Application of artificial bee colony algorithm and back propagation neural network in color evaluation of human–machine interaction interfaces

People prefer an attractive human–machine interaction interface, and color is an important factor affecting attractiveness. Therefore, to evaluate the color of human–machine interaction interfaces, a back propagation neural network (BPNN) optimized by the artificial bee colony (ABC) algorithm was proposed to predict and evaluate the interface color. The process of determining the weights and thresholds of each layer of BPNN was transformed into the process of searching for the best honey source. Based on a comprehensive analysis of visual aesthetics and usability, the five color evaluation characteristics of human–machine interaction interfaces (color type, color harmony, color area, color distribution, and color difference) were extracted and expressed mathematically. The color evaluation model of the human–machine interaction interface was constructed by considering the color evaluation characteristic values as the input of BPNN and the mean values of aesthetic degree and usability by subjective evaluation as the output. The color evaluation data of websites and iPhone apps were used to train and validate the model. In Study 1, the mean squared error (MSE) and R‐Square of ABC‐BPNN were 0.0399 and 0.9400, respectively. In Study 2, the MSE and R‐Square of ABC‐BPNN were 0.0285 and 0.9195, respectively. The results showed that the prediction effect of the ABC‐BPNN model was more accurate than that of the standard BPNN and Elman‐NN models. Finally, the proposed method was applied to the interface color design of an app to improve young people's sleep, producing a color scheme that fulfilled the user's psychological expectations, which accelerated the design process.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.