Application of the Random Forest Kernel in Nonparametric Regression Model with Spherical Variables

Abstract

In this paper, we apply the random forest kernel to nonparametric regression model with spherical and linear variables. Validate the new model with simulated data and actual airfoil noise data. Comparing with the Gaussian kernel and the linear-circular kernel, the experimental results show that the random forest kernel has stable performance and fast computation speed, and the random forest kernel has a better fitting effect in high dimension.