For the first time, an artificial neural network (ANN) has been employed for predicting the intensity of gas mixtures comprising different odour components. Sensory assessments are necessary but they are time-consuming, harmful, and expensive. Therefore, an instrumental quantification of subjective sensory assessments is highly desired. Because of nonlinearities arising in sensory-instrumental relationships, we decided for an ANN that was trained by gas chromatographic signals of gas mixtures. The ANN could be demonstrated to classify odour intensity fairly well.
Catalytic activity of platinum supported on SnO₂ in the reaction of CO oxidation by NO was examined. Catalysts were tested in gas mixture containing 1 vol.% of NO and 1 vol.% of CO in helium; activation procedure consisted of treatment of the catalysts with CO at 500°C. Improvement of catalytic activity after activation process was observed. The mechanisms of the oxidation and activation process with application of semiconductor resistive sensors made of Pt/SnO₂ were investigated.