2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro 2009
DOI: 10.1109/isbi.2009.5193224
|View full text |Cite
|
Sign up to set email alerts
|

EEG classification by ICA source selection of Laplacian-filtered data

Abstract: We studied the performance of a double-spatial filtering method for classification of single-trial electroencephalography (EEG) data that couples the spherical surface Laplacian (SL) and independent component analysis (ICA). This method was evaluated in the context of a binary classification experiment with brain states driven by mental imagery of auditory and visual stimuli. A statistically significant improvement was achieved with respect to the rates provided by raw data and by data filtered by either SL or… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2011
2011
2023
2023

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(4 citation statements)
references
References 14 publications
0
4
0
Order By: Relevance
“…The TMS artifact (or artifacts in dual-stimulus trials) was removed by eliminating EEG data from 5 ms before to 5 ms after the TMS pulse. Since we were interested in characterizing cortical phenomena circumscribed at motor cortex level, we applied a Laplacian filter to our EEG signal to reduce volume conduction (Nunez and Srinivasan, 2006; Carvalhaes et al, 2009). Scalp surface Laplacian was computed using the “CSD,” a MATLAB-based open source toolbox based on the spherical splines method (Kayser and Tenke, 2006a,b; Kayser, 2009).…”
Section: Methodsmentioning
confidence: 99%
“…The TMS artifact (or artifacts in dual-stimulus trials) was removed by eliminating EEG data from 5 ms before to 5 ms after the TMS pulse. Since we were interested in characterizing cortical phenomena circumscribed at motor cortex level, we applied a Laplacian filter to our EEG signal to reduce volume conduction (Nunez and Srinivasan, 2006; Carvalhaes et al, 2009). Scalp surface Laplacian was computed using the “CSD,” a MATLAB-based open source toolbox based on the spherical splines method (Kayser and Tenke, 2006a,b; Kayser, 2009).…”
Section: Methodsmentioning
confidence: 99%
“…Sphering involves first zero-centering the rows of the input matrix, followed by a linear transformation using the inverse of the principal square root of the covariance matrix. The outcome is a decorrelated data ensemble with a diagonal covariance matrix [10].…”
Section: B Preprocessing Stagementioning
confidence: 99%
“…The third experiment was previously described in Carvalhaes et al (2009) and Carvalhaes and Suppes (2011). Eleven participants (S1-S11) were randomly presented on every other trial either a visual "stop" sign, flashed on a 17-inch LED computer screen, or the sound of the English word "go", via computer speaker.…”
Section: Exp Iii: 2-class Imagery Taskmentioning
confidence: 99%