An artificial neural network for the ergonomic evaluation of a human-computer interface

The paper examines neural networks as a tool for optimizing the placement of icons in an interface. Such networks will be used to determine the exact placement of icons on the screen. This method will be applied in the final phase of system interface evaluation, to give a group of users the opportunity to move icons on the screen as they see fit. Each new position is recorded by a neural network. Afterwards, the networks can be interrogated to deduce the optimal placement of each icon, thus avoiding the necessity of re-programming the interface several times.<>