A deep contractive autoencoder for solving multiclass classification problems

Contractive auto encoder (CAE) is on of the most robust variant of standard Auto Encoder (AE). The major drawback associated with the conventional CAE is its higher reconstruction error during encoding and decoding process of input features to the network. This drawback in the operational procedure...

Full description

Saved in:
Bibliographic Details
Published in:Evolutionary intelligence Vol. 14; no. 4; pp. 1619 - 1633
Main Authors: Aamir, Muhammad, Mohd Nawi, Nazri, Wahid, Fazli, Mahdin, Hairulnizam
Format: Journal Article
Language:English
Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.12.2021
Springer Nature B.V
Subjects:
ISSN:1864-5909, 1864-5917
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Contractive auto encoder (CAE) is on of the most robust variant of standard Auto Encoder (AE). The major drawback associated with the conventional CAE is its higher reconstruction error during encoding and decoding process of input features to the network. This drawback in the operational procedure of CAE leads to its incapability of going into finer details present in the input features by missing the information worth consideration. Resultantly, the features extracted by CAE lack the true representation of all the input features and the classifier fails in solving classification problems efficiently. In this work, an improved variant of CAE is proposed based on layered architecture following feed forward mechanism named as deep CAE. In the proposed architecture, the normal CAEs are arranged in layers and inside each layer, the process of encoding and decoding take place. The features obtained from the previous CAE are given as inputs to the next CAE. Each CAE in all layers are responsible for reducing the reconstruction error thus resulting in obtaining the informative features. The feature set obtained from the last CAE is given as input to the softmax classifier for classification. The performance and efficiency of the proposed model has been tested on five MNIST variant-datasets. The results have been compared with standard SAE, DAE, RBM, SCAE, ScatNet and PCANet in term of training error, testing error and execution time. The results revealed that the proposed model outperform the aforementioned models.
AbstractList Contractive auto encoder (CAE) is on of the most robust variant of standard Auto Encoder (AE). The major drawback associated with the conventional CAE is its higher reconstruction error during encoding and decoding process of input features to the network. This drawback in the operational procedure of CAE leads to its incapability of going into finer details present in the input features by missing the information worth consideration. Resultantly, the features extracted by CAE lack the true representation of all the input features and the classifier fails in solving classification problems efficiently. In this work, an improved variant of CAE is proposed based on layered architecture following feed forward mechanism named as deep CAE. In the proposed architecture, the normal CAEs are arranged in layers and inside each layer, the process of encoding and decoding take place. The features obtained from the previous CAE are given as inputs to the next CAE. Each CAE in all layers are responsible for reducing the reconstruction error thus resulting in obtaining the informative features. The feature set obtained from the last CAE is given as input to the softmax classifier for classification. The performance and efficiency of the proposed model has been tested on five MNIST variant-datasets. The results have been compared with standard SAE, DAE, RBM, SCAE, ScatNet and PCANet in term of training error, testing error and execution time. The results revealed that the proposed model outperform the aforementioned models.
Author Mohd Nawi, Nazri
Mahdin, Hairulnizam
Wahid, Fazli
Aamir, Muhammad
Author_xml – sequence: 1
  givenname: Muhammad
  surname: Aamir
  fullname: Aamir, Muhammad
  organization: Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn
– sequence: 2
  givenname: Nazri
  surname: Mohd Nawi
  fullname: Mohd Nawi, Nazri
  organization: Soft Computing and Data Mining Center, Universiti Tun Hussein Onn
– sequence: 3
  givenname: Fazli
  surname: Wahid
  fullname: Wahid, Fazli
  email: fazli.wahid@cs.uol.edu.pk
  organization: Faculty of Computer Science and Information Technology, The University of Lahore, Gujrat Campus
– sequence: 4
  givenname: Hairulnizam
  surname: Mahdin
  fullname: Mahdin, Hairulnizam
  organization: Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn
BookMark eNp9kM1OAyEURompiW31BVyRuB69MAwMy6bxL6lxo2vCMNDQTKHCTBPf3rE1mrjo5nIX3-GDM0OTEINF6JrALQEQd5lQ4FUBFAoARlnBz9CU1JwVlSRi8ruDvECznDcAnIJgU_SywK21O2xi6JM2vd9brIc-2mBiaxN2MeEcu70Pa7wdut6bTueMD9M7b3TvY8C7FJvObvMlOne6y_bq55yj94f7t-VTsXp9fF4uVoUpieyLFipekYZoZsE1IETLwZaikW1dSi3rxkhLBBFGaEKoLR11jBPJTFu1jdO6nKOb471j8cdgc682cUhhrFS0qitGJK_FmKLHlEkx52Sd2iW_1elTEVDf2tRRmxq1qYM2xUeo_gcZ3x9-Ofrx3Wm0PKJ57Alrm_5edYL6AjKkhLM
CitedBy_id crossref_primary_10_1007_s10661_024_13101_3
crossref_primary_10_1109_LSP_2021_3077853
crossref_primary_10_3390_e24010036
crossref_primary_10_1016_j_asoc_2024_111378
crossref_primary_10_1109_TGRS_2025_3583982
crossref_primary_10_3389_fdata_2024_1462745
crossref_primary_10_3390_electronics10212667
crossref_primary_10_1109_ACCESS_2023_3321800
crossref_primary_10_1007_s13369_021_05674_9
crossref_primary_10_1109_ACCESS_2020_3015206
Cites_doi 10.1016/j.future.2016.06.005
10.1016/j.neucom.2015.07.058
10.1109/TNNLS.2015.2479223
10.1109/TNNLS.2014.2310059
10.3390/mi9080411
10.1007/s10589-014-9678-4
10.1016/j.neucom.2015.07.119
10.3390/s18114024
10.5391/IJFIS.2020.20.1.8
10.1016/j.imavis.2017.01.005
10.1016/j.neucom.2015.02.023
10.1109/TIP.2015.2487860
10.1109/TIE.2016.2586442
10.1109/TIP.2015.2475625
10.1016/j.sigpro.2015.01.001
10.18517/ijaseit.7.5.2972
10.3390/rs10060877
10.1609/aaai.v30i1.9952
10.1109/ICASSP.2014.6854900
10.1145/1273496.1273556
10.1007/978-0-387-78189-1_8
10.1145/2502081.2502112
10.1007/978-3-319-72550-5_2
10.1109/ISPDC.2016.60
10.1007/s12065-018-0165-1
10.1007/978-3-642-23783-6_41
10.1109/IJCNN.2015.7280669
10.1109/CISP.2015.7407967
10.1007/978-3-642-17622-7_18
ContentType Journal Article
Copyright Springer-Verlag GmbH Germany, part of Springer Nature 2020
Springer-Verlag GmbH Germany, part of Springer Nature 2020.
Copyright_xml – notice: Springer-Verlag GmbH Germany, part of Springer Nature 2020
– notice: Springer-Verlag GmbH Germany, part of Springer Nature 2020.
DBID AAYXX
CITATION
JQ2
DOI 10.1007/s12065-020-00424-6
DatabaseName CrossRef
ProQuest Computer Science Collection
DatabaseTitle CrossRef
ProQuest Computer Science Collection
DatabaseTitleList ProQuest Computer Science Collection

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1864-5917
EndPage 1633
ExternalDocumentID 10_1007_s12065_020_00424_6
GroupedDBID -5B
-5G
-BR
-EM
-Y2
-~C
.86
06D
0R~
0VY
1N0
203
29G
29~
2JN
2JY
2KG
2VQ
2~H
30V
4.4
406
408
409
40D
5GY
5VS
67Z
6NX
875
8TC
8UJ
96X
AAAVM
AABHQ
AACDK
AAHNG
AAIAL
AAJBT
AAJKR
AANZL
AARHV
AARTL
AASML
AATNV
AATVU
AAUYE
AAWCG
AAYIU
AAYQN
AAYTO
AAYZH
ABAKF
ABBXA
ABDZT
ABECU
ABFTD
ABFTV
ABHQN
ABJNI
ABJOX
ABKCH
ABMNI
ABMQK
ABQBU
ABSXP
ABTEG
ABTHY
ABTKH
ABTMW
ABULA
ABWNU
ABXPI
ACAOD
ACDTI
ACGFS
ACHSB
ACKNC
ACMDZ
ACMLO
ACOKC
ACOMO
ACPIV
ACZOJ
ADHHG
ADHIR
ADINQ
ADKNI
ADKPE
ADRFC
ADTPH
ADURQ
ADYFF
ADZKW
AEBTG
AEFQL
AEGAL
AEGNC
AEJHL
AEJRE
AEKMD
AEMSY
AEOHA
AEPYU
AESKC
AETLH
AEVLU
AEXYK
AFBBN
AFGCZ
AFLOW
AFQWF
AFWTZ
AFZKB
AGAYW
AGDGC
AGJBK
AGMZJ
AGQEE
AGQMX
AGRTI
AGWZB
AGYKE
AHAVH
AHBYD
AHSBF
AHYZX
AIAKS
AIGIU
AIIXL
AILAN
AITGF
AJBLW
AJRNO
AJZVZ
ALFXC
ALMA_UNASSIGNED_HOLDINGS
ALWAN
AMKLP
AMXSW
AMYLF
AMYQR
ANMIH
AOCGG
AUKKA
AXYYD
AYJHY
B-.
BA0
BDATZ
BGNMA
CAG
COF
CS3
CSCUP
DDRTE
DNIVK
DPUIP
EBLON
EBS
EIOEI
EJD
ESBYG
F5P
FERAY
FFXSO
FIGPU
FINBP
FNLPD
FRRFC
FSGXE
FWDCC
GGCAI
GGRSB
GJIRD
GNWQR
GQ6
GQ7
GQ8
GXS
H13
HF~
HG5
HG6
HLICF
HMJXF
HQYDN
HRMNR
HZ~
I0C
IJ-
IKXTQ
IWAJR
IXC
IXD
IZIGR
IZQ
I~X
J-C
J0Z
JBSCW
JCJTX
JZLTJ
KOV
LLZTM
M4Y
MA-
NPVJJ
NQJWS
NU0
O9-
O93
O9J
OAM
P2P
P9P
PT4
QOS
R89
RLLFE
ROL
RPX
RSV
S16
S1Z
S27
S3B
SAP
SDH
SEG
SHX
SISQX
SJYHP
SNE
SNPRN
SNX
SOHCF
SOJ
SPISZ
SRMVM
SSLCW
STPWE
T13
TSG
TSK
U2A
UG4
UOJIU
UTJUX
UZXMN
VC2
VFIZW
W48
WK8
YLTOR
Z45
ZMTXR
~A9
AAPKM
AAYXX
ABBRH
ABDBE
ABFSG
ABJCF
ABRTQ
ACSTC
ADKFA
AEZWR
AFDZB
AFFHD
AFHIU
AFKRA
AFOHR
AHPBZ
AHWEU
AIXLP
ARAPS
ATHPR
AYFIA
AZQEC
BENPR
BGLVJ
CCPQU
CITATION
DWQXO
GNUQQ
HCIFZ
K7-
M2P
M7S
PHGZM
PHGZT
PQGLB
PTHSS
JQ2
ID FETCH-LOGICAL-c319t-d05651b1a4e0fb077d60e37b9d839a98bc9e1717c7a112e3f2f46194cd5dbfaa3
IEDL.DBID RSV
ISICitedReferencesCount 17
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000539503900001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1864-5909
IngestDate Wed Sep 17 23:58:12 EDT 2025
Sat Nov 29 06:12:13 EST 2025
Tue Nov 18 22:18:52 EST 2025
Fri Feb 21 02:47:36 EST 2025
IsPeerReviewed true
IsScholarly true
Issue 4
Keywords Deep auto encoder
Contractive auto encoder
Feature reduction
MNIST variants
Classification
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c319t-d05651b1a4e0fb077d60e37b9d839a98bc9e1717c7a112e3f2f46194cd5dbfaa3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
PQID 2585419687
PQPubID 2043920
PageCount 15
ParticipantIDs proquest_journals_2585419687
crossref_primary_10_1007_s12065_020_00424_6
crossref_citationtrail_10_1007_s12065_020_00424_6
springer_journals_10_1007_s12065_020_00424_6
PublicationCentury 2000
PublicationDate 2021-12-01
PublicationDateYYYYMMDD 2021-12-01
PublicationDate_xml – month: 12
  year: 2021
  text: 2021-12-01
  day: 01
PublicationDecade 2020
PublicationPlace Berlin/Heidelberg
PublicationPlace_xml – name: Berlin/Heidelberg
– name: Heidelberg
PublicationTitle Evolutionary intelligence
PublicationTitleAbbrev Evol. Intel
PublicationYear 2021
Publisher Springer Berlin Heidelberg
Springer Nature B.V
Publisher_xml – name: Springer Berlin Heidelberg
– name: Springer Nature B.V
References Snášel, Nowaková, Xhafa, Barolli (CR22) 2017; 67
Vincent, Larochelle, Lajoie, Bengio, Manzagol (CR12) 2010; 11
CR19
CR18
Hosseini-Asl, Zurada, Nasraoui (CR2) 2016; 27
CR39
Jae-Neung Lee, Kwak (CR43) 2018; 9
CR16
CR15
CR37
CR14
CR36
CR13
Hong, Yu, Wan, Tao, Wang (CR9) 2015; 24
CR11
CR10
CR32
CR31
CR30
Wahid, Ghazali, Fayaz, Shah (CR25) 2017; 8
Aamir, Mohd Nawi, Mahdin, Naseem, Zulqarnain (CR1) 2020; 20
CR3
Jia, Sun, Gao, Song, Shi (CR4) 2015; 160
CR6
Liu, Ma, Tao, You (CR7) 2016; 187
CR29
Sankaran, Vatsa, Singh, Majumdar (CR33) 2017; 60
Chan, Jia, Gao, Lu, Zeng, Ma (CR34) 2015; 24
Lee, Byeon, Kwak (CR44) 2018; 9
CR28
CR27
Zhang, Ding, Shi (CR5) 2016; 171
CR24
Biglari, Ebadian (CR42) 2015; 60
Wahid, Ismail, Ghazali, Aamir (CR20) 2019; 13
CR23
Zi, Xie, Jiang (CR35) 2018; 10
Lee, Byeon, Pan, Kwak (CR38) 2018
Liu, Feng, Zhou (CR17) 2016; 120
Soon, Khaw, Chuah, Kanesan (CR40) 2018; 99
Chorowski, Zurada (CR8) 2015; 26
Aamir, Mohd Nawi, Wahid, Mahdin (CR26) 2019; 10
Mohd Nawi, Hamzah, Hamid, Rehman, Aamir, Azhar (CR21) 2017; 7
Liao, Jin, Pavel (CR41) 2016; 63
V Snášel (424_CR22) 2017; 67
424_CR6
N Zhang (424_CR5) 2016; 171
424_CR3
N Mohd Nawi (424_CR21) 2017; 7
M Aamir (424_CR1) 2020; 20
F Wahid (424_CR25) 2017; 8
YHB Jae-Neung Lee (424_CR43) 2018; 9
424_CR19
F Biglari (424_CR42) 2015; 60
P Vincent (424_CR12) 2010; 11
424_CR24
424_CR23
424_CR29
C Hong (424_CR9) 2015; 24
424_CR28
424_CR27
A Sankaran (424_CR33) 2017; 60
FC Soon (424_CR40) 2018; 99
E Hosseini-Asl (424_CR2) 2016; 27
JN Lee (424_CR38) 2018
L Liao (424_CR41) 2016; 63
J Chorowski (424_CR8) 2015; 26
Y Zi (424_CR35) 2018; 10
K Jia (424_CR4) 2015; 160
W Liu (424_CR7) 2016; 187
424_CR14
Y Liu (424_CR17) 2016; 120
424_CR36
424_CR13
M Aamir (424_CR26) 2019; 10
424_CR11
424_CR18
424_CR39
424_CR16
F Wahid (424_CR20) 2019; 13
424_CR15
424_CR37
424_CR10
424_CR32
TH Chan (424_CR34) 2015; 24
424_CR31
424_CR30
JN Lee (424_CR44) 2018; 9
References_xml – volume: 67
  start-page: 286
  year: 2017
  end-page: 296
  ident: CR22
  article-title: Geometrical and topological approaches to Big Data
  publication-title: Future Gener Comput Syst
  doi: 10.1016/j.future.2016.06.005
– volume: 99
  start-page: 1
  year: 2018
  end-page: 11
  ident: CR40
  article-title: PCANet-Based Convolutional Neural Network Architecture For a Vehicle Model Recognition System
  publication-title: IEEE Trans Intell Transp Syst
– ident: CR18
– volume: 171
  start-page: 1066
  year: 2016
  end-page: 1074
  ident: CR5
  article-title: Denoising Laplacian multi-layer extreme learning machine
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.07.058
– volume: 27
  start-page: 2486
  issue: 12
  year: 2016
  end-page: 2498
  ident: CR2
  article-title: Deep learning of part-based representation of data using sparse autoencoders with nonnegativity constraints
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2015.2479223
– ident: CR14
– ident: CR39
– ident: CR16
– ident: CR37
– ident: CR30
– volume: 26
  start-page: 62
  issue: 1
  year: 2015
  end-page: 69
  ident: CR8
  article-title: Learning understandable neural networks with nonnegative weight constraints
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2014.2310059
– volume: 8
  start-page: 9
  year: 2017
  ident: CR25
  article-title: Statistical features based approach (SFBA) for hourly energy consumption prediction using neural network
  publication-title: Networks
– ident: CR10
– volume: 9
  start-page: 411
  issue: 8
  year: 2018
  ident: CR44
  article-title: Design of ensemble stacked auto-encoder for classification of horse gaits with MEMS inertial sensor technology
  publication-title: Micromachines
  doi: 10.3390/mi9080411
– ident: CR6
– ident: CR29
– volume: 60
  start-page: 413
  issue: 2
  year: 2015
  end-page: 422
  ident: CR42
  article-title: Limited memory BFGS method based on a high-order tensor model
  publication-title: Comput Optim Appl
  doi: 10.1007/s10589-014-9678-4
– volume: 187
  start-page: 59
  year: 2016
  end-page: 65
  ident: CR7
  article-title: HSAE: a Hessian regularized sparse auto-encoders
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.07.119
– volume: 10
  start-page: 416
  issue: 8
  year: 2019
  end-page: 426
  ident: CR26
  article-title: An efficient normalized restricted Boltzmann machine for solving multiclassclassification problems
  publication-title: Int J Adv Comput Sci Appl
– year: 2018
  ident: CR38
  article-title: An EigenECG network approach based on PCANet for personal identification from ECG Signal
  publication-title: Sensors
  doi: 10.3390/s18114024
– ident: CR27
– ident: CR23
– volume: 20
  start-page: 8
  issue: 1
  year: 2020
  end-page: 16
  ident: CR1
  article-title: Auto-encoder variants for solving handwritten digits classification problem
  publication-title: Int J Fuzzy Logic Intell Syst
  doi: 10.5391/IJFIS.2020.20.1.8
– ident: CR19
– volume: 60
  start-page: 64
  year: 2017
  end-page: 74
  ident: CR33
  article-title: Group sparse autoencoder
  publication-title: Image Vis Comput
  doi: 10.1016/j.imavis.2017.01.005
– volume: 160
  start-page: 250
  year: 2015
  end-page: 260
  ident: CR4
  article-title: Laplacian auto-encoders: an explicit learning of nonlinear data manifold
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.02.023
– ident: CR3
– ident: CR15
– ident: CR31
– volume: 24
  start-page: 5659
  issue: 12
  year: 2015
  end-page: 5670
  ident: CR9
  article-title: Multimodal deep autoencoder for human pose recovery
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2015.2487860
– ident: CR13
– ident: CR11
– volume: 63
  start-page: 7076
  issue: 11
  year: 2016
  end-page: 7083
  ident: CR41
  article-title: Enhanced restricted Boltzmann machine with prognosability regularization for prognostics and health assessment
  publication-title: IEEE Trans Industr Electron
  doi: 10.1109/TIE.2016.2586442
– volume: 11
  start-page: 3371
  year: 2010
  end-page: 3408
  ident: CR12
  article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion
  publication-title: J Mach Learn Res
– volume: 24
  start-page: 5017
  issue: 12
  year: 2015
  end-page: 5032
  ident: CR34
  article-title: PCANet: A simple deep learning baseline for image classification?
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2015.2475625
– ident: CR32
– volume: 13
  start-page: 5904
  issue: 12
  year: 2019
  end-page: 5927
  ident: CR20
  article-title: An efficient artificial intelligence hybrid approach for energy management in intelligent buildings
  publication-title: KSII Trans Internet Inf Syst
– ident: CR36
– volume: 120
  start-page: 761
  year: 2016
  end-page: 766
  ident: CR17
  article-title: Multimodal video classification with stacked contractive autoencoders
  publication-title: Sig Process
  doi: 10.1016/j.sigpro.2015.01.001
– volume: 9
  start-page: 411
  issue: 4
  year: 2018
  ident: CR43
  article-title: An EigenECG network approach based on PCANet for personal identification from ECG signal
  publication-title: Micromachines
– volume: 7
  start-page: 1693
  issue: 5
  year: 2017
  end-page: 1700
  ident: CR21
  article-title: An optimized back propagation learning algorithm with adaptive learning rate
  publication-title: Int J Adv Sci Eng Inf Technol
  doi: 10.18517/ijaseit.7.5.2972
– ident: CR28
– volume: 10
  start-page: 877
  issue: 6
  year: 2018
  ident: CR35
  article-title: A cloud detection method for Landsat 8 images based on PCANet
  publication-title: Remote Sens
  doi: 10.3390/rs10060877
– ident: CR24
– ident: 424_CR10
  doi: 10.1609/aaai.v30i1.9952
– volume: 171
  start-page: 1066
  year: 2016
  ident: 424_CR5
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.07.058
– ident: 424_CR18
– volume: 99
  start-page: 1
  year: 2018
  ident: 424_CR40
  publication-title: IEEE Trans Intell Transp Syst
– volume: 160
  start-page: 250
  year: 2015
  ident: 424_CR4
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.02.023
– volume: 67
  start-page: 286
  year: 2017
  ident: 424_CR22
  publication-title: Future Gener Comput Syst
  doi: 10.1016/j.future.2016.06.005
– ident: 424_CR39
– ident: 424_CR13
  doi: 10.1109/ICASSP.2014.6854900
– ident: 424_CR28
  doi: 10.1145/1273496.1273556
– volume: 27
  start-page: 2486
  issue: 12
  year: 2016
  ident: 424_CR2
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2015.2479223
– ident: 424_CR24
  doi: 10.1007/978-0-387-78189-1_8
– ident: 424_CR15
  doi: 10.1145/2502081.2502112
– ident: 424_CR27
  doi: 10.1007/978-3-319-72550-5_2
– ident: 424_CR14
– volume: 7
  start-page: 1693
  issue: 5
  year: 2017
  ident: 424_CR21
  publication-title: Int J Adv Sci Eng Inf Technol
  doi: 10.18517/ijaseit.7.5.2972
– ident: 424_CR31
– ident: 424_CR16
– volume: 8
  start-page: 9
  year: 2017
  ident: 424_CR25
  publication-title: Networks
– ident: 424_CR37
  doi: 10.1109/ISPDC.2016.60
– volume: 10
  start-page: 877
  issue: 6
  year: 2018
  ident: 424_CR35
  publication-title: Remote Sens
  doi: 10.3390/rs10060877
– volume: 120
  start-page: 761
  year: 2016
  ident: 424_CR17
  publication-title: Sig Process
  doi: 10.1016/j.sigpro.2015.01.001
– volume: 187
  start-page: 59
  year: 2016
  ident: 424_CR7
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2015.07.119
– ident: 424_CR6
– volume: 9
  start-page: 411
  issue: 8
  year: 2018
  ident: 424_CR44
  publication-title: Micromachines
  doi: 10.3390/mi9080411
– volume: 11
  start-page: 3371
  year: 2010
  ident: 424_CR12
  publication-title: J Mach Learn Res
– volume: 9
  start-page: 411
  issue: 4
  year: 2018
  ident: 424_CR43
  publication-title: Micromachines
– volume: 13
  start-page: 5904
  issue: 12
  year: 2019
  ident: 424_CR20
  publication-title: KSII Trans Internet Inf Syst
– volume: 20
  start-page: 8
  issue: 1
  year: 2020
  ident: 424_CR1
  publication-title: Int J Fuzzy Logic Intell Syst
  doi: 10.5391/IJFIS.2020.20.1.8
– volume: 26
  start-page: 62
  issue: 1
  year: 2015
  ident: 424_CR8
  publication-title: IEEE Trans Neural Netw Learn Syst
  doi: 10.1109/TNNLS.2014.2310059
– ident: 424_CR23
  doi: 10.1007/s12065-018-0165-1
– volume: 24
  start-page: 5659
  issue: 12
  year: 2015
  ident: 424_CR9
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2015.2487860
– ident: 424_CR3
– volume: 60
  start-page: 64
  year: 2017
  ident: 424_CR33
  publication-title: Image Vis Comput
  doi: 10.1016/j.imavis.2017.01.005
– ident: 424_CR11
  doi: 10.1007/978-3-642-23783-6_41
– ident: 424_CR36
  doi: 10.1109/IJCNN.2015.7280669
– ident: 424_CR32
  doi: 10.1109/CISP.2015.7407967
– volume: 24
  start-page: 5017
  issue: 12
  year: 2015
  ident: 424_CR34
  publication-title: IEEE Trans Image Process
  doi: 10.1109/TIP.2015.2475625
– year: 2018
  ident: 424_CR38
  publication-title: Sensors
  doi: 10.3390/s18114024
– volume: 60
  start-page: 413
  issue: 2
  year: 2015
  ident: 424_CR42
  publication-title: Comput Optim Appl
  doi: 10.1007/s10589-014-9678-4
– ident: 424_CR19
  doi: 10.1007/978-3-642-17622-7_18
– ident: 424_CR29
– ident: 424_CR30
– volume: 63
  start-page: 7076
  issue: 11
  year: 2016
  ident: 424_CR41
  publication-title: IEEE Trans Industr Electron
  doi: 10.1109/TIE.2016.2586442
– volume: 10
  start-page: 416
  issue: 8
  year: 2019
  ident: 424_CR26
  publication-title: Int J Adv Comput Sci Appl
SSID ssj0062074
Score 2.3110058
Snippet Contractive auto encoder (CAE) is on of the most robust variant of standard Auto Encoder (AE). The major drawback associated with the conventional CAE is its...
SourceID proquest
crossref
springer
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 1619
SubjectTerms Applications of Mathematics
Artificial Intelligence
Bioinformatics
Classification
Classifiers
Coders
Control
Engineering
Errors
Feature extraction
Mathematical and Computational Engineering
Mechatronics
Model testing
Reconstruction
Research Paper
Robotics
Statistical Physics and Dynamical Systems
Title A deep contractive autoencoder for solving multiclass classification problems
URI https://link.springer.com/article/10.1007/s12065-020-00424-6
https://www.proquest.com/docview/2585419687
Volume 14
WOSCitedRecordID wos000539503900001&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: PRVAVX
  databaseName: SpringerLink
  customDbUrl:
  eissn: 1864-5917
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0062074
  issn: 1864-5909
  databaseCode: RSV
  dateStart: 20080301
  isFulltext: true
  titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22
  providerName: Springer Nature
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LSwMxEB60etCD1apYrZKDNw3sezfHIhYvFvFFb8tuMgFBaulu_f1O0qyrooJe9pIHyySZ-b7MZAbgVOjE0I7CILeAR5FCLlAQS0EtI9QEQZRni02k43E2mYgb9yisaqLdG5ek1dTtY7eAzCU3dMf663iyCmtk7jJTsOH27rHRv0ng2dzLfpZEPBaecE9lvp_jszlqMeYXt6i1NqPu__5zG7YcumTD5XbYgRWc9qDbVG5g7iD3YPNDGsJduB4yhThjNmy9sAqQFYv6xeS4VDSMcC2jLWquHpgNQJQGcjP7NZFGdnGZK01T7cHD6PL-4oq7Mgtc0vmruSIMFPulX0To6dJLU5V4GKalUASeCpGVUqBPrE-mBYEzDHWgI3P3IVWsSl0U4T50pi9TPAAWa4UiMK5dYmElMT8USYYykzHGZaizPviNtHPpcpCbUhjPeZs92UgvJ-nlVnp50oez9zGzZQaOX3sPmkXM3Wms8oA4UUSqJkv7cN4sWtv882yHf-t-BBuBCXmx0S4D6NTzBR7Dunytn6r5id2lbymj4DM
linkProvider Springer Nature
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3dS8MwED90CuqD06k4nZoH37TQdv3K4xDHxG2ITtlbaZMLCLKNtfPv95K1VkUFfelLPiiX5O53ucvvAM65CrTbkWjk5lqeJ9HiyMlLQSU8VARBpG2KTYTDYTQe87viUVhWZruXIUmjqavHbi6ZS0u7OyZeZwWrsOaRxdKM-fcPT6X-DVzbcC87UeBZPrd58VTm-zk-m6MKY34Jixpr063_7z93YLtAl6yz3A67sIKTBtTLyg2sOMgN2PpAQ7gHgw6TiDNm0tYTowBZssinmuNS0jDCtYy2qL56YCYBUWjIzcxXZxqZxWVFaZpsHx6716OrnlWUWbAEnb_ckoSBfCd1Eg9tldphKAMb22HKJYGnhEep4OiQ1yfChMAZtpWrPH33IaQvU5Uk7QOoTaYTPATmK4nc1aFd8sJS8vyQBxGKSPjop20VNcEppR2LgoNcl8J4iSv2ZC29mKQXG-nFQRMu3sfMlgwcv_ZulYsYF6cxi13yiTxSNVHYhMty0armn2c7-lv3M9jojQb9uH8zvD2GTVenv5jMlxbU8vkCT2BdvObP2fzU7Ng3tMLjFw
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LSwMxEB60iujBalWsVs3Bmy7dR_aRY1GLopaCD3pbsskEBGlLu_X3m6S7bhUVxMteNgnL5PV9OzPfAJwyFRnawQ1y8x1KJToMmWYpqARFpSGIdG2xibjXSwYD1l_I4rfR7qVLcp7TYFSahnl7LFW7Snzz9dXpGOpjfXdOtAwr1ATSG77-8FyexZHvWh1mL4moEzKXFWkz34_x-Wqq8OYXF6m9ebr1_3_zFmwWqJN05stkG5Zw2IB6WdGBFBu8ARsL8oQ7cN8hEnFMbDg7twcj4bN8ZLQvpe6m8S7RS9f8kiA2MFEYKE7s00Qg2UknRcma6S48da8eL66dovyCI_S-zB2psVHoZR6n6KrMjWMZuRjEGZMaVHGWZIKhp9mgiLkGbRgoX1HzT0TIUGaK82APasPREPeBhEoi843LV7OzTDNCZFGCIhEhhlmgkiZ4peVTUWiTmxIZr2mlqmysl2rrpdZ6adSEs48-47kyx6-tW-WEpsUunaa-5kpUH0FJ3ITzcgKr1z-PdvC35iew1r_spnc3vdtDWPdNVIwNiGlBLZ_M8AhWxVv-Mp0c28X7Dn366_s
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=A+deep+contractive+autoencoder+for+solving+multiclass+classification+problems&rft.jtitle=Evolutionary+intelligence&rft.au=Aamir%2C+Muhammad&rft.au=Mohd+Nawi%2C+Nazri&rft.au=Wahid%2C+Fazli&rft.au=Mahdin%2C+Hairulnizam&rft.date=2021-12-01&rft.issn=1864-5909&rft.eissn=1864-5917&rft.volume=14&rft.issue=4&rft.spage=1619&rft.epage=1633&rft_id=info:doi/10.1007%2Fs12065-020-00424-6&rft.externalDBID=n%2Fa&rft.externalDocID=10_1007_s12065_020_00424_6
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1864-5909&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1864-5909&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1864-5909&client=summon