Using ANN To Predict The Best HUB Location

The power and usefulness of artificial neural networks have been demonstrated in several applications including signal processing, speech recognition and robotic control. In this paper, we present the results of an attempt to assess the feasibility of using artificial neural networks in predicting the best hub location in a star topology local area network. The idea is to train the network to predict the position that would produce the most economical wiring or cabling plan, that is, the coordinates produced by the trained network are a reflection of the shortest path possible between the nodes in the network given the selected position of the hub