An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine

Extreme learning machine (ELM) is a novel single-hidden layer feedforward neural network to obtain fast learning speed by randomly initializing weights and deviations. Due to its extremely fast learning speed, it has been widely used in training of massive data in recent years. In order to adapt to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yanqiang Tang, Chenghai Li
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Online regularized extreme learning machine sequential learning intrusion detection improved particle swarm optimization network security Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/c609ef3cb6e14ed38b13afbbd18d4aee
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:c609ef3cb6e14ed38b13afbbd18d4aee
record_format	dspace
spelling	oai:doaj.org-article:c609ef3cb6e14ed38b13afbbd18d4aee2021-11-19T00:06:52ZAn Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine2169-353610.1109/ACCESS.2021.3093313https://doaj.org/article/c609ef3cb6e14ed38b13afbbd18d4aee2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9467307/https://doaj.org/toc/2169-3536Extreme learning machine (ELM) is a novel single-hidden layer feedforward neural network to obtain fast learning speed by randomly initializing weights and deviations. Due to its extremely fast learning speed, it has been widely used in training of massive data in recent years. In order to adapt to the real network environment, based on the ELM, we propose an improved particle swarm optimized online regularized extreme learning machine (IPSO-IRELM) intrusion detection algorithm model. First, the model replaces the traditional batch learning with sequential learning by dynamically adapting the new data obtained in the training network instead of training all collected samples in an offline manner; second, we improve the particle swarm optimization algorithm and compare it with typical improved algorithms to prove its effectiveness; finally, to solve the random initialization problem of IRELM, we use IPSO to optimize the initial weights and deviations of IRELM to improve the classification ability of IRELM. The experimental results show that IPSO-IRELM algorithm has better generalization ability, which not only improves the accuracy of intrusion detection, but also has certain recognition ability for minority class samples.Yanqiang TangChenghai LiIEEEarticleOnline regularized extreme learning machinesequential learningintrusion detectionimproved particle swarm optimizationnetwork securityElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 94826-94844 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Online regularized extreme learning machine sequential learning intrusion detection improved particle swarm optimization network security Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Online regularized extreme learning machine sequential learning intrusion detection improved particle swarm optimization network security Electrical engineering. Electronics. Nuclear engineering TK1-9971 Yanqiang Tang Chenghai Li An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine
description	Extreme learning machine (ELM) is a novel single-hidden layer feedforward neural network to obtain fast learning speed by randomly initializing weights and deviations. Due to its extremely fast learning speed, it has been widely used in training of massive data in recent years. In order to adapt to the real network environment, based on the ELM, we propose an improved particle swarm optimized online regularized extreme learning machine (IPSO-IRELM) intrusion detection algorithm model. First, the model replaces the traditional batch learning with sequential learning by dynamically adapting the new data obtained in the training network instead of training all collected samples in an offline manner; second, we improve the particle swarm optimization algorithm and compare it with typical improved algorithms to prove its effectiveness; finally, to solve the random initialization problem of IRELM, we use IPSO to optimize the initial weights and deviations of IRELM to improve the classification ability of IRELM. The experimental results show that IPSO-IRELM algorithm has better generalization ability, which not only improves the accuracy of intrusion detection, but also has certain recognition ability for minority class samples.
format	article
author	Yanqiang Tang Chenghai Li
author_facet	Yanqiang Tang Chenghai Li
author_sort	Yanqiang Tang
title	An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine
title_short	An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine
title_full	An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine
title_fullStr	An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine
title_full_unstemmed	An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine
title_sort	online network intrusion detection model based on improved regularized extreme learning machine
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/c609ef3cb6e14ed38b13afbbd18d4aee
work_keys_str_mv	AT yanqiangtang anonlinenetworkintrusiondetectionmodelbasedonimprovedregularizedextremelearningmachine AT chenghaili anonlinenetworkintrusiondetectionmodelbasedonimprovedregularizedextremelearningmachine AT yanqiangtang onlinenetworkintrusiondetectionmodelbasedonimprovedregularizedextremelearningmachine AT chenghaili onlinenetworkintrusiondetectionmodelbasedonimprovedregularizedextremelearningmachine
_version_	1718420634803896320

An Online Network Intrusion Detection Model Based on Improved Regularized Extreme Learning Machine

Ejemplares similares