Neural network modeling of smart nanostructure sensor for electronic nose application

Electronic nose applications in environmental monitoring are nowadays of great interest, because of the instruments proven capability of recognizing and discriminating between a variety of different gases and odors using just a small number of sensors. We present in this paper a neural network technique to create smart models for design a smart sensor for electronic nose application. The first one, called a selector, can select exactly the nature of gas detected, the second intelligent model is a compensator, which can automatically compensate the temperature effect on sensor's response and make the response independent of variation of temperature. The third one is corrector; linearize the output response of the sensor. The electronic nose is based on Co-doped SnO2 nanofibers sensor. The method discriminates qualitatively and quantitatively between six gases.