Nonlinear Signal Estimation using KernelWiener Filter in Canonical Correlation Analysis Framework

In this paper, we introduce a nonlinear Wiener filter using canonical correlation analysis (CCA) framework. This approach is based upon the theory of reproducing kernel Hilbert spaces. A method is proposed to find approximate Wiener filtered signal in the original signal space by solving an optimization problem in the higher dimensional space. The Euclidean distance between the true and estimated signals is used in the higher dimensional space to obtain the signal estimate. The signal estimation and reconstruction capability of the kernel Wiener filter is demonstrated and benchmarked with kernel regression on simulated data