Embedded stacked group sparse autoencoder ensemble with L1 regularization and manifold reduction
Learning useful representations from original features is a key issue in classification tasks. Stacked autoencoders (SAEs) are easy to understand and realize, and they are powerful tools that learn deep features from original features, so they are popular for classification problems. The deep featur...
Uloženo v:
| Vydáno v: | Applied soft computing Ročník 101; s. 107003 |
|---|---|
| Hlavní autoři: | , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier B.V
01.03.2021
|
| Témata: | |
| ISSN: | 1568-4946, 1872-9681 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Learning useful representations from original features is a key issue in classification tasks. Stacked autoencoders (SAEs) are easy to understand and realize, and they are powerful tools that learn deep features from original features, so they are popular for classification problems. The deep features can further combine the original features to construct more representative features for classification. However, existing SAEs do not consider the original features within the network structure and during training, so the deep features have low complementarity with the original features. To solve the problem, this paper proposes an embedded stacked group sparse autoencoder (ESGSAE) for more effective feature learning. Different from traditional stacked autoencoders, the ESGSAE model considers the complementarity between the original feature and the hidden outputs by embedding the original features into hidden layers. To alleviate the impact of the small sample problem on the generalization of the proposed ESGSAE model, an L1 regularization-based feature selection strategy is designed to further improve the feature quality. After that, an ensemble model with support vector machine (SVM) and weighted local discriminant preservation projection (w_LPPD) is designed to further enhance the feature quality. Based on the designs above, an embedded stacked group sparse autoencoder ensemble with L1 regularization and manifold reduction is proposed to obtain deep features with high complementarity in the context of the small sample problem. At the end of this paper, several representative public datasets are used for verification of the proposed algorithm. The results demonstrate that the ESGSAE ensemble model with L1 regularization and manifold reduction yields superior performance compared to other existing and state-of-the-art feature learning algorithms, including some representative deep stacked autoencoder methods. Specifically, compared with the original features, the representative feature extraction algorithms and the improved autoencoders, the algorithm proposed in this paper can improve the classification accuracy by up to 13.33%, 7.33%, and 9.55%, respectively. The data and codes can be found in: https://share.weiyun.com/Jt7qeORm
•A hybrid feature is embedded into the training process to construct a novel deep model.•A group sparsity constraint is introduced to obtain the sparse representations.•The ESGSAE ensemble model is constructed to obtain high complementary features.•A three-step feature learning mechanism is realized. |
|---|---|
| AbstractList | Learning useful representations from original features is a key issue in classification tasks. Stacked autoencoders (SAEs) are easy to understand and realize, and they are powerful tools that learn deep features from original features, so they are popular for classification problems. The deep features can further combine the original features to construct more representative features for classification. However, existing SAEs do not consider the original features within the network structure and during training, so the deep features have low complementarity with the original features. To solve the problem, this paper proposes an embedded stacked group sparse autoencoder (ESGSAE) for more effective feature learning. Different from traditional stacked autoencoders, the ESGSAE model considers the complementarity between the original feature and the hidden outputs by embedding the original features into hidden layers. To alleviate the impact of the small sample problem on the generalization of the proposed ESGSAE model, an L1 regularization-based feature selection strategy is designed to further improve the feature quality. After that, an ensemble model with support vector machine (SVM) and weighted local discriminant preservation projection (w_LPPD) is designed to further enhance the feature quality. Based on the designs above, an embedded stacked group sparse autoencoder ensemble with L1 regularization and manifold reduction is proposed to obtain deep features with high complementarity in the context of the small sample problem. At the end of this paper, several representative public datasets are used for verification of the proposed algorithm. The results demonstrate that the ESGSAE ensemble model with L1 regularization and manifold reduction yields superior performance compared to other existing and state-of-the-art feature learning algorithms, including some representative deep stacked autoencoder methods. Specifically, compared with the original features, the representative feature extraction algorithms and the improved autoencoders, the algorithm proposed in this paper can improve the classification accuracy by up to 13.33%, 7.33%, and 9.55%, respectively. The data and codes can be found in: https://share.weiyun.com/Jt7qeORm
•A hybrid feature is embedded into the training process to construct a novel deep model.•A group sparsity constraint is introduced to obtain the sparse representations.•The ESGSAE ensemble model is constructed to obtain high complementary features.•A three-step feature learning mechanism is realized. |
| ArticleNumber | 107003 |
| Author | Li, Yongming Liu, Yuchuan Lei, Yan Jiang, Mingfeng Wang, Pin |
| Author_xml | – sequence: 1 givenname: Yongming surname: Li fullname: Li, Yongming email: yongmingli@cqu.edu.cn organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, 400044, China – sequence: 2 givenname: Yan surname: Lei fullname: Lei, Yan organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, 400044, China – sequence: 3 givenname: Pin surname: Wang fullname: Wang, Pin organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, 400044, China – sequence: 4 givenname: Mingfeng surname: Jiang fullname: Jiang, Mingfeng organization: School of Information Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China – sequence: 5 givenname: Yuchuan surname: Liu fullname: Liu, Yuchuan organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, 400044, China |
| BookMark | eNp9kEtPwzAMgCM0JMbgD3DKH-hImvQlcUHTeEiTuMA55OGMjLaZkhYEv56UceKwky3bn2V_52jW-x4QuqJkSQktr3dLGb1e5iSfChUh7ATNaV3lWVPWdJbyoqwz3vDyDJ3HuCMJavJ6jl7XnQJjwOA4SP2e4jb4cY_jXoYIWI6Dh157AwFDH6FTLeBPN7zhDcUBtmMrg_uWg_M9lr3Bneyd9a1JPTPqqXyBTq1sI1z-xQV6uVs_rx6yzdP94-p2k2lGyJA1urCKWqWLmitmQatGW0OrvFJSW02kbFjFGGWUllzWjDeV5FVBCVeQRjhboPqwVwcfYwArtBt-DxuCdK2gREymxE5MpsRkShxMJTT_h-6D62T4Og7dHCBIT304CCJql1SBcQH0IIx3x_Afr9mGaA |
| CitedBy_id | crossref_primary_10_1007_s11760_021_01939_w crossref_primary_10_3390_app13127055 crossref_primary_10_1016_j_apenergy_2024_124960 crossref_primary_10_1109_ACCESS_2023_3289909 crossref_primary_10_1016_j_ins_2023_01_133 crossref_primary_10_1109_TAI_2023_3266190 crossref_primary_10_1007_s11063_021_10659_8 crossref_primary_10_1016_j_future_2024_107630 crossref_primary_10_1016_j_renene_2021_04_102 crossref_primary_10_3233_JIFS_212873 crossref_primary_10_1016_j_neunet_2025_107843 crossref_primary_10_1007_s10812_023_01491_0 |
| Cites_doi | 10.1016/j.engappai.2016.12.012 10.1016/j.asoc.2018.07.029 10.1016/j.neucom.2014.08.092 10.1016/j.compbiomed.2018.05.027 10.1109/72.977291 10.1007/s00429-013-0687-3 10.1016/j.isprsjprs.2013.05.008 10.1109/TNNLS.2015.2404823 10.1016/j.neucom.2020.04.057 10.1109/LSP.2014.2384196 10.1109/TIFS.2017.2668221 10.1186/s12938-018-0489-1 10.1109/TNNLS.2016.2603784 10.1109/TIP.2017.2725580 10.1109/JSTARS.2019.2892951 10.1109/TIP.2019.2901407 10.1016/j.procs.2017.09.066 10.1126/science.1127647 10.1109/ACCESS.2019.2951526 10.1093/bioinformatics/btz505 10.1109/LA-CCI.2017.8285680 10.1016/j.neunet.2018.04.016 10.1073/pnas.0807471105 10.1016/S0893-6080(05)80056-5 10.1109/ACCESS.2018.2884827 10.1109/TPAMI.2014.2301163 10.1162/NECO_a_00537 10.1109/TASLP.2016.2530401 10.1007/BF00332918 10.1109/TMM.2017.2766843 10.1109/TNSRE.2013.2293575 10.1016/j.neucom.2019.05.050 10.1007/s00521-016-2758-x 10.1561/2200000006 10.1109/TNNLS.2017.2783384 10.1109/JBHI.2013.2245674 10.1016/j.knosys.2019.04.022 10.1109/TSM.2017.2648856 10.1016/j.asoc.2019.106060 10.1109/TFUZZ.2010.2089631 10.1016/j.patcog.2003.08.004 10.1109/TMM.2016.2638204 10.1109/TPWRS.2016.2628873 10.1016/0169-7439(87)80084-9 10.1109/ACCESS.2017.2706363 10.1109/LGRS.2019.2901019 10.1109/ACCESS.2019.2927384 10.1016/j.patrec.2016.05.018 |
| ContentType | Journal Article |
| Copyright | 2020 Elsevier B.V. |
| Copyright_xml | – notice: 2020 Elsevier B.V. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.asoc.2020.107003 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-9681 |
| ExternalDocumentID | 10_1016_j_asoc_2020_107003 S156849462030942X |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 23M 4.4 457 4G. 53G 5GY 5VS 6J9 7-5 71M 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABBOA ABFNM ABFRF ABJNI ABMAC ABXDB ABYKQ ACDAQ ACGFO ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADJOM ADMUD ADTZH AEBSH AECPX AEFWE 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 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 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 SES SEW SPC SPCBC SST SSV SSZ T5K UHS UNMZH ~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-c300t-9c5fb1fbc584b3fecb9cfd1727bacfc0aa93733131164a83497a475104be7ba43 |
| ISICitedReferencesCount | 14 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000621420900013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1568-4946 |
| IngestDate | Sat Nov 29 07:03:55 EST 2025 Tue Nov 18 22:36:52 EST 2025 Fri Feb 23 02:41:49 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Embedded stacked group sparse autoencoder (ESGSAE) Embedded deep learning Feature fusion Ensemble learning Weighted local discriminant preservation projection (w_LPPD) |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c300t-9c5fb1fbc584b3fecb9cfd1727bacfc0aa93733131164a83497a475104be7ba43 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_asoc_2020_107003 crossref_primary_10_1016_j_asoc_2020_107003 elsevier_sciencedirect_doi_10_1016_j_asoc_2020_107003 |
| PublicationCentury | 2000 |
| PublicationDate | March 2021 2021-03-00 |
| PublicationDateYYYYMMDD | 2021-03-01 |
| PublicationDate_xml | – month: 03 year: 2021 text: March 2021 |
| PublicationDecade | 2020 |
| PublicationTitle | Applied soft computing |
| PublicationYear | 2021 |
| Publisher | Elsevier B.V |
| Publisher_xml | – name: Elsevier B.V |
| References | Li, Kuo, Lin (b10) 2011; 19 Luo, Yang, Xu, Fu (b39) 2015; 22 Yu (b43) 2019; 178 Jiang, Fu, Tao, Lei, Zhao (b15) 2019; 7 Lei, Yuan, Wang, Wenhu, Bo (b33) 2017; 19 Goswami, Vatsa, Singh (b26) 2017; 12 Kwak, Choi (b5) 2002; 13 Kan, Cen, He, Zhang, Zhang, Wang (b50) 2019; 28 Yao, Han, Nie, Xiao, Li (b1) 2018; 29 Raulf, Butke, Küpper, Großerüschkamp, Gerwert, Mosig, Wren (b31) 2020; 36 M. Gutoski, M. Ribeiro, N.M. Romero Aquino, A.E. Lazzaretti, H.S. Lopes, A clustering-based deep autoencoder for one-class image classification, in: 2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI, Arequipa, 2017, pp. 1–6. Li, Struzik, Zhang, Cichocki (b3) 2015; 165 Ferles, Papanikolaou, Naidoo (b32) 2018; 105 Zhu, Cheng, Zhang, Wu, Shao (b42) 2020; 88 Møller (b51) 1993; 6 Dua, Taniskidou (b54) 2017 Sutskever, Vinyals, Le (b17) 2014 Fan, Lin, Han (b41) 2019; 12 Mei, Yang, Yin (b49) 2017; 30 Yamada, Jitkrittum, Sigal, Xing, Sugiyama (b6) 2014; 26 Lee, Kwon (b12) 2017; 26 Sakar, Isenkul, Sakar, Sertbas, Gurgen, Delil, Apaydin, Kursun (b53) 2013; 17 He (b11) 2005 Wang, Zhang, Chen (b35) 2017; 32 Hoti, Holmström (b55) 2004; 37 Majtner, Yildirim-Yayilgan, Hardeberg (b46) 2016 Bakhti, Fezza, Hamidouche, Deforges (b30) 2019; 7 Hinton (b23) 2006; 313 Bourlard, Kamp (b24) 1988; 59 Tan, Liu, Li, Wang, Zeng, Yan, Li (b52) 2018; 17 Liu, Xie, Yu, Niu, Sun (b47) 2017 Wold, Esbensen, Geladi (b9) 1987; 2 Kim, Kim, Noh, Kim (b22) 2018; 6 Tsanas, Little, Fox, Ramig (b56) 2014; 22 Praveen, Agrawal, Sundaram, Sardesai (b28) 2018; 99 Tran, d’Avila Garcez (b20) 2018; 29 Charte, Charte, del Jesus, Herrera (b37) 2020; 404 Lv, Han, Qiu (b25) 2017; 5 Lin, Kai, Sun (b7) 2013; 8 Shi, Lei, Yin, Cao, Li, Chang (b40) 2019; 16 Grozdić, Jovičić, Subotić (b29) 2017; 59 Zhang, Zhang, Huang, Gao (b16) 2018; 20 Johnson, Xie (b57) 2013; 83 Donoho, Jin (b8) 2008; 105 Cho, van Merrienboer, Gulcehre, Bahdanau, Bougares, Schwenk, Bengio (b18) 2014 Simonyan, Vedaldi, Zisserman (b2) 2014; 36 Bengio (b45) 2009; 2 Uzair, Shafait, Ghanem, Mian (b13) 2016; 30 Görgel, Simsek (b27) 2019; 355 Yu (b44) 2019; 358 Chandra (b21) 2015; 26 Suk, Lee, Shen (b48) 2015; 220 Potapov, Potapova, Peterson (b34) 2016; 80 Dizaji, Herandi, Deng, Cai, Huang (b36) 2017 Kampffmeyer, Løkse, Bianchi, Jenssen, Livi (b38) 2018; 71 Phan, Hertel, Maass, Mazur, Mertins (b4) 2016; 24 Mehdiyev, Lahann, Emrich, Enke, Fettke, Loos (b19) 2017; 114 Yu (10.1016/j.asoc.2020.107003_b44) 2019; 358 Lin (10.1016/j.asoc.2020.107003_b7) 2013; 8 Zhang (10.1016/j.asoc.2020.107003_b16) 2018; 20 Sutskever (10.1016/j.asoc.2020.107003_b17) 2014 Tsanas (10.1016/j.asoc.2020.107003_b56) 2014; 22 Li (10.1016/j.asoc.2020.107003_b3) 2015; 165 Wang (10.1016/j.asoc.2020.107003_b35) 2017; 32 Kan (10.1016/j.asoc.2020.107003_b50) 2019; 28 Ferles (10.1016/j.asoc.2020.107003_b32) 2018; 105 Phan (10.1016/j.asoc.2020.107003_b4) 2016; 24 Hinton (10.1016/j.asoc.2020.107003_b23) 2006; 313 Bengio (10.1016/j.asoc.2020.107003_b45) 2009; 2 Sakar (10.1016/j.asoc.2020.107003_b53) 2013; 17 Fan (10.1016/j.asoc.2020.107003_b41) 2019; 12 Bakhti (10.1016/j.asoc.2020.107003_b30) 2019; 7 Lei (10.1016/j.asoc.2020.107003_b33) 2017; 19 Zhu (10.1016/j.asoc.2020.107003_b42) 2020; 88 Tan (10.1016/j.asoc.2020.107003_b52) 2018; 17 Hoti (10.1016/j.asoc.2020.107003_b55) 2004; 37 Tran (10.1016/j.asoc.2020.107003_b20) 2018; 29 Dua (10.1016/j.asoc.2020.107003_b54) 2017 Kwak (10.1016/j.asoc.2020.107003_b5) 2002; 13 Grozdić (10.1016/j.asoc.2020.107003_b29) 2017; 59 Yu (10.1016/j.asoc.2020.107003_b43) 2019; 178 Lv (10.1016/j.asoc.2020.107003_b25) 2017; 5 Simonyan (10.1016/j.asoc.2020.107003_b2) 2014; 36 10.1016/j.asoc.2020.107003_b14 Shi (10.1016/j.asoc.2020.107003_b40) 2019; 16 Mei (10.1016/j.asoc.2020.107003_b49) 2017; 30 Goswami (10.1016/j.asoc.2020.107003_b26) 2017; 12 Potapov (10.1016/j.asoc.2020.107003_b34) 2016; 80 Suk (10.1016/j.asoc.2020.107003_b48) 2015; 220 Raulf (10.1016/j.asoc.2020.107003_b31) 2020; 36 Lee (10.1016/j.asoc.2020.107003_b12) 2017; 26 Møller (10.1016/j.asoc.2020.107003_b51) 1993; 6 Liu (10.1016/j.asoc.2020.107003_b47) 2017 Uzair (10.1016/j.asoc.2020.107003_b13) 2016; 30 Bourlard (10.1016/j.asoc.2020.107003_b24) 1988; 59 Yao (10.1016/j.asoc.2020.107003_b1) 2018; 29 Jiang (10.1016/j.asoc.2020.107003_b15) 2019; 7 Kim (10.1016/j.asoc.2020.107003_b22) 2018; 6 Luo (10.1016/j.asoc.2020.107003_b39) 2015; 22 Chandra (10.1016/j.asoc.2020.107003_b21) 2015; 26 Donoho (10.1016/j.asoc.2020.107003_b8) 2008; 105 Charte (10.1016/j.asoc.2020.107003_b37) 2020; 404 Mehdiyev (10.1016/j.asoc.2020.107003_b19) 2017; 114 Yamada (10.1016/j.asoc.2020.107003_b6) 2014; 26 Kampffmeyer (10.1016/j.asoc.2020.107003_b38) 2018; 71 Görgel (10.1016/j.asoc.2020.107003_b27) 2019; 355 Praveen (10.1016/j.asoc.2020.107003_b28) 2018; 99 Johnson (10.1016/j.asoc.2020.107003_b57) 2013; 83 Li (10.1016/j.asoc.2020.107003_b10) 2011; 19 He (10.1016/j.asoc.2020.107003_b11) 2005 Dizaji (10.1016/j.asoc.2020.107003_b36) 2017 Cho (10.1016/j.asoc.2020.107003_b18) 2014 Wold (10.1016/j.asoc.2020.107003_b9) 1987; 2 Majtner (10.1016/j.asoc.2020.107003_b46) 2016 |
| References_xml | – volume: 7 start-page: 160397 year: 2019 end-page: 160407 ident: b30 article-title: DDSA: a defense against adversarial attacks using deep denoising sparse autoencoder publication-title: IEEE Access – start-page: 5747 year: 2017 end-page: 5756 ident: b36 article-title: Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization publication-title: Proc. IEEE Int. Conf. Comput. Vis. – start-page: 1724 year: 2014 end-page: 1734 ident: b18 article-title: Learning phrase representations using RNN encoder–decoder for statistical machine translation publication-title: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing – volume: 7 start-page: 90368 year: 2019 end-page: 90377 ident: b15 article-title: Parallelized convolutional recurrent neural network with spectral features for speech emotion recognition publication-title: IEEE Access – volume: 8 start-page: 3921 year: 2013 end-page: 3929 ident: b7 article-title: A novel relief feature selection algorithm based on mean–variance model publication-title: Syst. Simul. Technol. – volume: 12 start-page: 1686 year: 2017 end-page: 1698 ident: b26 article-title: Face verification via learned representation on feature-rich video frames publication-title: IEEE Trans. Inf. Forensics Secur. – start-page: 919 year: 2017 end-page: 923 ident: b47 article-title: Classification of thyroid nodules in ultrasound images using deep model based transfer learning and hybrid features publication-title: 2017 IEEE International Conference on Acoustics, Speech and Signal Processing – volume: 59 start-page: 291 year: 1988 end-page: 294 ident: b24 article-title: Auto-association by multilayer perceptrons and singular value decomposition publication-title: Biol. Cybernet. – volume: 6 start-page: 75216 year: 2018 end-page: 75228 ident: b22 article-title: Stable forecasting of environmental time series via long short term memory recurrent neural network publication-title: IEEE Access – volume: 30 start-page: 1211 year: 2016 end-page: 1223 ident: b13 article-title: Representation learning with deep extreme learning machines for efficient image set classification publication-title: Neural Comput. Appl. – volume: 24 start-page: 807 year: 2016 end-page: 822 ident: b4 article-title: Learning representations for nonspeech audio events through their similarities to speech patterns publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. – volume: 28 start-page: 5809 year: 2019 end-page: 5823 ident: b50 article-title: Supervised deep feature embedding with handcrafted feature publication-title: IEEE Trans. Image Process. – volume: 22 start-page: 181 year: 2014 end-page: 190 ident: b56 article-title: Objective automatic assessment of rehabilitative speech treatment in Parkinson’s disease publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. – start-page: 3104 year: 2014 end-page: 3112 ident: b17 article-title: Sequence to sequence learning with neural networks publication-title: Advances in Neural Information Processing Systems – volume: 6 start-page: 4 year: 1993 ident: b51 article-title: A scaled conjugate gradient algorithm for fast supervised learning publication-title: Neural Netw. – volume: 26 start-page: 3123 year: 2015 end-page: 3136 ident: b21 article-title: Competition and collaboration in cooperative coevolution of elman recurrent neural networks for time-series prediction publication-title: IEEE Trans. Neural Netw. Learn. Syst. – year: 2005 ident: b11 article-title: Locality Preserving Projections – volume: 355 start-page: 325 year: 2019 end-page: 342 ident: b27 article-title: Face recognition via deep stacked denoising sparse autoencoders (DSDSA) publication-title: Appl. Math. Comput. – volume: 32 start-page: 2673 year: 2017 end-page: 2681 ident: b35 article-title: Short-term electricity price forecasting with stacked denoising autoencoders publication-title: IEEE Trans. Power Syst. – volume: 165 start-page: 23 year: 2015 end-page: 31 ident: b3 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing – volume: 26 start-page: 4843 year: 2017 end-page: 4855 ident: b12 article-title: Going deeper with contextual CNN for hyperspectral image classification publication-title: IEEE Trans. Image Process. – volume: 19 start-page: 740 year: 2017 end-page: 749 ident: b33 article-title: A skin segmentation algorithm based on stacked autoencoders publication-title: IEEE Trans. Multimed. – volume: 13 start-page: 143 year: 2002 end-page: 159 ident: b5 article-title: Input feature selection for classification problems publication-title: IEEE Trans. Neural Netw. – start-page: 1 year: 2016 end-page: 6 ident: b46 article-title: Combining deep learning and hand-crafted features for skin lesion classification publication-title: 2016 Sixth International Conference on Image Processing Theory, Tools and Applications – volume: 36 start-page: 287 year: 2020 end-page: 294 ident: b31 article-title: Deep representation learning for domain adaptable classification of infrared spectral imaging data publication-title: Bioinformatics – volume: 88 year: 2020 ident: b42 article-title: Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings publication-title: Appl. Soft Comput. – volume: 16 start-page: 1462 year: 2019 end-page: 1466 ident: b40 article-title: Discriminative feature learning with distance constrained stacked sparse autoencoder for hyperspectral target detection publication-title: IEEE Geosci. Remote Sens. Lett. – volume: 404 start-page: 93 year: 2020 end-page: 107 ident: b37 article-title: An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges publication-title: Neurocomputing – volume: 17 start-page: 828 year: 2013 end-page: 834 ident: b53 article-title: Collection and analysis of a parkinson speech dataset with multiple types of sound recordings publication-title: IEEE J. Biomed. Health Inform. – volume: 114 start-page: 242 year: 2017 end-page: 249 ident: b19 article-title: Time series classification using deep learning for process planning: A case from the process industry publication-title: Procedia Comput. Sci. – volume: 12 start-page: 685 year: 2019 end-page: 699 ident: b41 article-title: A novel joint change detection approach based on weight-clustering sparse autoencoders publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. – volume: 99 start-page: 38 year: 2018 end-page: 52 ident: b28 article-title: Ischemic stroke lesion segmentation using stacked sparse autoencoder publication-title: Comput. Biol. Med. – volume: 29 start-page: 4882 year: 2018 end-page: 4893 ident: b1 article-title: Local regression and global information-embedded dimension reduction publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 313 start-page: 504 year: 2006 end-page: 507 ident: b23 article-title: Reducing the dimensionality of data with neural networks publication-title: Science – volume: 358 start-page: 235 year: 2019 end-page: 245 ident: b44 article-title: Manifold regularized stacked denoising autoencoders with feature selection publication-title: Neurocomputing – volume: 105 start-page: 112 year: 2018 end-page: 131 ident: b32 article-title: Denoising autoencoder self-organizing map (DASOM) publication-title: Neural Netw. – volume: 71 start-page: 816 year: 2018 end-page: 825 ident: b38 article-title: The deep kernelized autoencoder publication-title: Appl. Soft Comput. – volume: 19 start-page: 152 year: 2011 end-page: 163 ident: b10 article-title: LDA-based clustering algorithm and its application to an unsupervised feature extraction publication-title: IEEE Trans. Fuzzy Syst. – volume: 30 start-page: 105 year: 2017 end-page: 113 ident: b49 article-title: Unsupervised-learning-based feature-level fusion method for mura defect recognition publication-title: IEEE Trans. Semicond. Manuf. – volume: 80 start-page: 24 year: 2016 end-page: 29 ident: b34 article-title: A feasibility study of an autoencoder meta-model for improving generalization capabilities on training sets of small sizes publication-title: Pattern Recognit. Lett. – volume: 26 start-page: 185 year: 2014 end-page: 207 ident: b6 article-title: High-dimensional feature selection by feature-wise kernelized lasso publication-title: Neural Comput. – year: 2017 ident: b54 article-title: UCI Machine Learning Repository – volume: 178 start-page: 111 year: 2019 end-page: 122 ident: b43 article-title: Evolutionary manifold regularized stacked denoising autoencoders for gearbox fault diagnosis publication-title: Knowl.-Based Syst. – volume: 17 start-page: 49 year: 2018 ident: b52 article-title: Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning publication-title: Biomed. Eng. Online – volume: 36 start-page: 1573 year: 2014 end-page: 1585 ident: b2 article-title: Learning local feature descriptors using convex optimisation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – reference: M. Gutoski, M. Ribeiro, N.M. Romero Aquino, A.E. Lazzaretti, H.S. Lopes, A clustering-based deep autoencoder for one-class image classification, in: 2017 IEEE Latin American Conference on Computational Intelligence, LA-CCI, Arequipa, 2017, pp. 1–6. – volume: 220 start-page: 841 year: 2015 end-page: 859 ident: b48 article-title: Latent feature representation with stacked auto-encoder for AD/MCI diagnosis publication-title: Brain Struct. Funct. – volume: 2 start-page: 1 year: 2009 end-page: 127 ident: b45 article-title: Learning deep architectures for AI publication-title: Found. Trends Mach. Learn. – volume: 20 start-page: 1576 year: 2018 end-page: 1590 ident: b16 article-title: Speech emotion recognition using deep convolutional neural network and discriminant temporal pyramid matching publication-title: IEEE Trans. Multimed. – volume: 105 start-page: 14790 year: 2008 end-page: 14795 ident: b8 article-title: Higher criticism thresholding: optimal feature selection when useful features are rare and weak publication-title: Proc. Natl. Acad. Sci. USA – volume: 22 start-page: 1070 year: 2015 end-page: 1073 ident: b39 article-title: Locality-constrained sparse auto-encoder for image classification publication-title: IEEE Signal Process. Lett. – volume: 37 start-page: 409 year: 2004 end-page: 419 ident: b55 article-title: A semiparametric density estimation approach to pattern classification publication-title: Pattern Recognit. – volume: 5 start-page: 9021 year: 2017 end-page: 9031 ident: b25 article-title: Remote sensing image classification based on ensemble extreme learning machine with stacked autoencoder publication-title: IEEE Access – volume: 29 start-page: 246 year: 2018 end-page: 258 ident: b20 article-title: Deep logic networks: inserting and extracting knowledge from deep belief networks publication-title: IEEE Trans. Neural Netw. Learn. Syst. – volume: 83 start-page: 40 year: 2013 end-page: 49 ident: b57 article-title: Classifying a high resolution image of an urban area using super-object information publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 2 start-page: 37 year: 1987 end-page: 52 ident: b9 article-title: Principal component analysis publication-title: Chemom. Intell. Lab. Syst. – volume: 59 start-page: 15 year: 2017 end-page: 22 ident: b29 article-title: Whispered speech recognition using deep denoising autoencoder publication-title: Eng. Appl. Artif. Intell. – volume: 59 start-page: 15 year: 2017 ident: 10.1016/j.asoc.2020.107003_b29 article-title: Whispered speech recognition using deep denoising autoencoder publication-title: Eng. Appl. Artif. Intell. doi: 10.1016/j.engappai.2016.12.012 – volume: 71 start-page: 816 year: 2018 ident: 10.1016/j.asoc.2020.107003_b38 article-title: The deep kernelized autoencoder publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2018.07.029 – year: 2017 ident: 10.1016/j.asoc.2020.107003_b54 – volume: 165 start-page: 23 year: 2015 ident: 10.1016/j.asoc.2020.107003_b3 article-title: Feature learning from incomplete EEG with denoising autoencoder publication-title: Neurocomputing doi: 10.1016/j.neucom.2014.08.092 – volume: 99 start-page: 38 year: 2018 ident: 10.1016/j.asoc.2020.107003_b28 article-title: Ischemic stroke lesion segmentation using stacked sparse autoencoder publication-title: Comput. Biol. Med. doi: 10.1016/j.compbiomed.2018.05.027 – year: 2005 ident: 10.1016/j.asoc.2020.107003_b11 – volume: 13 start-page: 143 year: 2002 ident: 10.1016/j.asoc.2020.107003_b5 article-title: Input feature selection for classification problems publication-title: IEEE Trans. Neural Netw. doi: 10.1109/72.977291 – volume: 8 start-page: 3921 year: 2013 ident: 10.1016/j.asoc.2020.107003_b7 article-title: A novel relief feature selection algorithm based on mean–variance model publication-title: Syst. Simul. Technol. – volume: 220 start-page: 841 year: 2015 ident: 10.1016/j.asoc.2020.107003_b48 article-title: Latent feature representation with stacked auto-encoder for AD/MCI diagnosis publication-title: Brain Struct. Funct. doi: 10.1007/s00429-013-0687-3 – volume: 83 start-page: 40 year: 2013 ident: 10.1016/j.asoc.2020.107003_b57 article-title: Classifying a high resolution image of an urban area using super-object information publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2013.05.008 – volume: 26 start-page: 3123 year: 2015 ident: 10.1016/j.asoc.2020.107003_b21 article-title: Competition and collaboration in cooperative coevolution of elman recurrent neural networks for time-series prediction publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2015.2404823 – volume: 404 start-page: 93 year: 2020 ident: 10.1016/j.asoc.2020.107003_b37 article-title: An analysis on the use of autoencoders for representation learning: fundamentals, learning task case studies, explainability and challenges publication-title: Neurocomputing doi: 10.1016/j.neucom.2020.04.057 – volume: 22 start-page: 1070 year: 2015 ident: 10.1016/j.asoc.2020.107003_b39 article-title: Locality-constrained sparse auto-encoder for image classification publication-title: IEEE Signal Process. Lett. doi: 10.1109/LSP.2014.2384196 – volume: 12 start-page: 1686 year: 2017 ident: 10.1016/j.asoc.2020.107003_b26 article-title: Face verification via learned representation on feature-rich video frames publication-title: IEEE Trans. Inf. Forensics Secur. doi: 10.1109/TIFS.2017.2668221 – start-page: 5747 year: 2017 ident: 10.1016/j.asoc.2020.107003_b36 article-title: Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization publication-title: Proc. IEEE Int. Conf. Comput. Vis. – start-page: 3104 year: 2014 ident: 10.1016/j.asoc.2020.107003_b17 article-title: Sequence to sequence learning with neural networks – volume: 17 start-page: 49 year: 2018 ident: 10.1016/j.asoc.2020.107003_b52 article-title: Localized instance fusion of MRI data of Alzheimer’s disease for classification based on instance transfer ensemble learning publication-title: Biomed. Eng. Online doi: 10.1186/s12938-018-0489-1 – volume: 29 start-page: 246 year: 2018 ident: 10.1016/j.asoc.2020.107003_b20 article-title: Deep logic networks: inserting and extracting knowledge from deep belief networks publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2016.2603784 – start-page: 1 year: 2016 ident: 10.1016/j.asoc.2020.107003_b46 article-title: Combining deep learning and hand-crafted features for skin lesion classification – volume: 26 start-page: 4843 year: 2017 ident: 10.1016/j.asoc.2020.107003_b12 article-title: Going deeper with contextual CNN for hyperspectral image classification publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2017.2725580 – volume: 12 start-page: 685 year: 2019 ident: 10.1016/j.asoc.2020.107003_b41 article-title: A novel joint change detection approach based on weight-clustering sparse autoencoders publication-title: IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. doi: 10.1109/JSTARS.2019.2892951 – volume: 28 start-page: 5809 year: 2019 ident: 10.1016/j.asoc.2020.107003_b50 article-title: Supervised deep feature embedding with handcrafted feature publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2019.2901407 – volume: 114 start-page: 242 year: 2017 ident: 10.1016/j.asoc.2020.107003_b19 article-title: Time series classification using deep learning for process planning: A case from the process industry publication-title: Procedia Comput. Sci. doi: 10.1016/j.procs.2017.09.066 – volume: 313 start-page: 504 year: 2006 ident: 10.1016/j.asoc.2020.107003_b23 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – volume: 7 start-page: 160397 year: 2019 ident: 10.1016/j.asoc.2020.107003_b30 article-title: DDSA: a defense against adversarial attacks using deep denoising sparse autoencoder publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2951526 – volume: 36 start-page: 287 year: 2020 ident: 10.1016/j.asoc.2020.107003_b31 article-title: Deep representation learning for domain adaptable classification of infrared spectral imaging data publication-title: Bioinformatics doi: 10.1093/bioinformatics/btz505 – ident: 10.1016/j.asoc.2020.107003_b14 doi: 10.1109/LA-CCI.2017.8285680 – volume: 105 start-page: 112 year: 2018 ident: 10.1016/j.asoc.2020.107003_b32 article-title: Denoising autoencoder self-organizing map (DASOM) publication-title: Neural Netw. doi: 10.1016/j.neunet.2018.04.016 – volume: 105 start-page: 14790 year: 2008 ident: 10.1016/j.asoc.2020.107003_b8 article-title: Higher criticism thresholding: optimal feature selection when useful features are rare and weak publication-title: Proc. Natl. Acad. Sci. USA doi: 10.1073/pnas.0807471105 – volume: 6 start-page: 4 year: 1993 ident: 10.1016/j.asoc.2020.107003_b51 article-title: A scaled conjugate gradient algorithm for fast supervised learning publication-title: Neural Netw. doi: 10.1016/S0893-6080(05)80056-5 – volume: 6 start-page: 75216 year: 2018 ident: 10.1016/j.asoc.2020.107003_b22 article-title: Stable forecasting of environmental time series via long short term memory recurrent neural network publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2884827 – volume: 36 start-page: 1573 year: 2014 ident: 10.1016/j.asoc.2020.107003_b2 article-title: Learning local feature descriptors using convex optimisation publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2014.2301163 – volume: 26 start-page: 185 year: 2014 ident: 10.1016/j.asoc.2020.107003_b6 article-title: High-dimensional feature selection by feature-wise kernelized lasso publication-title: Neural Comput. doi: 10.1162/NECO_a_00537 – volume: 355 start-page: 325 year: 2019 ident: 10.1016/j.asoc.2020.107003_b27 article-title: Face recognition via deep stacked denoising sparse autoencoders (DSDSA) publication-title: Appl. Math. Comput. – volume: 24 start-page: 807 year: 2016 ident: 10.1016/j.asoc.2020.107003_b4 article-title: Learning representations for nonspeech audio events through their similarities to speech patterns publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. doi: 10.1109/TASLP.2016.2530401 – volume: 59 start-page: 291 year: 1988 ident: 10.1016/j.asoc.2020.107003_b24 article-title: Auto-association by multilayer perceptrons and singular value decomposition publication-title: Biol. Cybernet. doi: 10.1007/BF00332918 – volume: 20 start-page: 1576 year: 2018 ident: 10.1016/j.asoc.2020.107003_b16 article-title: Speech emotion recognition using deep convolutional neural network and discriminant temporal pyramid matching publication-title: IEEE Trans. Multimed. doi: 10.1109/TMM.2017.2766843 – volume: 22 start-page: 181 year: 2014 ident: 10.1016/j.asoc.2020.107003_b56 article-title: Objective automatic assessment of rehabilitative speech treatment in Parkinson’s disease publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2013.2293575 – volume: 358 start-page: 235 year: 2019 ident: 10.1016/j.asoc.2020.107003_b44 article-title: Manifold regularized stacked denoising autoencoders with feature selection publication-title: Neurocomputing doi: 10.1016/j.neucom.2019.05.050 – volume: 30 start-page: 1211 year: 2016 ident: 10.1016/j.asoc.2020.107003_b13 article-title: Representation learning with deep extreme learning machines for efficient image set classification publication-title: Neural Comput. Appl. doi: 10.1007/s00521-016-2758-x – volume: 2 start-page: 1 year: 2009 ident: 10.1016/j.asoc.2020.107003_b45 article-title: Learning deep architectures for AI publication-title: Found. Trends Mach. Learn. doi: 10.1561/2200000006 – volume: 29 start-page: 4882 year: 2018 ident: 10.1016/j.asoc.2020.107003_b1 article-title: Local regression and global information-embedded dimension reduction publication-title: IEEE Trans. Neural Netw. Learn. Syst. doi: 10.1109/TNNLS.2017.2783384 – volume: 17 start-page: 828 year: 2013 ident: 10.1016/j.asoc.2020.107003_b53 article-title: Collection and analysis of a parkinson speech dataset with multiple types of sound recordings publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2013.2245674 – volume: 178 start-page: 111 year: 2019 ident: 10.1016/j.asoc.2020.107003_b43 article-title: Evolutionary manifold regularized stacked denoising autoencoders for gearbox fault diagnosis publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2019.04.022 – volume: 30 start-page: 105 year: 2017 ident: 10.1016/j.asoc.2020.107003_b49 article-title: Unsupervised-learning-based feature-level fusion method for mura defect recognition publication-title: IEEE Trans. Semicond. Manuf. doi: 10.1109/TSM.2017.2648856 – start-page: 1724 year: 2014 ident: 10.1016/j.asoc.2020.107003_b18 article-title: Learning phrase representations using RNN encoder–decoder for statistical machine translation – volume: 88 year: 2020 ident: 10.1016/j.asoc.2020.107003_b42 article-title: Stacked pruning sparse denoising autoencoder based intelligent fault diagnosis of rolling bearings publication-title: Appl. Soft Comput. doi: 10.1016/j.asoc.2019.106060 – volume: 19 start-page: 152 year: 2011 ident: 10.1016/j.asoc.2020.107003_b10 article-title: LDA-based clustering algorithm and its application to an unsupervised feature extraction publication-title: IEEE Trans. Fuzzy Syst. doi: 10.1109/TFUZZ.2010.2089631 – start-page: 919 year: 2017 ident: 10.1016/j.asoc.2020.107003_b47 article-title: Classification of thyroid nodules in ultrasound images using deep model based transfer learning and hybrid features – volume: 37 start-page: 409 year: 2004 ident: 10.1016/j.asoc.2020.107003_b55 article-title: A semiparametric density estimation approach to pattern classification publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2003.08.004 – volume: 19 start-page: 740 year: 2017 ident: 10.1016/j.asoc.2020.107003_b33 article-title: A skin segmentation algorithm based on stacked autoencoders publication-title: IEEE Trans. Multimed. doi: 10.1109/TMM.2016.2638204 – volume: 32 start-page: 2673 year: 2017 ident: 10.1016/j.asoc.2020.107003_b35 article-title: Short-term electricity price forecasting with stacked denoising autoencoders publication-title: IEEE Trans. Power Syst. doi: 10.1109/TPWRS.2016.2628873 – volume: 2 start-page: 37 year: 1987 ident: 10.1016/j.asoc.2020.107003_b9 article-title: Principal component analysis publication-title: Chemom. Intell. Lab. Syst. doi: 10.1016/0169-7439(87)80084-9 – volume: 5 start-page: 9021 year: 2017 ident: 10.1016/j.asoc.2020.107003_b25 article-title: Remote sensing image classification based on ensemble extreme learning machine with stacked autoencoder publication-title: IEEE Access doi: 10.1109/ACCESS.2017.2706363 – volume: 16 start-page: 1462 year: 2019 ident: 10.1016/j.asoc.2020.107003_b40 article-title: Discriminative feature learning with distance constrained stacked sparse autoencoder for hyperspectral target detection publication-title: IEEE Geosci. Remote Sens. Lett. doi: 10.1109/LGRS.2019.2901019 – volume: 7 start-page: 90368 year: 2019 ident: 10.1016/j.asoc.2020.107003_b15 article-title: Parallelized convolutional recurrent neural network with spectral features for speech emotion recognition publication-title: IEEE Access doi: 10.1109/ACCESS.2019.2927384 – volume: 80 start-page: 24 year: 2016 ident: 10.1016/j.asoc.2020.107003_b34 article-title: A feasibility study of an autoencoder meta-model for improving generalization capabilities on training sets of small sizes publication-title: Pattern Recognit. Lett. doi: 10.1016/j.patrec.2016.05.018 |
| SSID | ssj0016928 |
| Score | 2.3848033 |
| Snippet | Learning useful representations from original features is a key issue in classification tasks. Stacked autoencoders (SAEs) are easy to understand and realize,... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 107003 |
| SubjectTerms | Embedded deep learning Embedded stacked group sparse autoencoder (ESGSAE) Ensemble learning Feature fusion Weighted local discriminant preservation projection (w_LPPD) |
| Title | Embedded stacked group sparse autoencoder ensemble with L1 regularization and manifold reduction |
| URI | https://dx.doi.org/10.1016/j.asoc.2020.107003 |
| Volume | 101 |
| WOSCitedRecordID | wos000621420900013&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: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-9681 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0016928 issn: 1568-4946 databaseCode: AIEXJ dateStart: 20010601 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELZgy4ELb0R5yQduUVAS20l8rNAiqEpViSKWU7ATG23VzVbZLOrPZ8Z2soGiCpC4RNEojiPPl_HMeB6EvOKmNIwJMFNhf8eUHBnrzKhYp7k1VjSFyhrXbKI4Pi4XC3kSQoI2rp1A0bbl5aW8-K-sBhowG1Nn_4Ld40uBAPfAdLgC2-H6R4yfr7QBadKglwB-0SZyiRsRSI5uYyK17ddYuxJLSIAFa1aYOeWcsUdp1LnG9F1IzXTnClgew67PMcel8YVmp-rsoMNuQJi76PRtP2yFGOTjIgW-rNtvqynVePIOlp-Dz_pkOZIOl4H2AUZaE0YH70Q2Cc_yLrMraTNeyuZlzGXwPRpPK4sslrnv3zKKZv-qK2LeexzOXitAMNj4GZKKJGG7TW0MNfyIk-FcGR4m8Wxxk-xlhZDljOwdvJ8vDsczp1y6Trzjx4UUKx8N-OtMv1djJqrJ6T1yJ9gU9MBj4T65YdoH5O7Qr4MG8f2QfB2gQQM0qIMG9dCgE2jQARoUoUGPUvozNChAgw7QoCM0HpFPb-enb97FocNGXLMk6WNZC6tTq2tQQzWzptaytg3qtFrVtk6UAu2VMSzJlHNVMi4LxQsQ41wbeISzx2TWrlvzhFAlMmHzFAS6spw7M16JUgudq9QwUeyTdFiwqg7l57ELynk1xBmeVbjIFS5y5Rd5n0TjmAtffOXap8XAhyqoj14trAA214x7-o_jnpHbO8Q_J7O-25oX5Fb9vV9uupcBXT8AJgOV2A |
| 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=Embedded+stacked+group+sparse+autoencoder+ensemble+with+L1+regularization+and+manifold+reduction&rft.jtitle=Applied+soft+computing&rft.au=Li%2C+Yongming&rft.au=Lei%2C+Yan&rft.au=Wang%2C+Pin&rft.au=Jiang%2C+Mingfeng&rft.date=2021-03-01&rft.pub=Elsevier+B.V&rft.issn=1568-4946&rft.eissn=1872-9681&rft.volume=101&rft_id=info:doi/10.1016%2Fj.asoc.2020.107003&rft.externalDocID=S156849462030942X |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1568-4946&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1568-4946&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1568-4946&client=summon |