Evaluation of a radial basis function neural network for the determinationof wheat quality from electronic nose data

Odorous contaminants in wheat have been detected using a conducting polymer array, A radial basis function artificial neural network (RBFann) was used to correlate sensor array responses with human grading of off-taints in wh eat. Wheat samples moulded by artificial means in the laboratory were used to evaluate the network, operating in quantitative mode, and also to develo p strategies for evaluating real samples. Commercial wheat samples were the n evaluated using the RBFann as a classifier network with great success, ac hieving a predictive success of 92.3% with no bad samples misclassified as good in a 40-sample population (24 good, 17 bad) using a training set of 92 samples (72 good, 20 bad). (C) 2000 Elsevier Science S.A, All rights reser ved.