bullet Sensors & Transducers Journal

    (ISSN 1726- 5479)


2008 e-Impact Factor

25 Top Downloaded Articles

Journal Subscription 2011

Editorial Calendar 2011

Submit an Article

Editorial Board

Current Issue

Sensors & Transducers journal's cover

Sensors & Transducers Journal 2010

Sensors & Transducers Journal 2009

Sensors & Transducers Journal 2008

Sensors & Transducers Journal 2007

2000-2002 S&T e-Digest Contents

2003 S&T e-Digest Contents

2004 S&T e-Digest Contents

2005 S&T e-Digest Contents

2006 S&T e-Digest Contents


Best Articles 2010




Vol. 126, Issue 3, March 2011, pp.64-73




A Fusion Approach to Feature Extraction by Wavelet Decomposition and Principal Component Analysis
in Transient Signal Processing of SAW Odor Sensor Array


Prashant SINGH and R. D. S. YADAVA

Sensors & Signal Processing Laboratory, Department of Physics, Faculty of Science,
Banaras Hindu University, Varanasi 221005, India

Tel.: +91-542-2307308, fax: +91-542-2368390

E-mail: p8singh@gmail.com, ardius@gmail.com, ardius@bhu.ac.in



Received: 5 November 2010   /Accepted: 17 March 2011   /Published: 29 March 2011


Abstract: This paper presents theoretical analysis of a new approach for development of surface acoustic wave (SAW) sensor array based odor recognition system. The construction of sensor array employs a single polymer interface for selective sorption of odorant chemicals in vapor phase. The individual sensors are however coated with different thicknesses. The idea of sensor coating thickness variation is for terminating solvation and diffusion kinetics of vapors into polymer up to different stages of equilibration on different sensors. This is expected to generate diversity in information content of the sensors transient. The analysis is based on wavelet decomposition of transient signals. The single sensor transients have been used earlier for generating odor identity signatures based on wavelet approximation coefficients. In the present work, however, we exploit variability in diffusion kinetics due to polymer thicknesses for making odor signatures. This is done by fusion of the wavelet coefficients from different sensors in the array, and then applying the principal component analysis. We find that the present approach substantially enhances the vapor class separability in feature space. The validation is done by generating synthetic sensor array data based on well-established SAW sensor theory.


Keywords: SAW electronic nose, Wavelet decomposition, Feature extraction, Transient signal analysis, Odor sensor array, Information fusion


Acrobat reader logo Click <here> or title of paper to download the full pages article (1.18 Mb)






1999 - 2011 Copyright , International Frequency Sensor Association (IFSA). All Rights Reserved.

Home - News - Links - Archives - Tools - Standardization - Patents - Marketplace - Projects - Wish List - Subscribe - Search - Membership - Submit Press Release - Twitter

 Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Sensor Jobs - e-Shop - Site Map - Video