Brain computer interface: The use of low resolution surface Laplacian and linear classifiers for the recognition of imagined hand movements

Febo Cincotti, Luigi Bianchi, José Del R Millán, Josep Mouriño, Serenella Salinari, Maria Grazia Marciani, Fabio Babiloni

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous or surface Laplacian transformed EEG signals. However, accurate SL estimates require the use of many EEG electrodes, when local estimation methods are used. Since BCI devices have to use a limited number of electrodes for practical reasons, we investigated the performances of spline methods for SL estimates using a limited number of electrodes (low resolution SL). In this paper, recognition of mental activity was attempted on both raw and SL-transformed EEG data from five healthy people performing two mental tasks, namely imagined right and left hand movements. Linear classifiers were used including Signal Space Projection (SSP) and Fisher's linear discriminant. Results showed an acceptable average correlation between the waveforms obtained with the low resolution SL and those obtained with the SL computed from 26 electrodes (full resolution SL). Recognition scores for mental EEG-patterns were obtained with the low-resolution surface Laplacian transformation of the recorded potentials when compared with those obtained by using full resolution SL (82%).

Original languageEnglish
Title of host publicationAnnual Reports of the Research Reactor Institute, Kyoto University
Pages655-658
Number of pages4
Volume1
Publication statusPublished - 2001
Event23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Istanbul, Turkey
Duration: Oct 25 2001Oct 28 2001

Other

Other23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CountryTurkey
CityIstanbul
Period10/25/0110/28/01

Fingerprint

Brain computer interface
Electroencephalography
Classifiers
Electrodes
Splines

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Mechanical Engineering

Cite this

Cincotti, F., Bianchi, L., Millán, J. D. R., Mouriño, J., Salinari, S., Marciani, M. G., & Babiloni, F. (2001). Brain computer interface: The use of low resolution surface Laplacian and linear classifiers for the recognition of imagined hand movements. In Annual Reports of the Research Reactor Institute, Kyoto University (Vol. 1, pp. 655-658)

Brain computer interface : The use of low resolution surface Laplacian and linear classifiers for the recognition of imagined hand movements. / Cincotti, Febo; Bianchi, Luigi; Millán, José Del R; Mouriño, Josep; Salinari, Serenella; Marciani, Maria Grazia; Babiloni, Fabio.

Annual Reports of the Research Reactor Institute, Kyoto University. Vol. 1 2001. p. 655-658.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cincotti, F, Bianchi, L, Millán, JDR, Mouriño, J, Salinari, S, Marciani, MG & Babiloni, F 2001, Brain computer interface: The use of low resolution surface Laplacian and linear classifiers for the recognition of imagined hand movements. in Annual Reports of the Research Reactor Institute, Kyoto University. vol. 1, pp. 655-658, 23rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Istanbul, Turkey, 10/25/01.
Cincotti F, Bianchi L, Millán JDR, Mouriño J, Salinari S, Marciani MG et al. Brain computer interface: The use of low resolution surface Laplacian and linear classifiers for the recognition of imagined hand movements. In Annual Reports of the Research Reactor Institute, Kyoto University. Vol. 1. 2001. p. 655-658
Cincotti, Febo ; Bianchi, Luigi ; Millán, José Del R ; Mouriño, Josep ; Salinari, Serenella ; Marciani, Maria Grazia ; Babiloni, Fabio. / Brain computer interface : The use of low resolution surface Laplacian and linear classifiers for the recognition of imagined hand movements. Annual Reports of the Research Reactor Institute, Kyoto University. Vol. 1 2001. pp. 655-658
@inproceedings{5de73a38f89b4fb19ed44d9086412a34,
title = "Brain computer interface: The use of low resolution surface Laplacian and linear classifiers for the recognition of imagined hand movements",
abstract = "EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous or surface Laplacian transformed EEG signals. However, accurate SL estimates require the use of many EEG electrodes, when local estimation methods are used. Since BCI devices have to use a limited number of electrodes for practical reasons, we investigated the performances of spline methods for SL estimates using a limited number of electrodes (low resolution SL). In this paper, recognition of mental activity was attempted on both raw and SL-transformed EEG data from five healthy people performing two mental tasks, namely imagined right and left hand movements. Linear classifiers were used including Signal Space Projection (SSP) and Fisher's linear discriminant. Results showed an acceptable average correlation between the waveforms obtained with the low resolution SL and those obtained with the SL computed from 26 electrodes (full resolution SL). Recognition scores for mental EEG-patterns were obtained with the low-resolution surface Laplacian transformation of the recorded potentials when compared with those obtained by using full resolution SL (82{\%}).",
author = "Febo Cincotti and Luigi Bianchi and Mill{\'a}n, {Jos{\'e} Del R} and Josep Mouri{\~n}o and Serenella Salinari and Marciani, {Maria Grazia} and Fabio Babiloni",
year = "2001",
language = "English",
volume = "1",
pages = "655--658",
booktitle = "Annual Reports of the Research Reactor Institute, Kyoto University",

}

TY - GEN

T1 - Brain computer interface

T2 - The use of low resolution surface Laplacian and linear classifiers for the recognition of imagined hand movements

AU - Cincotti, Febo

AU - Bianchi, Luigi

AU - Millán, José Del R

AU - Mouriño, Josep

AU - Salinari, Serenella

AU - Marciani, Maria Grazia

AU - Babiloni, Fabio

PY - 2001

Y1 - 2001

N2 - EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous or surface Laplacian transformed EEG signals. However, accurate SL estimates require the use of many EEG electrodes, when local estimation methods are used. Since BCI devices have to use a limited number of electrodes for practical reasons, we investigated the performances of spline methods for SL estimates using a limited number of electrodes (low resolution SL). In this paper, recognition of mental activity was attempted on both raw and SL-transformed EEG data from five healthy people performing two mental tasks, namely imagined right and left hand movements. Linear classifiers were used including Signal Space Projection (SSP) and Fisher's linear discriminant. Results showed an acceptable average correlation between the waveforms obtained with the low resolution SL and those obtained with the SL computed from 26 electrodes (full resolution SL). Recognition scores for mental EEG-patterns were obtained with the low-resolution surface Laplacian transformation of the recorded potentials when compared with those obtained by using full resolution SL (82%).

AB - EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous or surface Laplacian transformed EEG signals. However, accurate SL estimates require the use of many EEG electrodes, when local estimation methods are used. Since BCI devices have to use a limited number of electrodes for practical reasons, we investigated the performances of spline methods for SL estimates using a limited number of electrodes (low resolution SL). In this paper, recognition of mental activity was attempted on both raw and SL-transformed EEG data from five healthy people performing two mental tasks, namely imagined right and left hand movements. Linear classifiers were used including Signal Space Projection (SSP) and Fisher's linear discriminant. Results showed an acceptable average correlation between the waveforms obtained with the low resolution SL and those obtained with the SL computed from 26 electrodes (full resolution SL). Recognition scores for mental EEG-patterns were obtained with the low-resolution surface Laplacian transformation of the recorded potentials when compared with those obtained by using full resolution SL (82%).

UR - http://www.scopus.com/inward/record.url?scp=0035781316&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035781316&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0035781316

VL - 1

SP - 655

EP - 658

BT - Annual Reports of the Research Reactor Institute, Kyoto University

ER -