On the Performance of Orthogonal Source Separation Algorithms

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Blind separation of instantaneous mixtures of nonstationary sources (2001, background): “As explained in [15], this constraint bounds the performance and forbids the ‘super efficiency’ effect discussed in section II-D.”
Spatial and temporal independent component analysis of functional MRI data containing a pair of task‐related waveforms (2001, background): “, the final mixing matrix to be determined is constrained to be white, as opposed to prewhitening the initial data to decrease computation time), and this makes intuitive sense for fMRI data although it may not be as statistically efficient [Cardoso, 1994].”
Non-orthogonal joint diagonalization in the least-squares sense with application in blind source separation (2002, background): “In fact, in [16], it is shown that this " hard whitening " operation imposes a limit on the attainable performance in the context of BSS, especially in the presence of additive noise.”
EEG artifact removal—state-of-the-art and guidelines (2015, methodology): “[93, 94]), the algorithm for extraction of multiple unknown”
A blind source separation technique using second-order statistics (1997, background): “This (maybe surprising) phenomenon has been investigated in a more general context in [22].”
Time-Domain Blind Separation of Audio Sources on the Basis of a Complete ICA Decomposition of an Observation Space (2011, unknown): “1 and 2.”