To address the problem of the wine quality measurement a portable electronic nose (e-nose) has been developed. Two different micromachined resistive sensor arrays are developed for this portable e-nose, one with a polysilicon integrated heater and the other with a platinum one. The nose is tested with four different wines coming of Madrid region (Malvar, Airén, Garnacha, and Tempranillo). The principal component analysis (PCA) plots show a slight overlapping of the responses for the sensor array with Platinum heater and an 88% of classification result is obtained with a probabilistic neural network (PNN). With the sensor array with polysilicon heater a good separation is achieved by the PCA and the PNN classification success is 100%.
M. Aleixandre, J. Lozano, J. Gutiérrez, I. Sayago, M.J. Fernández and M.C. Horrillo
Sensors and Actuators B: Chemical. Volume 131, Issue 1, 14 April 2008, Pages 71–76