Cl. Fancourt et Jc. Principe, COMPETITIVE PRINCIPAL COMPONENT ANALYSIS FOR LOCALLY STATIONARY TIME-SERIES, IEEE transactions on signal processing, 46(11), 1998, pp. 3068-3081
A new unsupervised algorithm is proposed that performs competitive pri
ncipal component analysis (PCA) of a time series. A set of expert PCA
networks compete, through the mixture of experts (MOE) formalism, on t
he basis of their ability to reconstruct the original signal. The resu
lting network finds an optimal projection of the input onto a reduced
dimensional space as a function of the input and, hence, of time. As a
byproduct, the time series is both segmented and identified according
to stationary regions. Examples showing the performance of the algori
thm are included.