- News
- Subject and Goals
- Council and Annual Reports
- Contacts and Working Groups
- Lectures and Presentations
- Conferences and Seminars
- Publications
- Application Demos
- International Travels
- Visitors
- Past Events
- E-Synergy Login
SEARCH
MEMBERS OF RESEARCH CENTER
Research Centre
Data - Algorithms - Decision Making
Data - Algorithms - Decision Making
Established in 2005 under support of MŠMT ČR (project 1M0572)
Application Demos
A Fast Approximate Joint Diagonalization Algorithm Using a Criterion with a Block Diagonal Weight Matrix
Typ:
Application/Electronic document
Authors:
Area of research:
Decision-making and classifica
Year:
2008
Contact:
Anotation:
These four algorithms are related to a manuscript ``A Fast Approximate Joint Diagonalization Algorithm Using a Criterion with a Block Diagonal Weight Matrix" by Tichavsky, Yeredor and Nielsen, which was presented at ICASSP 2008 in Las Vegas. In the conference paper, the former two algorithms were called UWAJD and WAJD. BG_WEDGE is a combination of UWEDGE and WEDGE with properly adjusted weights, suitable for the Block Gaussian scenario. It represents a fast alternative to the Pham's algorithm "jadiag".
The WASOBI below is an improved implementation of the algorithm, which does not use ffdiag anymore but is based on UWEDGE and WEDGE. It is termed IWASOBI and is faster than previous versions WASOBI and EWASOBI. The IWASOBI algorithm allows separation of 100+ AR sources in order of seconds. UWEDGE, WEDGE, BG_WEDGE and IWASOBI. As a reference for WASOBI, you can also cite our EUSIPCO'06 paper (see Publications).
The WASOBI below is an improved implementation of the algorithm, which does not use ffdiag anymore but is based on UWEDGE and WEDGE. It is termed IWASOBI and is faster than previous versions WASOBI and EWASOBI. The IWASOBI algorithm allows separation of 100+ AR sources in order of seconds. UWEDGE, WEDGE, BG_WEDGE and IWASOBI. As a reference for WASOBI, you can also cite our EUSIPCO'06 paper (see Publications).