Temporal filtering and oriented PCA neural networks for blind source separation
Konstantinos Diamantaras, Théophilos Papadimitriou · 2004
PCA-related (principal component analysis) neural models have been shown to solve the instantaneous BSS (blind source separation) problem for temporally colored sources. In this paper we show that arbitrary temporal filtering combined with models associated to the extension of standard PCA known as oriented PCA (OPCA) provide a solution to the problem that is based on second order statistics and requires no prewhitening of the observation signals. Furthermore, the issue of the optimal temporal filter is addressed for filters of length 2 and 3 although the design of the universally optimal filter is still an open question. Earlier neural OPCA networks are used to demonstrate the validity of the method on artificially generated datasets.