility, allowing the ensemble to gather knowledge fast to quickly overcome high error rates, due to concept drift, while maintaining satisfactory results by slowing down the updating rate in stable concepts. Results comparing the proposed ensemble-based algorithm against eight other ensembles found in the literature show that the proposed algorithm is very competitive when dealing with data stream classification.
Author Bertini Junior, João Roberto
Nicoletti, Maria do Carmo
Author_xml – sequence: 1
  givenname: João Roberto
  surname: Bertini Junior
  fullname: Bertini Junior, João Roberto
  email: bertini@ft.unicamp.br
  organization: School of Technology, University of Campinas, SP, Rua Paschoal Marmo, 1888, Jd. Nova Itália, Limeira, Brazil
– sequence: 2
  givenname: Maria do Carmo
  surname: Nicoletti
  fullname: Nicoletti, Maria do Carmo
  email: carmo@cc.faccamp.br
  organization: FACCAMP, Campo Limpo Paulista, SP, Brazil
BookMark eNqFkE1LAzEQhoNUsK3-Aw_7B3adJLvZ1INQilWh4KX3kI-JpLRZSWLBf-_WevKgpxkYnpd3nhmZxCEiIbcUGgpU3O2aEL3_yA0DKhugDQC_IFMqe1YLDt1k3Dshatbx7orMct4B0B44nZL1MlahYNIlHLEyw5BLiG-10RldhTHjweyx8kOqckmoD-Oxcrroyu51zsEHO5JDvCaXXu8z3vzMOdmuH7er53rz-vSyWm5qy0GUWlihEYztmeO0d8a37QI6zVrjvTRyLKmF8yDZQhre-9ZYYRiVAp1gwCWfk_tzrE1Dzgm9sqF8FyhJh72ioE5C1E6dhaiTEAVUjUJGuP0Fv6dw0OnzP-zhjOH41zFgUtkGjBZdSGiLckP4O-ALFox_-A
CitedBy_id crossref_primary_10_1016_j_asoc_2022_108855
crossref_primary_10_1016_j_eswa_2020_113723
crossref_primary_10_1007_s10994_019_05840_z
crossref_primary_10_1016_j_bdr_2022_100356
crossref_primary_10_1155_2020_2836236
crossref_primary_10_1109_ACCESS_2021_3088612
crossref_primary_10_3390_electronics8060635
crossref_primary_10_32604_cmc_2021_016814
crossref_primary_10_7717_peerj_cs_424
crossref_primary_10_1109_TNNLS_2021_3091681
crossref_primary_10_1007_s43674_021_00015_7
crossref_primary_10_1109_ACCESS_2022_3207287
crossref_primary_10_3233_JIFS_191184
crossref_primary_10_1007_s10489_020_02106_3
crossref_primary_10_1155_2020_6147378
crossref_primary_10_3390_sym12081292
crossref_primary_10_3390_app13084649
crossref_primary_10_1016_j_datak_2023_102232
crossref_primary_10_1016_j_iot_2023_100994
crossref_primary_10_1016_j_asoc_2020_106825
crossref_primary_10_1088_1742_6596_1767_1_012016
crossref_primary_10_1109_TGCN_2022_3151716
crossref_primary_10_1007_s41870_024_01832_y
crossref_primary_10_1016_j_ins_2020_05_141
crossref_primary_10_7717_peerj_cs_459
crossref_primary_10_1016_j_knosys_2019_105114
crossref_primary_10_1002_sam_11662
crossref_primary_10_1016_j_engappai_2025_110034
crossref_primary_10_1371_journal_pone_0234824
crossref_primary_10_1016_j_eswa_2021_115591
crossref_primary_10_1155_2021_5549300
crossref_primary_10_3233_JIFS_211100
crossref_primary_10_1016_j_neucom_2024_128194
crossref_primary_10_3390_biomimetics8030306
crossref_primary_10_1016_j_asoc_2019_105601
crossref_primary_10_3389_fams_2018_00041
crossref_primary_10_1111_coin_12520
crossref_primary_10_1155_2020_6673535
Cites_doi 10.1016/j.ins.2016.10.028
10.1016/j.inffus.2013.04.006
10.1145/2523813
10.1006/jcss.1997.1504
10.1109/TNN.2011.2160459
10.1016/j.inffus.2017.09.005
10.1007/BF00116900
10.1006/inco.1994.1009
10.1016/j.inffus.2017.02.004
10.1007/s10994-012-5320-9
10.1109/TNNLS.2013.2251352
10.1145/1083784.1083789
10.1109/TNNLS.2013.2239309
10.1016/j.artint.2003.04.001
10.1016/j.inffus.2017.02.007
10.1109/MCI.2015.2471196
10.1023/A:1007661119649
10.1016/S1566-2535(02)00093-3
10.1016/j.inffus.2017.11.011
10.1007/BF00058655
10.3233/IDA-2007-11102
ContentType Journal Article
Copyright 2018 Elsevier B.V.
Copyright_xml – notice: 2018 Elsevier B.V.
DBID AAYXX
CITATION
DOI 10.1016/j.inffus.2018.01.003
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Mathematics
EISSN 1872-6305
EndPage 78
ExternalDocumentID 10_1016_j_inffus_2018_01_003
S156625351630183X
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
29I
4.4
457
4G.
5GY
5VS
7-5
71M
8P~
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
ABBOA
ABFNM
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ASPBG
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F0J
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HVGLF
HZ~
IHE
J1W
JJJVA
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
R2-
RIG
ROL
RPZ
SDF
SDG
SDP
SES
SEW
SPC
SPCBC
SST
SSV
SSZ
T5K
UHS
ZMT
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c306t-6c6ae0bc72d317dbf44905a24bff8b8156a6df08298b37f4bc6b2186ed620383
ISICitedReferencesCount 41
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000447084900006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1566-2535
IngestDate Tue Nov 18 22:16:45 EST 2025
Sat Nov 29 06:25:27 EST 2025
Fri Feb 23 02:23:31 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Incremental learning
Ensemble learning
Data stream classification
Boosting algorithms
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c306t-6c6ae0bc72d317dbf44905a24bff8b8156a6df08298b37f4bc6b2186ed620383
PageCount 13
ParticipantIDs crossref_citationtrail_10_1016_j_inffus_2018_01_003
crossref_primary_10_1016_j_inffus_2018_01_003
elsevier_sciencedirect_doi_10_1016_j_inffus_2018_01_003
PublicationCentury 2000
PublicationDate January 2019
2019-01-00
PublicationDateYYYYMMDD 2019-01-01
PublicationDate_xml – month: 01
  year: 2019
  text: January 2019
PublicationDecade 2010
PublicationTitle Information fusion
PublicationYear 2019
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References M. Lichman, UCI Machine Learning Repository, 2013. URL
Scholz, Klinkenberg (bib0027) 2007; 11
Oza, Russell (bib0018) 2001
Widmer, Kubat (bib0009) 1996; 23
Xu, Sun (bib0023) 2010
Kolter, Maloof (bib0033) 2007; 8
Maloof, Michalski (bib0010) 2004; 154
Zhao, Xie, Xu, Sun (bib0024) 2017; 38
Gama, Žliobaite, Bifet, Pechenizkiy, Bouchachia (bib0005) 2014; 46
Aggarwal (bib0003) 2010
Pelossof, Jones, Vovsha, Rudin (bib0020) 2009
Brzeziński, Stefanowski (bib0042) 2011; 6679
Gama (bib0006) 2010
Pocock, Yiapanis, Singer, Lujan, Brown (bib0021) 2010
Bouguelia, Karlsson, Pashami, Nowaczyk, Holst (bib0029) 2018; 43
Quinlan (bib0037) 1993
.
Li, Zhang, Shum, Zhang (bib0022) 2003
Maloof, Michalski (bib0039) 2000; 41
Breiman (bib0014) 1996; 24
S. Hettich, S. Bay, The UCI KDD archive, 1999, (University of California, Irvine, School of Information and Computer Sciences).
Chu, Zaniolo (bib0025) 2004
Littlestone, Warmuth (bib0044) 1994; 108
Krawczyk, Minku, Gama, Stefanowski, Woźniak (bib0012) 2017; 37
Street, Kim (bib0034) 2001
Schlimmer, Granger (bib0004) 1986
Kidera, Ozawa, Abe (bib0026) 2006
Alippi, Borrachi, Roveri (bib0040) 2013; 24
Brzeziński, Stefanowski (bib0041) 2014; 25
Aggarwal (Ed.) (bib0007) 2007
Ditzler, Roveri, Alippi, Polikar (bib0001) 2015; 10
Carcillo, Dal Pozzolo, Le Borgne, Caelen, Mazzer, Bontempi (bib0031) 2018; 41
Pietruczuk, Rutkowski, Jaworski, Duda (bib0043) 2017; 381
Freund, Schapire (bib0015) 1996
Jaber, Cornuéjols, Tarroux (bib0045) 2013; 8227
Breiman, Friedman, Olshen, Stone (bib0050) 1984
Freund, Schapire (bib0046) 1997; 55
Gama, Medas, Castillo, Rodrigues (bib0049) 2004; 3171
Gaber, Zaslavsky, Krishnaswamy (bib0002) 2005; 34
Read, Bifet, Pfahringer, Holmes (bib0011) 2012; 7619
Kuncheva, Skurichina, Duin (bib0017) 2002; 3
Gama, Sebastiao, Rodrigues (bib0048) 2013; 90
Elwell, Polikar (bib0028) 2011; 22
Nguyen, Woon, Ng (bib0008) 2014
Ramamurthy, Bhatnagar (bib0036) 2007
Oza, Russell (bib0019) 2001
Xingquan, Xindong, Ying (bib0032) 2004
Wang, Fan, Yu, Han (bib0035) 2003
Hulten, Spencer, Domingos (bib0038) 2001
Woźniak, Cyganek (bib0030) 2016; 9714
Bifet, Holmes, Pfahringer, Gavaldà (bib0047) 2009
Harries (bib0051) 1999
Woźniak, Grana, Corchado (bib0013) 2014; 16
Freund, Schapire (bib0016) 1997; 55
Chu (10.1016/j.inffus.2018.01.003_bib0025) 2004
Oza (10.1016/j.inffus.2018.01.003_bib0019) 2001
Alippi (10.1016/j.inffus.2018.01.003_bib0040) 2013; 24
10.1016/j.inffus.2018.01.003_bib0052
10.1016/j.inffus.2018.01.003_bib0053
Li (10.1016/j.inffus.2018.01.003_bib0022) 2003
Ramamurthy (10.1016/j.inffus.2018.01.003_bib0036) 2007
Scholz (10.1016/j.inffus.2018.01.003_bib0027) 2007; 11
Gaber (10.1016/j.inffus.2018.01.003_bib0002) 2005; 34
Bouguelia (10.1016/j.inffus.2018.01.003_bib0029) 2018; 43
Street (10.1016/j.inffus.2018.01.003_bib0034) 2001
Read (10.1016/j.inffus.2018.01.003_bib0011) 2012; 7619
Wang (10.1016/j.inffus.2018.01.003_bib0035) 2003
Gama (10.1016/j.inffus.2018.01.003_bib0005) 2014; 46
Aggarwal (10.1016/j.inffus.2018.01.003_bib0003) 2010
Woźniak (10.1016/j.inffus.2018.01.003_bib0013) 2014; 16
Kidera (10.1016/j.inffus.2018.01.003_bib0026) 2006
Freund (10.1016/j.inffus.2018.01.003_bib0015) 1996
Gama (10.1016/j.inffus.2018.01.003_bib0006) 2010
Zhao (10.1016/j.inffus.2018.01.003_bib0024) 2017; 38
Kolter (10.1016/j.inffus.2018.01.003_bib0033) 2007; 8
Kuncheva (10.1016/j.inffus.2018.01.003_bib0017) 2002; 3
Freund (10.1016/j.inffus.2018.01.003_bib0016) 1997; 55
Quinlan (10.1016/j.inffus.2018.01.003_bib0037) 1993
Harries (10.1016/j.inffus.2018.01.003_bib0051) 1999
Jaber (10.1016/j.inffus.2018.01.003_bib0045) 2013; 8227
Brzeziński (10.1016/j.inffus.2018.01.003_bib0041) 2014; 25
Littlestone (10.1016/j.inffus.2018.01.003_bib0044) 1994; 108
Freund (10.1016/j.inffus.2018.01.003_bib0046) 1997; 55
Elwell (10.1016/j.inffus.2018.01.003_bib0028) 2011; 22
Maloof (10.1016/j.inffus.2018.01.003_bib0039) 2000; 41
Widmer (10.1016/j.inffus.2018.01.003_bib0009) 1996; 23
Hulten (10.1016/j.inffus.2018.01.003_bib0038) 2001
Xingquan (10.1016/j.inffus.2018.01.003_bib0032) 2004
Ditzler (10.1016/j.inffus.2018.01.003_bib0001) 2015; 10
Carcillo (10.1016/j.inffus.2018.01.003_bib0031) 2018; 41
Brzeziński (10.1016/j.inffus.2018.01.003_bib0042) 2011; 6679
Aggarwal (Ed.) (10.1016/j.inffus.2018.01.003_bib0007) 2007
Oza (10.1016/j.inffus.2018.01.003_bib0018) 2001
Breiman (10.1016/j.inffus.2018.01.003_bib0014) 1996; 24
Nguyen (10.1016/j.inffus.2018.01.003_bib0008) 2014
Pocock (10.1016/j.inffus.2018.01.003_bib0021) 2010
Breiman (10.1016/j.inffus.2018.01.003_bib0050) 1984
Xu (10.1016/j.inffus.2018.01.003_bib0023) 2010
Schlimmer (10.1016/j.inffus.2018.01.003_bib0004) 1986
Pietruczuk (10.1016/j.inffus.2018.01.003_bib0043) 2017; 381
Bifet (10.1016/j.inffus.2018.01.003_bib0047) 2009
Krawczyk (10.1016/j.inffus.2018.01.003_bib0012) 2017; 37
Gama (10.1016/j.inffus.2018.01.003_bib0048) 2013; 90
Pelossof (10.1016/j.inffus.2018.01.003_bib0020) 2009
Maloof (10.1016/j.inffus.2018.01.003_bib0010) 2004; 154
Gama (10.1016/j.inffus.2018.01.003_bib0049) 2004; 3171
Woźniak (10.1016/j.inffus.2018.01.003_bib0030) 2016; 9714
References_xml – start-page: 97
  year: 2001
  end-page: 106
  ident: bib0038
  article-title: Mining time-changing data streams
  publication-title: Proceedings of the International Conference on Knowledge Discovery and Data Mining
– volume: 43
  start-page: 33
  year: 2018
  end-page: 46
  ident: bib0029
  article-title: Mode tracking using multiple data streams
  publication-title: Inf. Fusion
– year: 1999
  ident: bib0051
  article-title: Splice-2 comparative evaluation: electricity pricing
  publication-title: Technical Report
– volume: 38
  start-page: 43
  year: 2017
  end-page: 54
  ident: bib0024
  article-title: Multi-view learning overview: recent progress and new challenges
  publication-title: Inf. Fusion
– volume: 108
  start-page: 212
  year: 1994
  end-page: 261
  ident: bib0044
  article-title: The weighted majority algorithm
  publication-title: Inf. Comput.
– volume: 7619
  start-page: 313
  year: 2012
  end-page: 323
  ident: bib0011
  article-title: Batch-incremental versus instance-incremental learning in dynamic and evolving data
  publication-title: Advances in Intelligent Data Analysis XI
– volume: 11
  start-page: 3
  year: 2007
  end-page: 28
  ident: bib0027
  article-title: Boosting classifiers for drifting concepts
  publication-title: Intell. Data Anal.
– start-page: 105
  year: 2001
  end-page: 112
  ident: bib0018
  article-title: Online bagging and boosting
  publication-title: Artificial Intelligence and Statistics
– start-page: 226
  year: 2003
  end-page: 235
  ident: bib0035
  article-title: Mining concept-drifting data streams using ensemble classifiers
  publication-title: Proceedings of the International Conference on Knowledge Discovery and Data Mining (KDD)
– volume: 6679
  start-page: 155
  year: 2011
  end-page: 163
  ident: bib0042
  article-title: Accuracy updated ensemble for data streams with concept drift
  publication-title: Proceedings of the International Conference on Hybrid Artificial Intelligent Systems - Volume Part II
– volume: 41
  start-page: 27
  year: 2000
  end-page: 52
  ident: bib0039
  article-title: Selecting examples for partial memory learning
  publication-title: Mach. Learn.
– start-page: 377
  year: 2010
  end-page: 397
  ident: bib0003
  publication-title: Scientific Data Mining and Knowledge Discovery
– year: 2010
  ident: bib0006
  publication-title: Knowledge Discovery from Data Streams
– start-page: 205
  year: 2010
  end-page: 214
  ident: bib0021
  article-title: Online nonstationary boosting
  publication-title: Proceedings of the International Workshop Multiple Classifier Systems
– volume: 154
  start-page: 95
  year: 2004
  end-page: 126
  ident: bib0010
  article-title: Incremental learning with partial instance memory
  publication-title: Artif. Intell.
– volume: 3171
  start-page: 286
  year: 2004
  end-page: 295
  ident: bib0049
  article-title: Learning with drift detection
  publication-title: Proceedings of the Brazilian Symposium on Artificial Intelligence
– start-page: 1
  year: 2014
  end-page: 35
  ident: bib0008
  article-title: A survey on data stream clustering and classification
  publication-title: Knowl. Inf. Syst.
– volume: 46
  start-page: 44:1
  year: 2014
  end-page: 44:37
  ident: bib0005
  article-title: A survey on concept drift adaptation
  publication-title: ACM Comput. Surv.
– volume: 22
  start-page: 1517
  year: 2011
  end-page: 1531
  ident: bib0028
  article-title: Incremental learning of concept drift in nonstationary environments
  publication-title: IEEE Trans. Neural Netw.
– volume: 37
  start-page: 132
  year: 2017
  end-page: 156
  ident: bib0012
  article-title: Ensemble learning for data stream analysis: a survey
  publication-title: Inf. Fusion
– year: 2007
  ident: bib0007
  article-title: Data streams: Models and Algorithms
– volume: 24
  start-page: 123
  year: 1996
  end-page: 140
  ident: bib0014
  article-title: Bagging predictors
  publication-title: Mach. Learn.
– reference: S. Hettich, S. Bay, The UCI KDD archive, 1999, (University of California, Irvine, School of Information and Computer Sciences).
– start-page: 355
  year: 2010
  end-page: 362
  ident: bib0023
  article-title: An algorithm on multi-view adaboost
  publication-title: Proceedings of international conference on Neural information processing: theory and algorithms
– volume: 55
  start-page: 119
  year: 1997
  end-page: 139
  ident: bib0046
  article-title: A decision-theoretic generalization of on-line learning and an application to boosting
  publication-title: J. Comput. Syst. Sci.
– volume: 10
  start-page: 12
  year: 2015
  end-page: 25
  ident: bib0001
  article-title: Learning in nonstationary environments: a survey
  publication-title: IEEE Comput. Intell. Mag.
– volume: 16
  start-page: 3
  year: 2014
  end-page: 17
  ident: bib0013
  article-title: A survey of multiple classifier systems as hybrid systems
  publication-title: Inf. Fusion
– volume: 3
  start-page: 245
  year: 2002
  end-page: 258
  ident: bib0017
  article-title: An experimental study on diversity for bagging and boosting with linear classifiers
  publication-title: Inf. Fusion
– start-page: 148
  year: 1996
  end-page: 156
  ident: bib0015
  article-title: Experiments with a new boosting algorithm
  publication-title: Proceedings of the International Conference on Machine Learning
– volume: 8
  start-page: 2755
  year: 2007
  end-page: 2790
  ident: bib0033
  article-title: Dynamic weighted majority: an ensemble method for drifting concepts
  publication-title: J. Mach. Learn. Res.
– year: 1984
  ident: bib0050
  publication-title: Classification and Regression Trees
– start-page: 502
  year: 1986
  end-page: 507
  ident: bib0004
  article-title: Beyond incremental processing: tracking concept drift
  publication-title: Proceedings of the National Conference on Artificial Intelligence
– start-page: 305
  year: 2004
  end-page: 312
  ident: bib0032
  article-title: Dynamic classifier selection for effective mining from noisy data streams
  publication-title: Proceedings of the IEEE International Conference on Data Mining
– start-page: 1354
  year: 2009
  end-page: 1361
  ident: bib0020
  article-title: Online coordinate boosting
  publication-title: Proceedings of the IEEE International Conference on Computer Vision Workshops
– start-page: 1017
  year: 2003
  end-page: 1024
  ident: bib0022
  article-title: Floatboost learning for classification
  publication-title: Advances in Neural Information Processing Systems
– volume: 9714
  start-page: 497
  year: 2016
  end-page: 504
  ident: bib0030
  article-title: A first attempt on online data stream classifier using context
  publication-title: International Conference on Data Mining and Big Data
– start-page: 23
  year: 2009
  end-page: 37
  ident: bib0047
  article-title: Improving adaptive bagging methods for evolving data streams
  publication-title: Proceedings of the International Conference on Asian Conference Machine Learning
– volume: 8227
  start-page: 595
  year: 2013
  end-page: 604
  ident: bib0045
  article-title: A new on-line learning method for coping with recurring concepts: the adacc system
  publication-title: Neural Information Processing
– start-page: 377
  year: 2001
  end-page: 382
  ident: bib0034
  article-title: A streaming ensemble algorithm (sea) for large-scale classification
  publication-title: Proceedings of the International Conference on Knowledge Discovery and Data Mining (KDD)
– start-page: 359
  year: 2001
  end-page: 364
  ident: bib0019
  article-title: Experimental comparisons of online and batch versions of bagging and boosting
  publication-title: Proceedings of the International Conference Knowledge Discovery and Data Mining
– volume: 25
  start-page: 81
  year: 2014
  end-page: 94
  ident: bib0041
  article-title: Reacting to different types of concept drift: the accuracy updated ensemble algorithm
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 23
  start-page: 69
  year: 1996
  end-page: 101
  ident: bib0009
  article-title: Learning in the presence of concept drift and hidden contexts
  publication-title: Mach. Learn.
– start-page: 3421
  year: 2006
  end-page: 3427
  ident: bib0026
  article-title: An incremental learning algorithm of ensemble classifier systems
  publication-title: Proceedings of the International Joint Conference on Neural Networks
– start-page: 282
  year: 2004
  end-page: 292
  ident: bib0025
  article-title: Fast and light boosting for adaptive mining of data streams
  publication-title: Proceedings of the Pacific-Asia Conference on Knowledge Discovery and Data Mining
– year: 1993
  ident: bib0037
  publication-title: C4.5 Programs for Machine Learning
– volume: 381
  start-page: 46
  year: 2017
  end-page: 54
  ident: bib0043
  article-title: How to adjust an ensemble size in stream data mining?
  publication-title: Inf. Sci.
– reference: .
– reference: M. Lichman, UCI Machine Learning Repository, 2013. URL:
– volume: 34
  start-page: 18
  year: 2005
  end-page: 26
  ident: bib0002
  article-title: Mining data streams: a review
  publication-title: SIGMOD Record
– start-page: 404
  year: 2007
  end-page: 409
  ident: bib0036
  article-title: Tracking recurrent concept drift in streaming data using ensemble classifiers
  publication-title: Proceedings of the International Conference on Machine Learning and Applications
– volume: 55
  start-page: 119
  year: 1997
  end-page: 139
  ident: bib0016
  article-title: A decision-theoretic generalization of on-line learning and application to boosting
  publication-title: J. Comput. Syst. Sci.
– volume: 24
  start-page: 620
  year: 2013
  end-page: 634
  ident: bib0040
  article-title: Just-in-time classifiers for recurrent concepts
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 41
  start-page: 182
  year: 2018
  end-page: 194
  ident: bib0031
  article-title: Scarff: a scalable framework for streaming credit card fraud detection with spark
  publication-title: Inf. Fusion
– volume: 90
  start-page: 317
  year: 2013
  end-page: 346
  ident: bib0048
  article-title: On evaluating stream learning algorithms
  publication-title: Mach. Learn.
– volume: 9714
  start-page: 497
  year: 2016
  ident: 10.1016/j.inffus.2018.01.003_bib0030
  article-title: A first attempt on online data stream classifier using context
– volume: 381
  start-page: 46
  year: 2017
  ident: 10.1016/j.inffus.2018.01.003_bib0043
  article-title: How to adjust an ensemble size in stream data mining?
  publication-title: Inf. Sci.
  doi: 10.1016/j.ins.2016.10.028
– start-page: 148
  year: 1996
  ident: 10.1016/j.inffus.2018.01.003_bib0015
  article-title: Experiments with a new boosting algorithm
– ident: 10.1016/j.inffus.2018.01.003_bib0052
– volume: 16
  start-page: 3
  year: 2014
  ident: 10.1016/j.inffus.2018.01.003_bib0013
  article-title: A survey of multiple classifier systems as hybrid systems
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2013.04.006
– start-page: 226
  year: 2003
  ident: 10.1016/j.inffus.2018.01.003_bib0035
  article-title: Mining concept-drifting data streams using ensemble classifiers
– volume: 46
  start-page: 44:1
  issue: 4
  year: 2014
  ident: 10.1016/j.inffus.2018.01.003_bib0005
  article-title: A survey on concept drift adaptation
  publication-title: ACM Comput. Surv.
  doi: 10.1145/2523813
– year: 1993
  ident: 10.1016/j.inffus.2018.01.003_bib0037
– volume: 55
  start-page: 119
  year: 1997
  ident: 10.1016/j.inffus.2018.01.003_bib0046
  article-title: A decision-theoretic generalization of on-line learning and an application to boosting
  publication-title: J. Comput. Syst. Sci.
  doi: 10.1006/jcss.1997.1504
– volume: 22
  start-page: 1517
  issue: 10
  year: 2011
  ident: 10.1016/j.inffus.2018.01.003_bib0028
  article-title: Incremental learning of concept drift in nonstationary environments
  publication-title: IEEE Trans. Neural Netw.
  doi: 10.1109/TNN.2011.2160459
– volume: 8
  start-page: 2755
  year: 2007
  ident: 10.1016/j.inffus.2018.01.003_bib0033
  article-title: Dynamic weighted majority: an ensemble method for drifting concepts
  publication-title: J. Mach. Learn. Res.
– volume: 41
  start-page: 182
  year: 2018
  ident: 10.1016/j.inffus.2018.01.003_bib0031
  article-title: Scarff: a scalable framework for streaming credit card fraud detection with spark
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2017.09.005
– start-page: 205
  year: 2010
  ident: 10.1016/j.inffus.2018.01.003_bib0021
  article-title: Online nonstationary boosting
– year: 2007
  ident: 10.1016/j.inffus.2018.01.003_bib0007
– volume: 23
  start-page: 69
  issue: 1
  year: 1996
  ident: 10.1016/j.inffus.2018.01.003_bib0009
  article-title: Learning in the presence of concept drift and hidden contexts
  publication-title: Mach. Learn.
  doi: 10.1007/BF00116900
– volume: 108
  start-page: 212
  issue: 2
  year: 1994
  ident: 10.1016/j.inffus.2018.01.003_bib0044
  article-title: The weighted majority algorithm
  publication-title: Inf. Comput.
  doi: 10.1006/inco.1994.1009
– year: 2010
  ident: 10.1016/j.inffus.2018.01.003_bib0006
– volume: 37
  start-page: 132
  year: 2017
  ident: 10.1016/j.inffus.2018.01.003_bib0012
  article-title: Ensemble learning for data stream analysis: a survey
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2017.02.004
– year: 1984
  ident: 10.1016/j.inffus.2018.01.003_bib0050
– start-page: 105
  year: 2001
  ident: 10.1016/j.inffus.2018.01.003_bib0018
  article-title: Online bagging and boosting
– start-page: 359
  year: 2001
  ident: 10.1016/j.inffus.2018.01.003_bib0019
  article-title: Experimental comparisons of online and batch versions of bagging and boosting
– start-page: 404
  year: 2007
  ident: 10.1016/j.inffus.2018.01.003_bib0036
  article-title: Tracking recurrent concept drift in streaming data using ensemble classifiers
– volume: 90
  start-page: 317
  issue: 3
  year: 2013
  ident: 10.1016/j.inffus.2018.01.003_bib0048
  article-title: On evaluating stream learning algorithms
  publication-title: Mach. Learn.
  doi: 10.1007/s10994-012-5320-9
– volume: 6679
  start-page: 155
  year: 2011
  ident: 10.1016/j.inffus.2018.01.003_bib0042
  article-title: Accuracy updated ensemble for data streams with concept drift
– start-page: 305
  year: 2004
  ident: 10.1016/j.inffus.2018.01.003_bib0032
  article-title: Dynamic classifier selection for effective mining from noisy data streams
– start-page: 377
  year: 2010
  ident: 10.1016/j.inffus.2018.01.003_bib0003
– start-page: 355
  year: 2010
  ident: 10.1016/j.inffus.2018.01.003_bib0023
  article-title: An algorithm on multi-view adaboost
– start-page: 1017
  year: 2003
  ident: 10.1016/j.inffus.2018.01.003_bib0022
  article-title: Floatboost learning for classification
– year: 1999
  ident: 10.1016/j.inffus.2018.01.003_bib0051
  article-title: Splice-2 comparative evaluation: electricity pricing
– volume: 25
  start-page: 81
  issue: 1
  year: 2014
  ident: 10.1016/j.inffus.2018.01.003_bib0041
  article-title: Reacting to different types of concept drift: the accuracy updated ensemble algorithm
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2013.2251352
– volume: 34
  start-page: 18
  issue: 2
  year: 2005
  ident: 10.1016/j.inffus.2018.01.003_bib0002
  article-title: Mining data streams: a review
  publication-title: SIGMOD Record
  doi: 10.1145/1083784.1083789
– volume: 24
  start-page: 620
  issue: 4
  year: 2013
  ident: 10.1016/j.inffus.2018.01.003_bib0040
  article-title: Just-in-time classifiers for recurrent concepts
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2013.2239309
– volume: 154
  start-page: 95
  year: 2004
  ident: 10.1016/j.inffus.2018.01.003_bib0010
  article-title: Incremental learning with partial instance memory
  publication-title: Artif. Intell.
  doi: 10.1016/j.artint.2003.04.001
– volume: 38
  start-page: 43
  year: 2017
  ident: 10.1016/j.inffus.2018.01.003_bib0024
  article-title: Multi-view learning overview: recent progress and new challenges
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2017.02.007
– volume: 10
  start-page: 12
  year: 2015
  ident: 10.1016/j.inffus.2018.01.003_bib0001
  article-title: Learning in nonstationary environments: a survey
  publication-title: IEEE Comput. Intell. Mag.
  doi: 10.1109/MCI.2015.2471196
– start-page: 502
  year: 1986
  ident: 10.1016/j.inffus.2018.01.003_bib0004
  article-title: Beyond incremental processing: tracking concept drift
– volume: 3171
  start-page: 286
  year: 2004
  ident: 10.1016/j.inffus.2018.01.003_bib0049
  article-title: Learning with drift detection
– volume: 41
  start-page: 27
  year: 2000
  ident: 10.1016/j.inffus.2018.01.003_bib0039
  article-title: Selecting examples for partial memory learning
  publication-title: Mach. Learn.
  doi: 10.1023/A:1007661119649
– start-page: 97
  year: 2001
  ident: 10.1016/j.inffus.2018.01.003_bib0038
  article-title: Mining time-changing data streams
– start-page: 282
  year: 2004
  ident: 10.1016/j.inffus.2018.01.003_bib0025
  article-title: Fast and light boosting for adaptive mining of data streams
– volume: 3
  start-page: 245
  year: 2002
  ident: 10.1016/j.inffus.2018.01.003_bib0017
  article-title: An experimental study on diversity for bagging and boosting with linear classifiers
  publication-title: Inf. Fusion
  doi: 10.1016/S1566-2535(02)00093-3
– volume: 43
  start-page: 33
  year: 2018
  ident: 10.1016/j.inffus.2018.01.003_bib0029
  article-title: Mode tracking using multiple data streams
  publication-title: Inf. Fusion
  doi: 10.1016/j.inffus.2017.11.011
– volume: 24
  start-page: 123
  issue: 2
  year: 1996
  ident: 10.1016/j.inffus.2018.01.003_bib0014
  article-title: Bagging predictors
  publication-title: Mach. Learn.
  doi: 10.1007/BF00058655
– start-page: 1
  year: 2014
  ident: 10.1016/j.inffus.2018.01.003_bib0008
  article-title: A survey on data stream clustering and classification
  publication-title: Knowl. Inf. Syst.
– volume: 8227
  start-page: 595
  year: 2013
  ident: 10.1016/j.inffus.2018.01.003_bib0045
  article-title: A new on-line learning method for coping with recurring concepts: the adacc system
– volume: 55
  start-page: 119
  issue: 1
  year: 1997
  ident: 10.1016/j.inffus.2018.01.003_bib0016
  article-title: A decision-theoretic generalization of on-line learning and application to boosting
  publication-title: J. Comput. Syst. Sci.
  doi: 10.1006/jcss.1997.1504
– start-page: 377
  year: 2001
  ident: 10.1016/j.inffus.2018.01.003_bib0034
  article-title: A streaming ensemble algorithm (sea) for large-scale classification
– start-page: 1354
  year: 2009
  ident: 10.1016/j.inffus.2018.01.003_bib0020
  article-title: Online coordinate boosting
– start-page: 3421
  year: 2006
  ident: 10.1016/j.inffus.2018.01.003_bib0026
  article-title: An incremental learning algorithm of ensemble classifier systems
– volume: 7619
  start-page: 313
  year: 2012
  ident: 10.1016/j.inffus.2018.01.003_bib0011
  article-title: Batch-incremental versus instance-incremental learning in dynamic and evolving data
– volume: 11
  start-page: 3
  issue: 1
  year: 2007
  ident: 10.1016/j.inffus.2018.01.003_bib0027
  article-title: Boosting classifiers for drifting concepts
  publication-title: Intell. Data Anal.
  doi: 10.3233/IDA-2007-11102
– ident: 10.1016/j.inffus.2018.01.003_bib0053
– start-page: 23
  year: 2009
  ident: 10.1016/j.inffus.2018.01.003_bib0047
  article-title: Improving adaptive bagging methods for evolving data streams
SSID ssj0017031
Score 2.4605455
Snippet •The IBS ensemble bases on iteratively applying boosting to learn from data stream.•IBS adjusts to new concept by gathering knowledge according to its current...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 66
SubjectTerms Boosting algorithms
Data stream classification
Ensemble learning
Incremental learning
Title An iterative boosting-based ensemble for streaming data classification
URI https://dx.doi.org/10.1016/j.inffus.2018.01.003
Volume 45
WOSCitedRecordID wos000447084900006&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: PRVESC
  databaseName: ScienceDirect database
  customDbUrl:
  eissn: 1872-6305
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0017031
  issn: 1566-2535
  databaseCode: AIEXJ
  dateStart: 20000701
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swEBdbu4ftYeyTdeuGH_ZmNFzJluTHrLRsYS2DhZE3Y30YEha51Enpn987y3YcMvYFezFGWIms-_l0J_3ujpD3vJTaMuWoSXVGU6YN1cwpmglbOZE741q2xfcv8vJSzef5145u27TlBKT36vY2v_qvooY2EDaGzv6FuIcfhQa4B6HDFcQO1z8S_MTHIVVyy0uv6waJzRRXKxuDz-pWGCuF5EIMEylXuFWANNHYoB2NxKGtrJY9zX0IcYyrTTM6uf-IrGy_iKcbvwh-_7Ruj9553XG26-3BB0DOrQN74AI89DK2NfJNVvV45wGDnXZ2HvZDYoIGFYKyLOQg-eBCm5KMCp5kY7WbZiO9KcRoBQ41ffZ0e9hmWKJDAu-KrDzVZlxN-HYtGxiG33AcOAywN-FBPr9PDpnMclB8h5PPZ_PpcNSECfzbpLrduPv4ypYEuP9fP7dfRjbJ7Al53DkT0SSA4Cm55_wz8uhiyMTbPCfnEx8NcIh24RD1cIhAvtEAhwjhEO3C4QWZnZ_NTj_RrnYGNeAErqkwonSJNpJZsBCtrtI0T7KSpbqqlMYUQSV8jRhYrTSXVaqN0FiezFnBEq74S3Lga-9ekQjst1xJLu2JlmC8SOVSraFrxlleKiuOCO8npDBdXnksb_Kj6AmEyyJMY4HTWCQnmI_2iNCh11XIq_Kb52U_10VnGwabrwB4_LLn63_u-YY83ML-mBysrzfuLXlgbtaL5vpdh6M72bmMNQ
linkProvider Elsevier
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=An+iterative+boosting-based+ensemble+for+streaming+data+classification&rft.jtitle=Information+fusion&rft.au=Bertini+Junior%2C+Jo%C3%A3o+Roberto&rft.au=Nicoletti%2C+Maria+do+Carmo&rft.date=2019-01-01&rft.pub=Elsevier+B.V&rft.issn=1566-2535&rft.eissn=1872-6305&rft.volume=45&rft.spage=66&rft.epage=78&rft_id=info:doi/10.1016%2Fj.inffus.2018.01.003&rft.externalDocID=S156625351630183X
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1566-2535&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1566-2535&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1566-2535&client=summon