Gas quantitative analysis with support vector machine

Authors:
Liang Xie;Xiaodong Wang
Affiliations:
Department of Electronic Engineering, Zhejiang Normal University, Jinhua, China;Department of Electronic Engineering, Zhejiang Normal University, Jinhua, China
Venue:
CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
Year:
2009

Citing 2
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Support-Vector Networks

Machine Learning

Quantified Score

Hi-index	0.01

Visualization

Abstract

Gas sensor array is an important part of electronic nose. The gas analysis performance of electronic nose is affected badly by the cross sensitivity of gas sensor array. In order to solve the problem of the cross sensitivity, in this work a new method based on support vector machine (SVM) is used for pattern analysis of gas mixture quantitative analysis. The proposed method has been used for processing the measuring data obtained by a gas mixture experiment of butane and ethanol, in which the sensor array is composed of three sensors. The results clearly show that the SVM is effective technique for gas mixture quantitative analysis. Also, the SVM can achieve better prediction accuracy than BP neural network.