EVALUATION OF ARTIFICIAL NEURAL NETWORKS FOR FUNGAL IDENTIFICATION, EMPLOYING MORPHOMETRIC DATA FROM SPORES OF PESTALOTIOPSIS SPECIES

The relative abilities of the multilayer perceptron, radial basis func tion, asymmetric radial basis function and learning vector quantizatio n artificial neural networks (ANNs) and two non-neural methods to iden tify fungal spores were compared. ANNs were trained on morphometric da ta from spores of Pestalotiopsis spp. and a few species in the related Truncatella and Monochaetia. The optimized neural and statistical cla ssifiers had similar identification success on an unseen data set - be tween 76.0 and 78.8% of a 16-species group and between 63.0 and 67.7% of a 19-species group. The relative merits of each classifier are disc ussed, as is the potential of ANNs in mycology.