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 chapter is to consider an array sensing system of odors and to adopt a layered neural networks for classification. Furthermore, we consider mixed 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 the mixed effect, we use as the test data two out of four kinds of odors. An acceptable result, although not perfect, has been achieved for the classification of mixed odors, by using the layered neural network.
