Cargando…

Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble

Sensor drift is the most challenging problem in gas sensing at present. We propose a novel two-dimensional classifier ensemble strategy to solve the gas discrimination problem, regardless of the gas concentration, with high accuracy over extended periods of time. This strategy is appropriate for mul...

Descripción completa

Detalles Bibliográficos
Autores principales: Liu, Hang, Chu, Renzhi, Tang, Zhenan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4481969/
https://www.ncbi.nlm.nih.gov/pubmed/25942640
http://dx.doi.org/10.3390/s150510180
_version_ 1782378357661368320
author Liu, Hang
Chu, Renzhi
Tang, Zhenan
author_facet Liu, Hang
Chu, Renzhi
Tang, Zhenan
author_sort Liu, Hang
collection PubMed
description Sensor drift is the most challenging problem in gas sensing at present. We propose a novel two-dimensional classifier ensemble strategy to solve the gas discrimination problem, regardless of the gas concentration, with high accuracy over extended periods of time. This strategy is appropriate for multi-class classifiers that consist of combinations of pairwise classifiers, such as support vector machines. We compare the performance of the strategy with those of competing methods in an experiment based on a public dataset that was compiled over a period of three years. The experimental results demonstrate that the two-dimensional ensemble outperforms the other methods considered. Furthermore, we propose a pre-aging process inspired by that applied to the sensors to improve the stability of the classifier ensemble. The experimental results demonstrate that the weight of each multi-class classifier model in the ensemble remains fairly static before and after the addition of new classifier models to the ensemble, when a pre-aging procedure is applied.
format Online
Article
Text
id pubmed-4481969
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-44819692015-06-29 Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble Liu, Hang Chu, Renzhi Tang, Zhenan Sensors (Basel) Article Sensor drift is the most challenging problem in gas sensing at present. We propose a novel two-dimensional classifier ensemble strategy to solve the gas discrimination problem, regardless of the gas concentration, with high accuracy over extended periods of time. This strategy is appropriate for multi-class classifiers that consist of combinations of pairwise classifiers, such as support vector machines. We compare the performance of the strategy with those of competing methods in an experiment based on a public dataset that was compiled over a period of three years. The experimental results demonstrate that the two-dimensional ensemble outperforms the other methods considered. Furthermore, we propose a pre-aging process inspired by that applied to the sensors to improve the stability of the classifier ensemble. The experimental results demonstrate that the weight of each multi-class classifier model in the ensemble remains fairly static before and after the addition of new classifier models to the ensemble, when a pre-aging procedure is applied. MDPI 2015-04-30 /pmc/articles/PMC4481969/ /pubmed/25942640 http://dx.doi.org/10.3390/s150510180 Text en © 2015 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 license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Liu, Hang
Chu, Renzhi
Tang, Zhenan
Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble
title Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble
title_full Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble
title_fullStr Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble
title_full_unstemmed Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble
title_short Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble
title_sort metal oxide gas sensor drift compensation using a two-dimensional classifier ensemble
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4481969/
https://www.ncbi.nlm.nih.gov/pubmed/25942640
http://dx.doi.org/10.3390/s150510180
work_keys_str_mv AT liuhang metaloxidegassensordriftcompensationusingatwodimensionalclassifierensemble
AT churenzhi metaloxidegassensordriftcompensationusingatwodimensionalclassifierensemble
AT tangzhenan metaloxidegassensordriftcompensationusingatwodimensionalclassifierensemble