Performance model of the single-line display menu using neural network approach

신경회로망을 이용한 Single-line Display Menu의 수행도 예측모형

A lot of design guidelines have been proposed for menu-drive interfaces, but they are applicable only to the menus on ordinary CRT displays. Many hardware products, however, cannot employ large displays because of the cost and space limitations. Instead, a single-line display menu (SDM) is widely used, and the designers need useful guidelines applicable to the SDM. A focus is often placed upon the optimal menu structure, but only the standard menu structures, such as $64^{\1}, 8^{\2}, 4^{\3}, and 2^{\6}$, are 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 for each of the optional structures considered. Hence, a model is needed to provide a predicted value of user performance for a given menu structure. Although severaal models have been proposed for ordinary menus, none is available for the SDM yet. A performance model was developed in this study using the neural network approach. A The model developed in this study is capable of providing quantiative measures of human performance for any menu structures without conducting additional experiments, which will save much time and reduce the design cost.