Fast Independent Component Analysis Algorithm for Quaternion Valued Signals

Javidi, S, Cheong Took, C and Mandic, D (2011) Fast Independent Component Analysis Algorithm for Quaternion Valued Signals IEEE Transactions on Neural Networks, 22 (12), 1967 -.

Text SJ_CCT_DPM_QFast_ICA_IEEE_TNN_2011.pdf Restricted to Repository staff only Download (1MB)

Abstract

An extension of the fast independent component analysis algorithm is proposed for the blind separation of both Q-proper and Q-improper quaternion-valued signals. This is achieved by maximizing a negentropy-based cost function, and is derived rigorously using the recently developed HR calculus in order to implement Newton optimization in the augmented quaternion statistics framework. It is shown that the use of augmented statistics and the associated widely linear modeling provides theoretical and practical advantages when dealing with general quaternion signals with noncircular (rotation-dependent) distributions. Simulations using both benchmark and real-world quaternion-valued signals support the approach.

Item Type:	Article
Divisions :	Surrey research (other units)
Authors :	Javidi, S, Cheong Took, C and Mandic, D
Date :	December 2011
Depositing User :	Symplectic Elements
Date Deposited :	28 Mar 2017 14:12
Last Modified :	24 Jan 2020 11:54
URI:	http://epubs.surrey.ac.uk/id/eprint/739346

Actions (login required)

View Item

Downloads