@Created by Francois Cardoso

**DESCRIPTION**

An algorithm based on the (joint) diagonalization of cumulant matrices, for off-line ICA . Good statistical performance is achieved by involving all the cumulants of order 2 and 4 while a fast optimization is obtained by the device of joint diagonalization.

JADE has been successfully applied to the processing of real data sets, such as found in mobile telephony and in airport radar as well as to bio-medical signals (ECG, EEG, multi-electrode neural recordings).

The strongest point of JADE for applications of ICA is that it works off-the-shelf (no parameter tuning). The weakest point of the current implementation is that the number of sources (but not of sensors) is limited in practice (by the available memory) to something like 40 or 50 depending on your computer.

The JADE algorithm was originally developed to process complex signals, motivated by applications to digital communications. Now is available another implementation which is tuned to process more efficiently real-valued signals.

**SOURCE**

Homepage: http://www.tsi.enst.fr/%7Ecardoso/guidesepsou.html

**REFERENCES**

- J.F. Cardoso, A. Souloumiac,
**Blind beamforming for non Gaussian signals**, IEE Proceedings-F, 140(6), pp362-370, 1993 - J.F Cardoso,
**On the performance of orthogonal algorithms**, EUSIPCO '94, Edinburgh - J.F. Cardoso,
**High-order contrasts for independent component analysis**, Neural Computation, 11(1), pp157-192, 1999

**DOWNLOADS**

**Implementation for the ICA of real-valued data**

**CODE - jadeR.m **[18
KB] **
DEMO - demoR.m
**[3 KB]

**Implementation for complex-valued signals.
**