Analysis of 5 source separation algorithms on simulated EEG signals - Archive ouverte HAL
Communication Dans Un Congrès Année : 2008

Analysis of 5 source separation algorithms on simulated EEG signals

Résumé

In this paper we evaluate the performance of 5 BSS algorithms (AMUSE, SOBI, SOBI-RO, SONS, JADE-TD)on simulated EEG signals. A first reesult evaluates the influence of the noise and signal characteristics (frequency, length, SNR) on the algorithms performance. A second objetive is to introduce a new performance criterion, IEV which can be use to compare two matrices and is potentially usefull on real signals. We validate this new index by comparing it with classic performance indices used in source separation.
Fichier non déposé

Dates et versions

hal-00317928 , version 1 (03-09-2008)

Identifiants

  • HAL Id : hal-00317928 , version 1

Citer

Ricardo-Antonio Salido-Ruiz, Rebeca Romo-Vázquez, Radu Ranta, Lorenzo Leija. Analysis of 5 source separation algorithms on simulated EEG signals. Congreso de Computación, Informática, Biomédica y Electrónica, CONCIBE 2008, May 2008, Guadalajara, Mexico. pp.CDROM. ⟨hal-00317928⟩
81 Consultations
0 Téléchargements

Partager

More