Shallow neural network with kernel approximation for prediction problems in highly demanding data networks

[EN] Intrusion detection and network traffic classification are two of the main research applications of machine learning to highly demanding data networks e.g. IoT/sensors networks. These applications present new prediction challenges and strict requirements to the models applied for prediction. Th...

Descripción completa

Detalles Bibliográficos
Autores: Lopez-Martin, Manuel, Carro, Belén, Sánchez-Esguevillas, Antonio, Lloret, Jaime|||0000-0002-0862-0533
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/188470
Acceso en línea:https://riunet.upv.es/handle/10251/188470
Access Level:acceso abierto
Palabra clave:Shallow neural network
Kernel approximation
Intrusion detection
Network traffic classification
INGENIERIA TELEMATICA
id ES_fd453735c07f5d3e4e4fde68bed5d1d1
oai_identifier_str oai:riunet.upv.es:10251/188470
network_acronym_str ES
network_name_str España
repository_id_str
dc.title.none.fl_str_mv Shallow neural network with kernel approximation for prediction problems in highly demanding data networks
title Shallow neural network with kernel approximation for prediction problems in highly demanding data networks
spellingShingle Shallow neural network with kernel approximation for prediction problems in highly demanding data networks
Lopez-Martin, Manuel
Shallow neural network
Kernel approximation
Intrusion detection
Network traffic classification
INGENIERIA TELEMATICA
title_short Shallow neural network with kernel approximation for prediction problems in highly demanding data networks
title_full Shallow neural network with kernel approximation for prediction problems in highly demanding data networks
title_fullStr Shallow neural network with kernel approximation for prediction problems in highly demanding data networks
title_full_unstemmed Shallow neural network with kernel approximation for prediction problems in highly demanding data networks
title_sort Shallow neural network with kernel approximation for prediction problems in highly demanding data networks
dc.creator.none.fl_str_mv Lopez-Martin, Manuel
Carro, Belén
Sánchez-Esguevillas, Antonio
Lloret, Jaime|||0000-0002-0862-0533
author Lopez-Martin, Manuel
author_facet Lopez-Martin, Manuel
Carro, Belén
Sánchez-Esguevillas, Antonio
Lloret, Jaime|||0000-0002-0862-0533
author_role author
author2 Carro, Belén
Sánchez-Esguevillas, Antonio
Lloret, Jaime|||0000-0002-0862-0533
author2_role author
author
author
dc.contributor.none.fl_str_mv Departamento de Comunicaciones
Escuela Politécnica Superior de Gandia
Ministerio de Economía y Competitividad
Ministerio de Asuntos Económicos y Transformación Digital
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Shallow neural network
Kernel approximation
Intrusion detection
Network traffic classification
INGENIERIA TELEMATICA
topic Shallow neural network
Kernel approximation
Intrusion detection
Network traffic classification
INGENIERIA TELEMATICA
description [EN] Intrusion detection and network traffic classification are two of the main research applications of machine learning to highly demanding data networks e.g. IoT/sensors networks. These applications present new prediction challenges and strict requirements to the models applied for prediction. The models must be fast, accurate, flexible and capable of managing large datasets. They must be fast at the training, but mainly at the prediction phase, since inevitable environment changes require constant periodic training, and real-time prediction is mandatory. The models need to be accurate due to the consequences of prediction errors. They need also to be flexible and able to detect complex behaviors, usually encountered in non-linear models and, finally, training and prediction datasets are usually large due to traffic volumes. These requirements present conflicting solutions, between fast and simple shallow linear models and the slower and richer non-linear and deep learning models. Therefore, the perfect solution would be a mixture of both worlds. In this paper, we present such a solution made of a shallow neural network with linear activations plus a feature transformation based on kernel approximation algorithms which provide the necessary richness and non-linear behavior to the whole model. We have studied several kernel approximation algorithms: Nystrom, Random Fourier Features and Fastfood transformation and have applied them to three datasets related to intrusion detection and network traffic classification. This work presents the first application of a shallow linear model plus a kernel approximation to prediction problems with highly demanding network requirements. We show that the prediction performance obtained by these algorithms is positioned in the same range as the best non-linear classifiers, with a significant reduction in computational times, making them appropriate for new highly demanding networks. (C) 2019 Elsevier Ltd. All rights reserved.
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-06-15
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://riunet.upv.es/handle/10251/188470
url https://riunet.upv.es/handle/10251/188470
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Ministerio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 TIN2014-57991-C3-1-P DISTRIBUCION INTELIGENTE DE SERVICIOS MULTIMEDIA UTILIZANDO REDES COGNITIVAS ADAPTATIVAS DEFINIDAS POR SOFTWARE
Ministerio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 TIN2014-57991-C3-2-P INTELIGENCIA DISTRIBUIDA PARA EL CONTROL Y ADAPTACION DE REDES DINAMICAS DEFINIDAS POR SOFTWARE
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento - No comercial - Sin obra derivada (by-nc-nd)
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento - No comercial - Sin obra derivada (by-nc-nd)
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869425524067008512
spelling Shallow neural network with kernel approximation for prediction problems in highly demanding data networksLopez-Martin, ManuelCarro, BelénSánchez-Esguevillas, AntonioLloret, Jaime|||0000-0002-0862-0533Shallow neural networkKernel approximationIntrusion detectionNetwork traffic classificationINGENIERIA TELEMATICA[EN] Intrusion detection and network traffic classification are two of the main research applications of machine learning to highly demanding data networks e.g. IoT/sensors networks. These applications present new prediction challenges and strict requirements to the models applied for prediction. The models must be fast, accurate, flexible and capable of managing large datasets. They must be fast at the training, but mainly at the prediction phase, since inevitable environment changes require constant periodic training, and real-time prediction is mandatory. The models need to be accurate due to the consequences of prediction errors. They need also to be flexible and able to detect complex behaviors, usually encountered in non-linear models and, finally, training and prediction datasets are usually large due to traffic volumes. These requirements present conflicting solutions, between fast and simple shallow linear models and the slower and richer non-linear and deep learning models. Therefore, the perfect solution would be a mixture of both worlds. In this paper, we present such a solution made of a shallow neural network with linear activations plus a feature transformation based on kernel approximation algorithms which provide the necessary richness and non-linear behavior to the whole model. We have studied several kernel approximation algorithms: Nystrom, Random Fourier Features and Fastfood transformation and have applied them to three datasets related to intrusion detection and network traffic classification. This work presents the first application of a shallow linear model plus a kernel approximation to prediction problems with highly demanding network requirements. We show that the prediction performance obtained by these algorithms is positioned in the same range as the best non-linear classifiers, with a significant reduction in computational times, making them appropriate for new highly demanding networks. (C) 2019 Elsevier Ltd. All rights reserved.This work has been partially funded by the Ministerio de Economia y Competitividad del Gobierno de Espana and the Fondo de Desarrollo Regional (FEDER) within the project "Inteligencia distribuida para el control y adaptacion de redes dinamicas definidas por software, Ref: TIN2014-57991-C3-2-P", and the Project "Distribucion inteligente de servicios multimedia utilizando redes cognitivas adaptativas definidas por software, Ref: TIN2014-57991-C3-1-P", in the Programa Estatal de Fomento de la Investigacion Cientifica y Tecnica de Excelencia, Subprograma Estatal de Generacion de Conocimiento.ElsevierDepartamento de ComunicacionesEscuela Politécnica Superior de GandiaMinisterio de Economía y CompetitividadMinisterio de Asuntos Económicos y Transformación DigitalRepositorio Institucional de la Universitat Politècnica de València Riunet20192019-06-15journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfapplication/pdfhttps://riunet.upv.es/handle/10251/188470reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengMinisterio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 TIN2014-57991-C3-1-P DISTRIBUCION INTELIGENTE DE SERVICIOS MULTIMEDIA UTILIZANDO REDES COGNITIVAS ADAPTATIVAS DEFINIDAS POR SOFTWAREMinisterio de Economía y Competitividad http://dx.doi.org/10.13039/501100003329 TIN2014-57991-C3-2-P INTELIGENCIA DISTRIBUIDA PARA EL CONTROL Y ADAPTACION DE REDES DINAMICAS DEFINIDAS POR SOFTWAREopen accesshttp://purl.org/coar/access_right/c_abf2Reconocimiento - No comercial - Sin obra derivada (by-nc-nd) http://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:riunet.upv.es:10251/1884702026-06-13T07:49:27Z
score 15,301603

Similares en LA Referencia