AmIMcl-The problem of end effects in Hilbert-Huang transform is produced in the Empirical Mode Decomposition (EMD), which has a badly effect on HUbert-Huang transform. In order to overcome this problem, multi-objective Genetic Algorithm (GA) for solving the parameters selection of RBF Neural Network (RBF_NN) (GRHHT) is presented in tbis paper. Then the RBF_NN is used to predict the signal before EMD. The scheme can effectively resolve the end effects. The simulation results from the typical definite signals demonstrate that the problem of end effects in HUbert Huang transform could be resolved effectively, and its performance is better than prediction methods by RBF neural network and support Vector Machine (SVM), respectively.Keywo1Yls-genetic IIIgoritlt ll l, ' HillJ ert-HllfIII g hYmsfonn,'nelllYli network,' slIjJport vector lII f1cltin 1.