A novel prediction method for body fat by using Choquet integral with respect to L-measure and Gamma-support

Establishing a good algorithm for predicting body fat of body composition is an important issue. In this study, a novel body fat prediction method by using Choquet integral regression model based on L-measure and Gamma-support is proposed. For evaluating the performance of this new algorithm, a 5-fold Cross-Validation RMSE is performed. Experimental result shows that this new prediction scheme is better than the Choquet integral regression model based on Gamma-measure and P-measure, respectively and two traditional prediction models, ridge regression and multiple regression models, respectively.