AUTOMATIC CLASSIFICATION OF FIELD-COLLECTED DINOFLAGELLATES BY ARTIFICIAL NEURAL-NETWORK

Automatic taxonomic categorisation of 23 species of dinoflagellates wa s demonstrated using field-collected specimens. These dinoflagellates have been responsible for the majority of toxic and noxious phytoplank ton blooms which have occurred in the coastal waters of the European U nion in recent years and make severe impact on the aquaculture industr y. The performance by human 'expert' ecologists/taxonomists in identif ying these species was compared to that achieved by 2 artificial neura l network classifiers (multilayer perceptron and radial basis function networks) and 2 other statistical techniques, k-Nearest Neighbour and Quadratic Discriminant Analysis. The neural network classifiers outpe rform the classical statistical techniques. Over extended trials, the human experts averaged 85% while the radial basis network achieved a b est performance of 83%, the multilayer perceptron 66%, k-Nearest Neigh bour 60%, and the Quadratic Discriminant Analysis 56%.