Blind signal separation
From Wikipedia, the free encyclopedia
Blind signal separation, also known as blind source separation, is the separation of a set of signals from a set of mixed signals, without the aid of information (or with very little information) about the nature of the signals.
Blind signal separation relies on the following assumption:
- The source signals are non-redundant. For example, the signals may be mutually statistically independent or decorrelated.
Blind signal separation thus separates a set of signals into a set of other signals, such that the regularity of each resulting signal is maximized, and the regularity between the signals is minimized (i.e. statistical independence is maximized).
Because temporal redundancies (statistical regularities in the time domain) are "clumped" in this way into the resulting signals, the resulting signals can be more effectively deconvolved than the original signals.
There are different methods of blind signal separation:
- Principal components analysis
- Singular value decomposition
- Independent component analysis
- Dependent component analysis
- Non-negative matrix factorization
[edit] See also
- Source separation
- Deconvolution
- Infomax principle
- Adaptive filtering
