Handling partially labeled network data: A semi-supervised approach using stacked sparse autoencoder

Network traffic analytics has become a crucial task in order to better understand and manage network resources, especially in the network softwarization era where the implementation of this concept can be done easily with network function virtualization. Currently, many approaches have been proposed...

Full description

Saved in:

Bibliographic Details
Published in:	Computer networks (Amsterdam, Netherlands : 1999) Vol. 207; pp. 108742 - 12
Main Authors:	Aouedi, Ons, Piamrat, Kandaraj, Bagadthey, Dhruvjyoti
Format:	Journal Article
Language:	English
Published:	Amsterdam Elsevier B.V 22.04.2022 Elsevier Sequoia S.A Elsevier
Subjects:	Artificial Intelligence Classification Communications traffic Computer Science Data Decision making Decision trees Deep learning Empirical analysis Feature extraction Labeling Learning Machine learning Multilayer perceptrons Multilayers Networks Partial information Performance enhancement Semi-supervised learning Stacked sparse autoencoder Support vector machines Traffic classification Traffic models Deep learning Partial information Semi-supervised learning Machine learning Feature extraction Traffic classification Stacked sparse autoencoder deep learning stacked sparse autoencoder feature extraction partial information semi-supervised learning traffic classification
ISSN:	1389-1286, 1872-7069
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Network traffic analytics has become a crucial task in order to better understand and manage network resources, especially in the network softwarization era where the implementation of this concept can be done easily with network function virtualization. Currently, many approaches have been proposed to improve the performance of traffic classification. However, as new types of traffic emerge every day (and they are generally not labeled), this opens a new challenge to be handled. Moreover, the question of how to accurately classify the traffic using a limited amount of labeled data or partially labeled data is also another important concern. In fact, labeling data is often difficult and time-consuming. In order to solve the previously described issues, we reformulate traffic classification into a semi-supervised learning where both supervised learning (using labeled data) and unsupervised learning (no label data) are combined. To do so, this paper presents a stacked sparse autoencoder (SSAE) based semi-supervised deep-learning model for traffic classification. The main motivations of this approach are: (i) unlabeled data is often abundant and easily available; (ii) classification performance of the whole model can be greatly improved when a large amount of unlabeled traffic is included in the training process; (iii) there is a limit to how much human effort can be thrown at the labeling problem. To investigate the performance of our approach, an empirical study has been conducted on a real dataset and results indicate that using a large amount of unlabeled data in the SSAE pre-trained phase can improve significantly the classification performance of the whole model. Furthermore, the proposed approach is compared against other representative machine-learning and deep-learning models, which are Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Multi-Layer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), and Autoencoder.
AbstractList	Network traffic analytics has become a crucial task in order to better understand and manage network resources, especially in the network softwarization era where the implementation of this concept can be done easily with network function virtualization. Currently, many approaches have been proposed to improve the performance of traffic classification. However, as new types of traffic emerge every day (and they are generally not labeled), this opens a new challenge to be handled. Moreover, the question of how to accurately classify the traffic using a limited amount of labeled data or partially labeled data is also another important concern. In fact, labeling data is often difficult and time-consuming. In order to solve the previously described issues, we reformulate traffic classification into a semi-supervised learning where both supervised learning (using labeled data) and unsupervised learning (no label data) are combined. To do so, this paper presents a stacked sparse autoencoder (SSAE) based semi-supervised deep-learning model for traffic classification. The main motivations of this approach are: (i) unlabeled data is often abundant and easily available; (ii) classification performance of the whole model can be greatly improved when a large amount of unlabeled traffic is included in the training process; (iii) there is a limit to how much human effort can be thrown at the labeling problem. To investigate the performance of our approach, an empirical study has been conducted on a real dataset and results indicate that using a large amount of unlabeled data in the SSAE pre-trained phase can improve significantly the classification performance of the whole model. Furthermore, the proposed approach is compared against other representative machine-learning and deep-learning models, which are Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Multi-Layer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), and Autoencoder. Network traffic analytics has become a crucial task in order to better understand and manage network resources, especially in the network softwarization era where the implementation of this concept can be done easily with network function virtualization. Currently, many approaches have been proposed to improve the performance of traffic classification. However, as new types of traffic emerge every day (and they are generally not labeled), this opens a new challenge to be handled. Moreover, the question of how to accurately classify traffic using a limited amount of labeled data or partially labeled data hence becomes another important concern. In fact, labeling data is often difficult and time-consuming. In order to tackle the previously described issues, we reformulate traffic classification into a semi-supervised learning where both supervised learning (using labeled data) and unsupervised learning (no label data) are combined. To do so, this paper presents a stacked sparse autoencoder (SSAE) based semi-supervised deep-learning model for traffic classification. The main motivations of this approach are: (i) unlabeled data is often abundant and easily available; (ii) classification performance of the whole model can be greatly improved when a large amount of unlabeled traffic is included in the training process; (iii) there is a limit to how much human effort can be thrown at the labeling problem. To investigate the performance of our approach, an empirical study has been conducted on a real dataset and results indicate that using a large amount of unlabeled data in the SSAE pre-trained phase can improve significantly the classification performance of the whole model. The proposed approach is compared against other representative machine-learning and deep-learning models, which are Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Multi-Layer Perceptron (MLP), eXtreme Gradient Boosting (XGBoost), and Autoencoder. Furthermore, we have also conducted experiments on a well-known dataset including encrypted traffic (containing only time-related features) to evaluate the generalization performance of the proposed model.
ArticleNumber	108742
Author	Bagadthey, Dhruvjyoti Piamrat, Kandaraj Aouedi, Ons
Author_xml	– sequence: 1 givenname: Ons orcidid: 0000-0002-2343-0850 surname: Aouedi fullname: Aouedi, Ons organization: University of Nantes, LS2N, 2 Chemin de la Houssinière, Nantes, France – sequence: 2 givenname: Kandaraj orcidid: 0000-0002-4350-0254 surname: Piamrat fullname: Piamrat, Kandaraj email: kandaraj.piamrat@univ-nantes.fr organization: University of Nantes, LS2N, 2 Chemin de la Houssinière, Nantes, France – sequence: 3 givenname: Dhruvjyoti surname: Bagadthey fullname: Bagadthey, Dhruvjyoti organization: Department of Electrical Engineering, IIT Madras, Chennai 600036, Chennai, India
BackLink	https://hal.science/hal-03524935$$DView record in HAL
BookMark	eNqFkE1v1DAQhi3USvSDf8AhEicOWTyOEyc9IK0qyiKtxAXO1sSeUG-zcbCdRf339SqIAwc42Rq_76Pxc80uJj8RY2-Bb4BD8-GwMf44UdoILiCPWiXFK3YFrRKl4k13ke9V25Ug2uY1u47xwDmXUrRXzO5wsqObfhQzhuRwHJ-LEXsayRaZ-MuHp8JiwrtiW0Q6ujIuM4WTi_kd5zl4NI_FEs-AmNA85XHMpEgFLsnTZLylcMsuBxwjvfl93rDvD5--3e_K_dfPX-63-9JIkKkEM5ARfY89QDv02KjeNFBXvWqbSvDaDi0YqZTsuqqmTsoKrWnQ2p5sx-uhumHvV-4jjnoO7ojhWXt0erfd6_OMV7WQuXyCnH23ZvMffi4Ukz74JUx5PS0UB5CgeJVTck2Z4GMMNPzBAtdn9_qgV_f67F6v7nPt7q-acQmT81MK6Mb_lT-uZcqqTo6CjsZlk2RdIJO09e7fgBd13KUY
CitedBy_id	crossref_primary_10_3390_e25091274 crossref_primary_10_1016_j_comnet_2023_109990 crossref_primary_10_1002_cpe_8223 crossref_primary_10_1016_j_jmsy_2025_08_009 crossref_primary_10_1016_j_buildenv_2023_110718 crossref_primary_10_1007_s00521_023_08668_w crossref_primary_10_1016_j_chemosphere_2022_136046 crossref_primary_10_3390_app12136617
Cites_doi	10.1109/ICNP49622.2020.9259390 10.1109/MASS.2016.016 10.1016/j.comnet.2021.107840 10.1016/j.comcom.2021.01.021 10.1145/3065386 10.1109/MNET.2018.1800078 10.1109/ACCESS.2018.2872430 10.1016/j.comnet.2021.107974 10.1109/ICNP.2016.7785327 10.1016/j.comnet.2018.01.007 10.1109/COMST.2018.2883147 10.1109/ICCWorkshops50388.2021.9473580 10.1016/j.cmpb.2018.10.004 10.5220/0005740704070414 10.1007/978-3-319-95168-3_37 10.1016/j.inffus.2017.10.006 10.1109/COMST.2018.2866942 10.1109/ICSAI.2014.7009372 10.1016/j.measurement.2016.04.007 10.1038/s41598-019-55320-6 10.1109/TKDE.2008.239 10.1145/1390156.1390294 10.1109/ACCESS.2018.2858277 10.1109/SCC.2016.133 10.1016/j.jnca.2020.102890 10.1016/j.neucom.2015.09.116
ContentType	Journal Article
Copyright	2022 Elsevier B.V. Copyright Elsevier Sequoia S.A. Apr 22, 2022 Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml	– notice: 2022 Elsevier B.V. – notice: Copyright Elsevier Sequoia S.A. Apr 22, 2022 – notice: Distributed under a Creative Commons Attribution 4.0 International License
DBID	AAYXX CITATION 7SC 8FD E3H F2A JQ2 L7M L~C L~D 1XC VOOES
DOI	10.1016/j.comnet.2021.108742
DatabaseName	CrossRef Computer and Information Systems Abstracts Technology Research Database Library & Information Sciences Abstracts (LISA) Library & Information Science Abstracts (LISA) ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access)
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Library and Information Science Abstracts (LISA) ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Technology Research Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1872-7069
EndPage	12
ExternalDocumentID	oai:HAL:hal-03524935v1 10_1016_j_comnet_2021_108742 S1389128621005909
GroupedDBID	--K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5GY 5VS 6OB 7-5 71M 77K 8P~ AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAXUO AAYFN ABBOA ABMAC ABYKQ ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD AXJTR BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 FDB FEDTE FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HVGLF IHE J1W JJJVA KOM M41 MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 PC. PQQKQ Q38 ROL RPZ RXW SDF SDG SDP SES SPC SPCBC SST SSV SSZ T5K TAE TN5 ZMT ~G- 29F 77I 9DU AATTM AAXKI AAYWO AAYXX ABFNM ABJNI ABXDB ACLOT ACNNM ACVFH ADCNI ADJOM AEIPS AEUPX AFJKZ AFPUW AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS EJD F0J FGOYB HZ~ R2- SEW ZY4 ~HD 7SC 8FD E3H F2A JQ2 L7M L~C L~D 1XC VOOES
ID	FETCH-LOGICAL-c414t-1cfec2bbab118fba67bc6153b7863205df81c47749935e9443adc6addbed905f3
ISICitedReferencesCount	8
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000782963500006&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1389-1286
IngestDate	Tue Oct 14 20:19:19 EDT 2025 Fri Nov 14 18:44:40 EST 2025 Sat Nov 29 07:00:12 EST 2025 Tue Nov 18 22:36:44 EST 2025 Fri Feb 23 02:41:04 EST 2024
IsDoiOpenAccess	true
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Keywords	Deep learning Partial information Semi-supervised learning Machine learning Feature extraction Traffic classification Stacked sparse autoencoder deep learning stacked sparse autoencoder feature extraction partial information semi-supervised learning traffic classification
Language	English
License	Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c414t-1cfec2bbab118fba67bc6153b7863205df81c47749935e9443adc6addbed905f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-4350-0254 0000-0002-2343-0850
OpenAccessLink	https://hal.science/hal-03524935
PQID	2701141703
PQPubID	47119
PageCount	12
ParticipantIDs	hal_primary_oai_HAL_hal_03524935v1 proquest_journals_2701141703 crossref_primary_10_1016_j_comnet_2021_108742 crossref_citationtrail_10_1016_j_comnet_2021_108742 elsevier_sciencedirect_doi_10_1016_j_comnet_2021_108742
PublicationCentury	2000
PublicationDate	2022-04-22
PublicationDateYYYYMMDD	2022-04-22
PublicationDate_xml	– month: 04 year: 2022 text: 2022-04-22 day: 22
PublicationDecade	2020
PublicationPlace	Amsterdam
PublicationPlace_xml	– name: Amsterdam
PublicationTitle	Computer networks (Amsterdam, Netherlands : 1999)
PublicationYear	2022
Publisher	Elsevier B.V Elsevier Sequoia S.A Elsevier
Publisher_xml	– name: Elsevier B.V – name: Elsevier Sequoia S.A – name: Elsevier
References	D’Angelo, Palmieri (b26) 2021; 173 M. Uddin, T. Nadeem, TrafficVision: A case for pushing software defined networks to wireless edges, in: Proceedings Of The 13th International Conference On Mobile Ad Hoc And Sensor Systems, Brasilia, Brazil, MASS, 2016, pp. 37–46. Camelo, Shahid, Fontaine, de Figueiredo, De Poorter, Moerman, Latre (b12) 2019 Sagheer, Kotb (b14) 2019; 9 Krizhevsky, Sutskever, Hinton (b33) 2017; 60 Li, Chen, Yang, Gao, Zhang, Deen (b25) 2018; 32 Yan, Han (b17) 2018; 6 Zhang, Yang, Chen, Li (b8) 2018; 42 Xie, Yu, Huang, Xie, Liu, Wang, Liu (b18) 2018; 21 Srivastava, Hinton, Krizhevsky, Sutskever, Salakhutdinov (b28) 2014; 15 Barut, Luo, Zhang, Li, Li (b2) 2020 Pacheco, Exposito, Gineste, Baudoin, Aguilar (b9) 2018; 21 Lin, Xu, Gao (b37) 2021; 190 Shi, Li, Zhang, Cheng, Cao (b3) 2018; 132 Y. Li, J. Li, MultiClassifier: A combination of DPI and ML for application-layer classification in SDN, in: Proceedings Of The 2nd International Conference On Systems And Informatics, Shanghai, China, ICSAI, Shanghai, China, 2014, pp. 682–686. G. Draper-Gil, A.H. Lashkari, M.S.I. Mamun, A.A. Ghorbani, Characterization of encrypted and vpn traffic using time-related, in: Proceedings Of The 2nd International Conference On Information Systems Security And Privacy, ICISSP, 2016, pp. 407–414. P. Vincent, H. Larochelle, Y. Bengio, P.-A. Manzagol, Extracting and composing robust features with denoising autoencoders, in: Proceedings Of The 25th International Conference On Machine Learning, 2008, pp. 1096–1103. P. Amaral, J. Dinis, P. Pinto, L. Bernardo, J. Tavares, H.S. Mamede, Machine learning in software defined networks: Data collection and traffic classification, in: Proceedings Of The 24th International Conference On Network Protocols, Singapore, ICNP, 2016, pp. 1–5. He, Garcia (b31) 2009; 21 O. Aouedi, K. Piamrat, D. Bagadthey, A Semi-supervised Stacked Autoencoder Approach for Network Traffic Classification, in: Proceedings Of The 28th International Conference On Network Protocols (ICNP) HDR-Nets Workshop, Madrid, Spain, 2020. J.S. Rojas, Á.R. Gallón, J.C. Corrales, Personalized service degradation policies on OTT applications based on the consumption behavior of users, in: Proceedings Of The International Conference On Computational Science And Its Applications, Melbourne, Australia, 2018, pp. 543–557. Abbasi, Shahraki, Taherkordi (b10) 2021 Hinton, Srivastava, Krizhevsky, Sutskever, Salakhutdinov (b29) 2012 Xiao, Wu, Lin, Zhao (b15) 2018; 166 Sun, Shao, Zhao, Yan, Zhang, Chen (b16) 2016; 89 Vincent, Larochelle, Lajoie, Bengio, Manzagol, Bottou (b30) 2010; 11 Kilincer, Ertam, Sengur (b35) 2021 (b1) 2019 Erhan, Courville, Bengio, Vincent (b13) 2010 Guo, Liu, Oerlemans, Lao, Wu, Lew (b27) 2016; 187 Yao, Liu, Zhang, Wu, Jiang, Yu (b38) 2019 Zhao, Zhang, Sang (b22) 2019 De Schepper, Camelo, Famaey, Latré (b11) 2020; 30 O. Aouedi, K. Piamrat, B. Parrein, Performance evaluation of feature selection and tree-based algorithms for traffic classification, in: 2021 IEEE International Conference On Communications (ICC) DDINS Workshop, Montreal, Canada, 2021. Wang, Ye, Chen, Qian (b21) 2018; 6 Hady, Schwenker (b5) 2013 Zhang, Wang, Li, He, Huang (b23) 2018; 29 Rezaei, Liu (b39) 2020 P. Wang, S.-C. Lin, M. Luo, A framework for QoS-aware traffic classification using semi-supervised machine learning in SDNs, in: Proceedings Of The IEEE International Conference On Services Computing, San Francisco, CA, USA, SCC, 2016, pp. 760–765. Sun (10.1016/j.comnet.2021.108742_b16) 2016; 89 D’Angelo (10.1016/j.comnet.2021.108742_b26) 2021; 173 Shi (10.1016/j.comnet.2021.108742_b3) 2018; 132 Sagheer (10.1016/j.comnet.2021.108742_b14) 2019; 9 Guo (10.1016/j.comnet.2021.108742_b27) 2016; 187 Kilincer (10.1016/j.comnet.2021.108742_b35) 2021 10.1016/j.comnet.2021.108742_b20 Krizhevsky (10.1016/j.comnet.2021.108742_b33) 2017; 60 Pacheco (10.1016/j.comnet.2021.108742_b9) 2018; 21 Yan (10.1016/j.comnet.2021.108742_b17) 2018; 6 Yao (10.1016/j.comnet.2021.108742_b38) 2019 10.1016/j.comnet.2021.108742_b19 He (10.1016/j.comnet.2021.108742_b31) 2009; 21 Hinton (10.1016/j.comnet.2021.108742_b29) 2012 Lin (10.1016/j.comnet.2021.108742_b37) 2021; 190 Rezaei (10.1016/j.comnet.2021.108742_b39) 2020 Zhang (10.1016/j.comnet.2021.108742_b8) 2018; 42 Xiao (10.1016/j.comnet.2021.108742_b15) 2018; 166 10.1016/j.comnet.2021.108742_b36 Li (10.1016/j.comnet.2021.108742_b25) 2018; 32 Hady (10.1016/j.comnet.2021.108742_b5) 2013 Wang (10.1016/j.comnet.2021.108742_b21) 2018; 6 De Schepper (10.1016/j.comnet.2021.108742_b11) 2020; 30 10.1016/j.comnet.2021.108742_b34 10.1016/j.comnet.2021.108742_b32 Zhang (10.1016/j.comnet.2021.108742_b23) 2018; 29 Zhao (10.1016/j.comnet.2021.108742_b22) 2019 Vincent (10.1016/j.comnet.2021.108742_b30) 2010; 11 10.1016/j.comnet.2021.108742_b4 Abbasi (10.1016/j.comnet.2021.108742_b10) 2021 Erhan (10.1016/j.comnet.2021.108742_b13) 2010 10.1016/j.comnet.2021.108742_b24 Barut (10.1016/j.comnet.2021.108742_b2) 2020 10.1016/j.comnet.2021.108742_b7 Camelo (10.1016/j.comnet.2021.108742_b12) 2019 Xie (10.1016/j.comnet.2021.108742_b18) 2018; 21 10.1016/j.comnet.2021.108742_b6 Srivastava (10.1016/j.comnet.2021.108742_b28) 2014; 15 (10.1016/j.comnet.2021.108742_b1) 2019
References_xml	– volume: 21 start-page: 1988 year: 2018 end-page: 2014 ident: b9 article-title: Towards the deployment of machine learning solutions in network traffic classification: A systematic survey publication-title: IEEE Commun. Surv. Tutor. – volume: 190 year: 2021 ident: b37 article-title: TSCRNN: A novel classification scheme of encrypted traffic based on flow spatiotemporal features for efficient management of IIoT publication-title: Comput. Netw. – year: 2021 ident: b10 article-title: Deep learning for network traffic monitoring and analysis (NTMA): A survey publication-title: Comput. Commun. – volume: 6 start-page: 41238 year: 2018 end-page: 41248 ident: b17 article-title: Effective feature extraction via stacked sparse autoencoder to improve intrusion detection system publication-title: IEEE Access – start-page: 1 year: 2020 end-page: 9 ident: b39 article-title: Multitask learning for network traffic classification publication-title: 2020 29th International Conference On Computer Communications And Networks – volume: 166 start-page: 99 year: 2018 end-page: 105 ident: b15 article-title: A semi-supervised deep learning method based on stacked sparse auto-encoder for cancer prediction using RNA-seq data publication-title: Comput. Methods Programs Biomed. – year: 2012 ident: b29 article-title: Improving neural networks by preventing co-adaptation of feature detectors – start-page: 201 year: 2010 end-page: 208 ident: b13 article-title: Why does unsupervised pre-training help deep learning? publication-title: Proceedings Of The Thirteenth International Conference On Artificial Intelligence And Statistics – volume: 21 start-page: 393 year: 2018 end-page: 430 ident: b18 article-title: A survey of machine learning techniques applied to software defined networking (SDN): Research issues and challenges publication-title: IEEE Commun. Surv. Tutor. – start-page: 1 year: 2019 end-page: 10 ident: b12 article-title: A semi-supervised learning approach towards automatic wireless technology recognition publication-title: 2019 IEEE International Symposium On Dynamic Spectrum Access Networks – volume: 42 start-page: 146 year: 2018 end-page: 157 ident: b8 article-title: A survey on deep learning for big data publication-title: Inf. Fusion – reference: P. Amaral, J. Dinis, P. Pinto, L. Bernardo, J. Tavares, H.S. Mamede, Machine learning in software defined networks: Data collection and traffic classification, in: Proceedings Of The 24th International Conference On Network Protocols, Singapore, ICNP, 2016, pp. 1–5. – volume: 60 start-page: 84 year: 2017 end-page: 90 ident: b33 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM – volume: 187 start-page: 27 year: 2016 end-page: 48 ident: b27 article-title: Deep learning for visual understanding: A review publication-title: Neurocomputing – volume: 132 start-page: 81 year: 2018 end-page: 98 ident: b3 article-title: An efficient feature generation approach based on deep learning and feature selection techniques for traffic classification publication-title: Comput. Netw. – volume: 89 start-page: 171 year: 2016 end-page: 178 ident: b16 article-title: A sparse auto-encoder-based deep neural network approach for induction motor faults classification publication-title: Measurement – start-page: 85 year: 2019 end-page: 89 ident: b22 article-title: Towards unknown traffic identification via embeddings and deep autoencoders publication-title: 2019 26th International Conference On Telecommunications – reference: O. Aouedi, K. Piamrat, B. Parrein, Performance evaluation of feature selection and tree-based algorithms for traffic classification, in: 2021 IEEE International Conference On Communications (ICC) DDINS Workshop, Montreal, Canada, 2021. – year: 2019 ident: b1 article-title: Cisco visual networking index: Global mobile data traffic forecast update, 2017–2022 white paper, Cisco – start-page: 215 year: 2013 end-page: 239 ident: b5 article-title: Semi-supervised learning publication-title: Handbook On Neural Information Processing – volume: 9 start-page: 1 year: 2019 end-page: 16 ident: b14 article-title: Unsupervised pre-training of a deep LSTM-based stacked autoencoder for multivariate time series forecasting problems publication-title: Sci. Rep. – reference: P. Vincent, H. Larochelle, Y. Bengio, P.-A. Manzagol, Extracting and composing robust features with denoising autoencoders, in: Proceedings Of The 25th International Conference On Machine Learning, 2008, pp. 1096–1103. – year: 2020 ident: b2 article-title: NetML: A challenge for network traffic analytics – reference: O. Aouedi, K. Piamrat, D. Bagadthey, A Semi-supervised Stacked Autoencoder Approach for Network Traffic Classification, in: Proceedings Of The 28th International Conference On Network Protocols (ICNP) HDR-Nets Workshop, Madrid, Spain, 2020. – volume: 173 year: 2021 ident: b26 article-title: Network traffic classification using deep convolutional recurrent autoencoder neural networks for spatial–temporal features extraction publication-title: J. Netw. Comput. Appl. – volume: 6 start-page: 55380 year: 2018 end-page: 55391 ident: b21 article-title: Datanet: Deep learning based encrypted network traffic classification in sdn home gateway publication-title: IEEE Access – volume: 29 year: 2018 ident: b23 article-title: Deep learning-based network application classification for SDN publication-title: Trans. Emerg. Telecommun. Technol. – volume: 32 start-page: 22 year: 2018 end-page: 27 ident: b25 article-title: An improved stacked auto-encoder for network traffic flow classification publication-title: IEEE Netw. – volume: 15 start-page: 1929 year: 2014 end-page: 1958 ident: b28 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – volume: 30 year: 2020 ident: b11 article-title: Traffic classification at the radio spectrum level using deep learning models trained with synthetic data publication-title: Int. J. Netw. Manag. – reference: Y. Li, J. Li, MultiClassifier: A combination of DPI and ML for application-layer classification in SDN, in: Proceedings Of The 2nd International Conference On Systems And Informatics, Shanghai, China, ICSAI, Shanghai, China, 2014, pp. 682–686. – volume: 21 start-page: 1263 year: 2009 end-page: 1284 ident: b31 article-title: Learning from imbalanced data publication-title: IEEE Trans. Knowl. Data Eng. – reference: M. Uddin, T. Nadeem, TrafficVision: A case for pushing software defined networks to wireless edges, in: Proceedings Of The 13th International Conference On Mobile Ad Hoc And Sensor Systems, Brasilia, Brazil, MASS, 2016, pp. 37–46. – reference: J.S. Rojas, Á.R. Gallón, J.C. Corrales, Personalized service degradation policies on OTT applications based on the consumption behavior of users, in: Proceedings Of The International Conference On Computational Science And Its Applications, Melbourne, Australia, 2018, pp. 543–557. – year: 2019 ident: b38 article-title: Identification of encrypted traffic through attention mechanism based long short term memory publication-title: IEEE Trans. Big Data – volume: 11 year: 2010 ident: b30 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J. Mach. Learn. Res. – reference: P. Wang, S.-C. Lin, M. Luo, A framework for QoS-aware traffic classification using semi-supervised machine learning in SDNs, in: Proceedings Of The IEEE International Conference On Services Computing, San Francisco, CA, USA, SCC, 2016, pp. 760–765. – year: 2021 ident: b35 article-title: Machine learning methods for cyber security intrusion detection: Datasets and comparative study publication-title: Comput. Netw. – reference: G. Draper-Gil, A.H. Lashkari, M.S.I. Mamun, A.A. Ghorbani, Characterization of encrypted and vpn traffic using time-related, in: Proceedings Of The 2nd International Conference On Information Systems Security And Privacy, ICISSP, 2016, pp. 407–414. – ident: 10.1016/j.comnet.2021.108742_b6 doi: 10.1109/ICNP49622.2020.9259390 – year: 2019 ident: 10.1016/j.comnet.2021.108742_b1 – ident: 10.1016/j.comnet.2021.108742_b19 doi: 10.1109/MASS.2016.016 – year: 2021 ident: 10.1016/j.comnet.2021.108742_b35 article-title: Machine learning methods for cyber security intrusion detection: Datasets and comparative study publication-title: Comput. Netw. doi: 10.1016/j.comnet.2021.107840 – year: 2021 ident: 10.1016/j.comnet.2021.108742_b10 article-title: Deep learning for network traffic monitoring and analysis (NTMA): A survey publication-title: Comput. Commun. doi: 10.1016/j.comcom.2021.01.021 – volume: 60 start-page: 84 issue: 6 year: 2017 ident: 10.1016/j.comnet.2021.108742_b33 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. ACM doi: 10.1145/3065386 – volume: 32 start-page: 22 issue: 6 year: 2018 ident: 10.1016/j.comnet.2021.108742_b25 article-title: An improved stacked auto-encoder for network traffic flow classification publication-title: IEEE Netw. doi: 10.1109/MNET.2018.1800078 – start-page: 85 year: 2019 ident: 10.1016/j.comnet.2021.108742_b22 article-title: Towards unknown traffic identification via embeddings and deep autoencoders – year: 2012 ident: 10.1016/j.comnet.2021.108742_b29 – volume: 6 start-page: 55380 year: 2018 ident: 10.1016/j.comnet.2021.108742_b21 article-title: Datanet: Deep learning based encrypted network traffic classification in sdn home gateway publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2872430 – volume: 190 year: 2021 ident: 10.1016/j.comnet.2021.108742_b37 article-title: TSCRNN: A novel classification scheme of encrypted traffic based on flow spatiotemporal features for efficient management of IIoT publication-title: Comput. Netw. doi: 10.1016/j.comnet.2021.107974 – ident: 10.1016/j.comnet.2021.108742_b20 doi: 10.1109/ICNP.2016.7785327 – volume: 132 start-page: 81 year: 2018 ident: 10.1016/j.comnet.2021.108742_b3 article-title: An efficient feature generation approach based on deep learning and feature selection techniques for traffic classification publication-title: Comput. Netw. doi: 10.1016/j.comnet.2018.01.007 – start-page: 215 year: 2013 ident: 10.1016/j.comnet.2021.108742_b5 article-title: Semi-supervised learning – volume: 21 start-page: 1988 issue: 2 year: 2018 ident: 10.1016/j.comnet.2021.108742_b9 article-title: Towards the deployment of machine learning solutions in network traffic classification: A systematic survey publication-title: IEEE Commun. Surv. Tutor. doi: 10.1109/COMST.2018.2883147 – volume: 11 issue: 12 year: 2010 ident: 10.1016/j.comnet.2021.108742_b30 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: J. Mach. Learn. Res. – ident: 10.1016/j.comnet.2021.108742_b34 doi: 10.1109/ICCWorkshops50388.2021.9473580 – year: 2020 ident: 10.1016/j.comnet.2021.108742_b2 – volume: 166 start-page: 99 year: 2018 ident: 10.1016/j.comnet.2021.108742_b15 article-title: A semi-supervised deep learning method based on stacked sparse auto-encoder for cancer prediction using RNA-seq data publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2018.10.004 – ident: 10.1016/j.comnet.2021.108742_b36 doi: 10.5220/0005740704070414 – ident: 10.1016/j.comnet.2021.108742_b32 doi: 10.1007/978-3-319-95168-3_37 – start-page: 1 year: 2020 ident: 10.1016/j.comnet.2021.108742_b39 article-title: Multitask learning for network traffic classification – volume: 42 start-page: 146 year: 2018 ident: 10.1016/j.comnet.2021.108742_b8 article-title: A survey on deep learning for big data publication-title: Inf. Fusion doi: 10.1016/j.inffus.2017.10.006 – volume: 21 start-page: 393 issue: 1 year: 2018 ident: 10.1016/j.comnet.2021.108742_b18 article-title: A survey of machine learning techniques applied to software defined networking (SDN): Research issues and challenges publication-title: IEEE Commun. Surv. Tutor. doi: 10.1109/COMST.2018.2866942 – ident: 10.1016/j.comnet.2021.108742_b4 doi: 10.1109/ICSAI.2014.7009372 – start-page: 1 year: 2019 ident: 10.1016/j.comnet.2021.108742_b12 article-title: A semi-supervised learning approach towards automatic wireless technology recognition – volume: 89 start-page: 171 year: 2016 ident: 10.1016/j.comnet.2021.108742_b16 article-title: A sparse auto-encoder-based deep neural network approach for induction motor faults classification publication-title: Measurement doi: 10.1016/j.measurement.2016.04.007 – volume: 30 issue: 4 year: 2020 ident: 10.1016/j.comnet.2021.108742_b11 article-title: Traffic classification at the radio spectrum level using deep learning models trained with synthetic data publication-title: Int. J. Netw. Manag. – volume: 29 issue: 5 year: 2018 ident: 10.1016/j.comnet.2021.108742_b23 article-title: Deep learning-based network application classification for SDN publication-title: Trans. Emerg. Telecommun. Technol. – volume: 9 start-page: 1 issue: 1 year: 2019 ident: 10.1016/j.comnet.2021.108742_b14 article-title: Unsupervised pre-training of a deep LSTM-based stacked autoencoder for multivariate time series forecasting problems publication-title: Sci. Rep. doi: 10.1038/s41598-019-55320-6 – volume: 21 start-page: 1263 issue: 9 year: 2009 ident: 10.1016/j.comnet.2021.108742_b31 article-title: Learning from imbalanced data publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2008.239 – ident: 10.1016/j.comnet.2021.108742_b24 doi: 10.1145/1390156.1390294 – year: 2019 ident: 10.1016/j.comnet.2021.108742_b38 article-title: Identification of encrypted traffic through attention mechanism based long short term memory publication-title: IEEE Trans. Big Data – volume: 15 start-page: 1929 issue: 1 year: 2014 ident: 10.1016/j.comnet.2021.108742_b28 article-title: Dropout: a simple way to prevent neural networks from overfitting publication-title: J. Mach. Learn. Res. – start-page: 201 year: 2010 ident: 10.1016/j.comnet.2021.108742_b13 article-title: Why does unsupervised pre-training help deep learning? – volume: 6 start-page: 41238 year: 2018 ident: 10.1016/j.comnet.2021.108742_b17 article-title: Effective feature extraction via stacked sparse autoencoder to improve intrusion detection system publication-title: IEEE Access doi: 10.1109/ACCESS.2018.2858277 – ident: 10.1016/j.comnet.2021.108742_b7 doi: 10.1109/SCC.2016.133 – volume: 173 year: 2021 ident: 10.1016/j.comnet.2021.108742_b26 article-title: Network traffic classification using deep convolutional recurrent autoencoder neural networks for spatial–temporal features extraction publication-title: J. Netw. Comput. Appl. doi: 10.1016/j.jnca.2020.102890 – volume: 187 start-page: 27 year: 2016 ident: 10.1016/j.comnet.2021.108742_b27 article-title: Deep learning for visual understanding: A review publication-title: Neurocomputing doi: 10.1016/j.neucom.2015.09.116
SSID	ssj0004428
Score	2.431366
Snippet	Network traffic analytics has become a crucial task in order to better understand and manage network resources, especially in the network softwarization era...
SourceID	hal proquest crossref elsevier
SourceType	Open Access Repository Aggregation Database Enrichment Source Index Database Publisher
StartPage	108742
SubjectTerms	Artificial Intelligence Classification Communications traffic Computer Science Data Decision making Decision trees Deep learning Empirical analysis Feature extraction Labeling Learning Machine learning Multilayer perceptrons Multilayers Networks Partial information Performance enhancement Semi-supervised learning Stacked sparse autoencoder Support vector machines Traffic classification Traffic models
Title	Handling partially labeled network data: A semi-supervised approach using stacked sparse autoencoder
URI	https://dx.doi.org/10.1016/j.comnet.2021.108742 https://www.proquest.com/docview/2701141703 https://hal.science/hal-03524935
Volume	207
WOSCitedRecordID	wos000782963500006&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: 1872-7069 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004428 issn: 1389-1286 databaseCode: AIEXJ dateStart: 19990114 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6jQd4QFxFYSAL8RYFNYlTx7xVaKigaUxiSH2L7Nhlrdq0appq-xf8ZM6J7bRqhQZIvESt69itzxefS8_5TMg7JZICmdBC2OuykCWGh6Kv4G0vlYnuMx2phmf2nF9cZKORuOx0fvpamM2Ml2V2cyOW_1XU0AbCxtLZvxB3Oyg0wGsQOlxB7HD9I8EPkTehqTHHD-VsdhuApEG76KC0Od8BpoXakvTKzCdhVS9xx6igh6cYD-rKBRrgKdcBbDurygSyXi-Q-FK7lF7PcOBOhvDjN4HcwRwpGLTD27as2MUghNiNQSxq0KHY8WvZ2viXEzkHeNqUDwx3yOk27PpDahjRZgBcr-rN9HaxnuxGMMD57bEw3vq7h6U1zU4MllQIytPxZNu2jIM70LNnu_jtO7an5h6oAhuVmKIk4de_h4kjTKjklsxrj2T7W_N_LcwGHjCW44ojchLzVGTH5GTw-Wz0ZVtry5rzetuv58sxm5zBw7l-Z-4cXWPe7Z76b2yaq0fkoXNG6MCC6DHpmPIJebBDUfmUaA8n2sKJOjhRJ26KcPpAB3QPTNSDiTZgog5M1IKJ7oDpGfn-6ezq4zB0J3OEBYvYOoyKsSlipaQC_3SsZJ-rAj0HxbN-EvdSPc6igoFnAdZvagRjidRFH1SpMlr00nHynByXi9K8IBTJhkRsYCk5mMKGZVqqDGzKFBRDVHDZJYlfwLxwtPV4esos9_mJ09wue47Lnttl75KwvWtpaVvu6M-9bHJnelqTMgc43XHnWxBlOwmytQ8H5zm2IdUwgwXYRF1y6iWdu62iymOOwYgIVO7Lf579Fbm_faJOyfF6VZvX5F6xWU-q1RuH3V8OscC5
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=Handling+partially+labeled+network+data%3A+A+semi-supervised+approach+using+stacked+sparse+autoencoder&rft.jtitle=Computer+networks+%28Amsterdam%2C+Netherlands+%3A+1999%29&rft.au=Aouedi%2C+Ons&rft.au=Piamrat%2C+Kandaraj&rft.au=Bagadthey%2C+Dhruvjyoti&rft.date=2022-04-22&rft.pub=Elsevier+B.V&rft.issn=1389-1286&rft.eissn=1872-7069&rft.volume=207&rft_id=info:doi/10.1016%2Fj.comnet.2021.108742&rft.externalDocID=S1389128621005909
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1389-1286&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1389-1286&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1389-1286&client=summon