A comparison between SVM and PLS for E-nose based gas concentration monitoring

The present paper deals with gas concentration monitoring based on an electronic nose. The proposed approach investigates two regression methods for gas concentration estimation: the first is the most used in gas quantification with electronic nose and known as the partial least squares (PLS) and the second, known as the support vector machine (SVM) regression, is recently used by the electronic nose community. Data used in this work are collected using an E-nose device developed in our laboratory and responding to various concentrations of pine essential oil vapours. The comparison between the two regression methods studied in this paper is related to the accuracy, the universality as well as the number of samples needed for learning. The results are analyzed in order to select the more suitable prediction model for gas concentration estimation.

[1]  Paul Geladi,et al.  A comparison of modeling nonlinear systems with artificial neural networks and partial least squares , 1999 .

[2]  J W Gardner and P N Bartlett,et al.  Electronic Noses: Principles and Applications , 1999 .

[3]  Anne-Claude Romain,et al.  Long term stability of metal oxide-based gas sensors for e-nose environmental applications: An overview , 2009 .

[4]  Lei Zhang,et al.  On-line sensor calibration transfer among electronic nose instruments for monitoring volatile organic chemicals in indoor air quality , 2011 .

[5]  A. Gutierrez-Galvez,et al.  Signal and Data Processing for Machine Olfaction and Chemical Sensing: A Review , 2012, IEEE Sensors Journal.

[6]  Jordi Coello,et al.  Calibration in non-linear near infrared reflectance spectroscopy: a comparison of several methods , 1999 .

[7]  Kai Song,et al.  A Wireless Electronic Nose System Using a Fe2O3 Gas Sensing Array and Least Squares Support Vector Regression , 2011, Sensors.

[8]  S. Wold,et al.  The kernel algorithm for PLS , 1993 .

[9]  J. Brezmes,et al.  Variable selection for support vector machine based multisensor systems , 2007 .

[10]  Xichang Wang,et al.  Prediction of total viable counts on chilled pork using an electronic nose combined with support vector machine. , 2012, Meat science.

[11]  Martine Lumbreras,et al.  Optimization of an electronic nose for rapid quantitative recognition , 2014, 2014 International Conference on Control, Decision and Information Technologies (CoDIT).

[12]  José Pedro Santos,et al.  Correlating e-nose responses to wine sensorial descriptors and gas chromatography–mass spectrometry profiles using partial least squares regression analysis , 2007 .

[13]  M. Siadat,et al.  Reduction of drift impact in gas sensor response to improve quantitative odor analysis , 2017, 2017 IEEE International Conference on Industrial Technology (ICIT).

[14]  Julian W. Gardner,et al.  A brief history of electronic noses , 1994 .

[15]  Julian W. Gardner,et al.  Electronic noses: a review of signal processing techniques , 1999 .

[16]  Michele Penza,et al.  Application of Artificial Neural Networks to a Gas Sensor-Array Database for Environmental Monitoring , 2012 .