Conference paper
Dynamic components of linear stable mixtures from fractional low order moments
The second moment-based independent component analysis scheme of Molgedey and Schuster (1994) is generalized to fractional low-order moments, relevant for linear mixtures of heavy tail stable processes. The Molgedey-Schuster algorithm stands out by allowing explicitly construction of the independent components.
Surprisingly, this turns out to be possible also for decorrelation based on fractional low-order moments.
Language: | English |
---|---|
Publisher: | IEEE Press |
Year: | 2001 |
Pages: | 3957-3960 |
Proceedings: | 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing |
ISBN: | 0780370414 and 9780780370418 |
ISSN: | 2379190x and 15206149 |
Types: | Conference paper |
DOI: | 10.1109/ICASSP.2001.940710 |
ORCIDs: | Hansen, Lars Kai |
Blind source separation Decorrelation Image reconstruction Independent component analysis Mathematical model Molgedey-Schuster algorithm Random variables Signal processing Signal processing algorithms Source separation Tail decorrelation dynamic components fractional low order moments heavy tail stable processes independent component analysis linear stable mixtures numerical stability probability signal processing statistical analysis