Skip to Main content Skip to Navigation
Journal articles

Efficient Stepsize Selection Strategy for Givens Parametrized ICA Applied to EEG Denoising

Abstract : In this letter, an efficient stepsize selection strategy for Givens parametrization-based independent component analysis (ICA) approaches is presented. The method is an extension of the pioneering deflationary ICA algorithm introduced by Delfosse and Loubaton (DelL(R)). The methodology underlying the computation of such a stepsize is based on sampling the contrast function using the information carried by its frequency components. Epileptic ElectroEncephaloGraphy (EEG)-based simulations show that the proposed approach stands for the best extraction accuracy/numerical complexity tradeoff with 15 times faster execution time. This is compared to a deterministic implementation of the DelLR technique and its recently proposed Jacobi-based variant, namely the JDICA method.
Document type :
Journal articles
Complete list of metadatas

https://hal-univ-rennes1.archives-ouvertes.fr/hal-01533426
Contributor : Laurent Jonchère <>
Submitted on : Tuesday, June 6, 2017 - 2:40:52 PM
Last modification on : Wednesday, May 16, 2018 - 11:23:41 AM

Identifiers

Collections

Citation

Majd Saleh, Ahmad Karfoul, Amar Kachenoura, Isabelle Merlet, Laurent Albera. Efficient Stepsize Selection Strategy for Givens Parametrized ICA Applied to EEG Denoising. IEEE Signal Processing Letters, Institute of Electrical and Electronics Engineers, 2017, 24 (6), pp.882--886. ⟨10.1109/LSP.2017.2696359⟩. ⟨hal-01533426⟩

Share

Metrics

Record views

603