Cargando…

A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach

A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from...

Descripción completa

Detalles Bibliográficos
Autores principales: Jian, Yulin, Huang, Daoyu, Yan, Jia, Lu, Kun, Huang, Ying, Wen, Tailai, Zeng, Tanyue, Zhong, Shijie, Xie, Qilong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5492859/
https://www.ncbi.nlm.nih.gov/pubmed/28629202
http://dx.doi.org/10.3390/s17061434
_version_ 1783247416953143296
author Jian, Yulin
Huang, Daoyu
Yan, Jia
Lu, Kun
Huang, Ying
Wen, Tailai
Zeng, Tanyue
Zhong, Shijie
Xie, Qilong
author_facet Jian, Yulin
Huang, Daoyu
Yan, Jia
Lu, Kun
Huang, Ying
Wen, Tailai
Zeng, Tanyue
Zhong, Shijie
Xie, Qilong
author_sort Jian, Yulin
collection PubMed
description A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification.
format Online
Article
Text
id pubmed-5492859
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-54928592017-07-03 A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach Jian, Yulin Huang, Daoyu Yan, Jia Lu, Kun Huang, Ying Wen, Tailai Zeng, Tanyue Zhong, Shijie Xie, Qilong Sensors (Basel) Article A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification. MDPI 2017-06-19 /pmc/articles/PMC5492859/ /pubmed/28629202 http://dx.doi.org/10.3390/s17061434 Text en © 2017 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Jian, Yulin
Huang, Daoyu
Yan, Jia
Lu, Kun
Huang, Ying
Wen, Tailai
Zeng, Tanyue
Zhong, Shijie
Xie, Qilong
A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach
title A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach
title_full A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach
title_fullStr A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach
title_full_unstemmed A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach
title_short A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach
title_sort novel extreme learning machine classification model for e-nose application based on the multiple kernel approach
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5492859/
https://www.ncbi.nlm.nih.gov/pubmed/28629202
http://dx.doi.org/10.3390/s17061434
work_keys_str_mv AT jianyulin anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT huangdaoyu anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT yanjia anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT lukun anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT huangying anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT wentailai anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT zengtanyue anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT zhongshijie anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT xieqilong anovelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT jianyulin novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT huangdaoyu novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT yanjia novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT lukun novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT huangying novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT wentailai novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT zengtanyue novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT zhongshijie novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach
AT xieqilong novelextremelearningmachineclassificationmodelforenoseapplicationbasedonthemultiplekernelapproach