Electronic Nose System by Neural Networks

This paper is concerned with a new construction of an electronic nose system based on a neural network. The neural network used here is a competitive neural network by the learning vector quantization (LVQ). Various smells are measured with an array of many metal oxide gas sensors. After reducing noises from the smell data which are measured under the different concentrations, we take the maximum values among the time series data of smells. The data are affected by concentration levels, we use a normalization method to reduce the fluctuation of the data due to the concentration levels. Those data are used to classify the various smells of tees and coffees. The classification results are about 96% in case of four kinds of tees and about 89% for five kinds of coffees.