Neural network classifier for ship domain assessment

The article presents an attempt to apply an artificial neural network in an ti-collision systems at sea. Such systems determine safe trajectory for a s hip by, most frequently, processing the information sourced from an automat ic radar plotting aids (ARPA) type arrangement. In this research work the u se of neural classifier has been proposed as an element supporting a naviga tor in the process of determining the ship's domain, i.e., the area around a ship which, for safety reasons, should remain free from navigational obst acles. Neural classifier has a form of a multilayer feed-forward network of a perceptronic nature. It has been assigned a task to represent the evalua tion of a navigational situation provided by an experienced navigator funct ioning as a teacher in the process of the network learning phase. Programs designed in the MATLAB language have been applied for the simulation of the network and also for the illustration of a navigational situation. Testing of the correctness of classification of the collision situations by the ne twork have been also conducted. In the final part of the article conclusion s have been formulated with regard to the application of the neural classif ier in the process of determining a safe trajectory of a ship. (C) 2000 IMA CS/Elsevier Science B.V. All rights reserved.