Human performance models using neural network

A single line display menu (SDM) is widely used for the user interface of many electronic consumer products, and the designers need useful guidelines applicable to the SDM. In many studies on menus, major focus has been placed on the optimal menu structure, but only a few standard menu structures, such as $64^{1},8^{2},4^{3}$,and $2^{6}$ are usually tested for optimality. In many cases, however, ill defined or asymmetric structures are suggested as design alternatives. To determine the optimal menu structure, user performance should be obtained in terms of quantitative measures. Hence, a model is needed to provide a predicted value of user performance for a given menu structure. Altough several models have been proposed for ordinary menus, none is available for the SDM yet. To solve this problem a performance model was developed in this study using the neural network approach. This model is capable of providing quantitative measures of human performance for any menu structures without conducting additional experiments, which will save much time and reduce the design cost.