Neuro-adaptation method for a case-based reasoning system

A multi-agent approach is presented for identifying and forecasting the structure of the water ahead of an ongoing vessel. The work addresses the task of forecasting the behaviour of complex environments, in which the underling knowledge of the domain is not completely available, the rules governing the system are fuzzy and the available data sets are limited and incomplete. A hybrid approach is proposed that combines the ability of a case-based reasoning system for selecting previous similar situations and the generalising ability of artificial neural networks to guide the adaptation stage of the case-based reasoning system. The successful application of the approach to oceanographic forecasting in the Atlantic Ocean is described.