Home // ADVCOMP 2012, The Sixth International Conference on Advanced Engineering Computing and Applications in Sciences // View article

Intelligent Classification of Odor Data Using Neural Networks

Authors:
Sigeru Omatu
Hideo Araki
Toru Fujinaka
Mitsuaki Yano

Keywords: odor classification; odor sensors; sensor array;mixed odors; neural networks;

Abstract:
Metal oxide semiconductor gas (MOG) sensors and quartz crystal microbalance (QCM) sensors are used to measure several kinds of odors. Using neural networks to classify the measured data of odors, artificial electronic noses have been developed. This paper is to consider an array sensing system of odors and to adopt a layered neural networks for classification. Furthermore, we consider mixing effect of odors for classification accuracy. For simplicity we will treat the case that two kinds of odors are mixed since more than two becomes too complex to analyze the classification efficiency. In order to consider an mixed effect, as the test data we use all combinations of two kinds of odors among four kinds of odors. Using the layered neural network used here shows that when two kind odors are mixed the classification of each odors acceptable although the perfect classification could not been achieved.

Pages: 35 to 41

Copyright: Copyright (c) IARIA, 2012

Publication date: September 23, 2012

Published in: conference

ISSN: 2308-4499

ISBN: 978-1-61208-237-0

Location: Barcelona, Spain

Dates: from September 23, 2012 to September 28, 2012