Projection generalized correntropy twin support vector regression

Abstract

A projection generalized maximum correntropy twin support vector regression algorithm is proposed. The generalized correntropy function is added into the loss function of adaptive filtering, maximizing which can suppress the interference of noise or outliers.Considering the fact that single-shift projection twin support vector regression cannot observe local information of samples, a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) combined with wavelet soft threshold denoising is used to assign weights to samples. The CEEMDAN is used to decompose the original data, calculate the Pearson correlation coefficient between the mode functions and the original data. The mode with low correlation is filtered by wavelet based algorithm with soft-threshold to get the reconstructed samples after noise reduction. Smaller weights will be assigned to reconstructed samples with significant differences from the original data, while larger weights will be assigned to reconstructed samples with smaller differences. Similarly, the empirical risk term in the cost function is also assigned calculated weights to improve the robustness. Due to the use of empirical mode decomposition, the proposed method is particularly suitable for processing non-stationary data. Experimental results on artificial and UCI datasets verified the effectiveness of the algorithm.