Robust electronic-nose system with temperature and humidity drift compensation for tea and spice flavour discrimination

The aim of this paper is to determine aroma and flavour of the tea and spices by using Electronic-nose (E-nose) system with temperature and humidity drift compensation techniques. E-nose sensors are used with variable temperature and humidity conditions. Compensation for drift is an important factor and that generally is neglected. Therefore, we have put an effort to compensate the drifts in E-nose response data. Firstly, drift coefficients for E-noses sensors due to temperature and humidity variations in samples are determined and subsequently, these coefficients are used to eliminate drift in E-nose response data during online capturing and processing. We have described the results and experiments conducted by using four metal oxide semiconductor (MOS) based E-nose sensors. Artificial neural network (ANN) based pattern recognition techniques are used for discrimination and classification of electronic nose response data for different flavour terms of tea and spice.