Artificial neural networks have been used to analyze odour patterns and are showing promising results. In this paper, a pattern recognition system of an artificial nose with neural networks which implement temporal processing is presented. The results were compared to those obtained by a Multi-Layer Perceptron (MLP) neural network. The signals generated by an array of six conducting polymer sensors exposed to the odours of three different vintages of the same wine were analyzed. Experimental details of the training method are shown, as well as the results obtained for different numbers of hidden units in one-hidden-layer networks.
展开▼
