Color trend prediction method based on genetic algorithm and extreme learning machine

Abstract

AbstractPredicting the trends of future color is a crucial task in the study of color application, which is also of great importance to the business economy and has received increasing attention in the design field in recent years. More advanced quantitative computational methods are expected to make the prediction more accurate, and thus help designers to avoid the interference of subjective factors when carrying out the design. In this article, a hybrid model based on genetic algorithm and extreme learning machine is developed to predict color trends. The accuracy is improved through the optimal solution of hidden bias and input weights of the extreme learning machine searched by a genetic algorithm. By using a real historical dataset of smartphone appearance color, the prediction results of the genetic algorithm‐extreme learning machine model are compared with those of several commonly used models in the past. The accuracy of the model is evaluated in terms of absolute error and mean absolute error values. The results show that the method proposed in this article can maintain higher accuracy when predicting the trends of smartphone appearance color.