As we see, blind source extraction (BSE) is advantageous over blind source separation (BSS) when obtaining some underlying source signals from high dimensional signals. Among a variety of BSE algorithms, a large number of algorithms are based on linear prediction (LP-BSE). In this paper we reveal that they are, in nature, minor component analysis (MCA) algorithms, and thus they have some problems that are inherent in MCA algorithms. We also find a switch phenomenon of online LP-BSE algorithms, showing that different parts of a singly extracted signal are the counterparts of different source signals. The two issues should be noticed when one applies these algorithms to practical applications. Computer simulations are given to confirm these observations.
Citation:
Min Gan, Hongfa Wang, Guoying Yue, Nan Xie, Haibo Zhang, "Observations on Liner Prediction Based Blind Source Extraction Algorithms," icis, pp.373-376, Seventh IEEE/ACIS International Conference on Computer and Information Science (icis 2008), 2008