DocumentCode :
875396
Title :
Enhancing the signal-to-noise ratio of ICA-based extracted ERPs
Author :
Lemm, Steven ; Curio, Gabriel ; Hlushchuk, Yevhen ; Muller, Klaus-Robert
Author_Institution :
Dept. of Intelligent Data Anal., FIRST Fraunhofer Inst., Berlin, Germany
Volume :
53
Issue :
4
fYear :
2006
fDate :
4/1/2006 12:00:00 AM
Firstpage :
601
Lastpage :
607
Abstract :
When decomposing single trial electroencephalography it is a challenge to incorporate prior physiological knowledge. Here, we develop a method that uses prior information about the phase-locking property of event-related potentials in a regularization framework to bias a blind source separation algorithm toward an improved separation of single-trial phase-locked responses in terms of an increased signal-to-noise ratio. In particular, we suggest a transformation of the data, using weighted average of the single trial and trial-averaged response, that redirects the focus of source separation methods onto the subspace of event-related potentials. The practical benefit with respect to an improved separation of such components from ongoing background activity and extraneous noise is first illustrated on artificial data and finally verified in a real-world application of extracting single-trial somatosensory evoked potentials from multichannel EEG-recordings.
Keywords :
bioelectric potentials; blind source separation; electroencephalography; independent component analysis; medical signal processing; noise; somatosensory phenomena; ICA-based extracted ERP; blind source separation; event-related potentials; multichannel EEG recordings; phase-locking property; regularization; signal-to-noise ratio enhancement; single trial electroencephalography decomposition; single-trial somatosensory evoked potentials; Blind source separation; Data analysis; Data mining; Electroencephalography; Enterprise resource planning; Independent component analysis; Nervous system; Signal analysis; Signal to noise ratio; Source separation; Bioelectrical potentials; electroencephalogram (EEG); independent component analysis (ICA); signal-to-noise ratio; Algorithms; Brain; Computer Simulation; Diagnosis, Computer-Assisted; Electroencephalography; Evoked Potentials; Humans; Models, Neurological; Models, Statistical; Pattern Recognition, Automated; Principal Component Analysis; Reproducibility of Results; Sensitivity and Specificity; Stochastic Processes;
fLanguage :
English
Journal_Title :
Biomedical Engineering, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9294
Type :
jour
DOI :
10.1109/TBME.2006.870258
Filename :
1608509
Link To Document :
بازگشت