Sunspot series prediction using a Multiscale Recurrent Neural Network
Tae-Hyun Kim, Dong-Chul Park, Dong-Min Woo, Woong Huh, Chung-Hwa Yoon, Hyen-Ug Kim, Yun‐Sik Lee · 2010
A prediction scheme for sunspot series using a Multiscale Bilinear Recurrent Neural Network (M-BRNN) is proposed in this paper. The recurrent neural network adopted in this scheme is the Bilinear recurrent neural network. The M-BRNN is a combination of several Bilinear Recurrent Neural Network (BRNN) models. Each BRNN predicts a signal at a certain resolution level obtained by the wavelet transform. In order to evaluate the performance of the proposed M-BRNN-based predictor, experiments are conducted on the Wolf sunspot series number data and the resulting prediction accuracy is compared with those of conventional MultiLayer Perceptron Type Neural Network (MLPNN)-based and BRNN-based predictors. The results show that the proposed M-BRNN-based predictor outperforms the MLPNN-based and BRNN-based predictors in terms of the Normalized Mean Squared Error (NMSE).