THE APPLICATION OF ARTIFICIAL NEURAL NETWORKS TO THE CLASSIFICATION OF AUSTRALIAN WHEAT VARIETIES

摘要

This paper reports the results obtained from the application of artificial neural networks to the Australian wheat variety classification problem. A 'HyperSAB' network with a self adaptive acceleration strategy for the error back propagation learning has been developed. This has been applied to six different Australian wheat varieties with 200 samples in each case. The results indicate that the artificial neural network has some potential to be used as an identification tool in this problem.