Recognition of imagined hand movements with low resolution surface Laplacian and linear classifiers

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

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous EEG signals. In this framework, it was suggested that EEG patterns can be better detected with EEG data transformed with Surface Laplacian computation (SL) than with the unprocessed raw potentials. 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). 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 these obtained with the SL computed from 26 electrodes (full resolution SL). More importantly, satisfactorily 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%). These results demonstrated also the utility of linear classifiers for the detection of mental patterns in the BCI field.

Original languageEnglish
Pages (from-to)323-328
Number of pages6
JournalMedical Engineering and Physics
Volume23
Issue number5
DOIs
Publication statusPublished - 2001

Fingerprint

Electroencephalography
Classifiers
Hand
Brain-Computer Interfaces
Electrodes
Brain computer interface
Splines
Equipment and Supplies

Keywords

  • Brain Computer Interface
  • Linear classifiers
  • Signal Space Projection
  • Surface Laplacian

ASJC Scopus subject areas

  • Orthopedics and Sports Medicine
  • Psychology(all)

Cite this

Recognition of imagined hand movements with low resolution surface Laplacian and linear classifiers. / Babiloni, Fabio; Cincotti, Febo; Bianchi, Luigi; Pirri, Giada; Del R. Millán, José; Mouriño, Josep; Salinari, Serenella; Grazia Marciani, Maria.

In: Medical Engineering and Physics, Vol. 23, No. 5, 2001, p. 323-328.

Research output: Contribution to journalArticle

Babiloni, F, Cincotti, F, Bianchi, L, Pirri, G, Del R. Millán, J, Mouriño, J, Salinari, S & Grazia Marciani, M 2001, 'Recognition of imagined hand movements with low resolution surface Laplacian and linear classifiers', Medical Engineering and Physics, vol. 23, no. 5, pp. 323-328. https://doi.org/10.1016/S1350-4533(01)00049-2
Babiloni, Fabio ; Cincotti, Febo ; Bianchi, Luigi ; Pirri, Giada ; Del R. Millán, José ; Mouriño, Josep ; Salinari, Serenella ; Grazia Marciani, Maria. / Recognition of imagined hand movements with low resolution surface Laplacian and linear classifiers. In: Medical Engineering and Physics. 2001 ; Vol. 23, No. 5. pp. 323-328.
@article{1abfed22ed5f4cba99d20eb15f8658e9,
title = "Recognition of imagined hand movements with low resolution surface Laplacian and linear classifiers",
abstract = "EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous EEG signals. In this framework, it was suggested that EEG patterns can be better detected with EEG data transformed with Surface Laplacian computation (SL) than with the unprocessed raw potentials. 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). 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 these obtained with the SL computed from 26 electrodes (full resolution SL). More importantly, satisfactorily 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{\%}). These results demonstrated also the utility of linear classifiers for the detection of mental patterns in the BCI field.",
keywords = "Brain Computer Interface, Linear classifiers, Signal Space Projection, Surface Laplacian",
author = "Fabio Babiloni and Febo Cincotti and Luigi Bianchi and Giada Pirri and {Del R. Mill{\'a}n}, Jos{\'e} and Josep Mouri{\~n}o and Serenella Salinari and {Grazia Marciani}, Maria",
year = "2001",
doi = "10.1016/S1350-4533(01)00049-2",
language = "English",
volume = "23",
pages = "323--328",
journal = "Medical Engineering and Physics",
issn = "1350-4533",
publisher = "Elsevier BV",
number = "5",

}

TY - JOUR

T1 - Recognition of imagined hand movements with low resolution surface Laplacian and linear classifiers

AU - Babiloni, Fabio

AU - Cincotti, Febo

AU - Bianchi, Luigi

AU - Pirri, Giada

AU - Del R. Millán, José

AU - Mouriño, Josep

AU - Salinari, Serenella

AU - Grazia Marciani, Maria

PY - 2001

Y1 - 2001

N2 - EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous EEG signals. In this framework, it was suggested that EEG patterns can be better detected with EEG data transformed with Surface Laplacian computation (SL) than with the unprocessed raw potentials. 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). 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 these obtained with the SL computed from 26 electrodes (full resolution SL). More importantly, satisfactorily 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%). These results demonstrated also the utility of linear classifiers for the detection of mental patterns in the BCI field.

AB - EEG-based Brain Computer Interfaces (BCIs) require on-line detection of mental states from spontaneous EEG signals. In this framework, it was suggested that EEG patterns can be better detected with EEG data transformed with Surface Laplacian computation (SL) than with the unprocessed raw potentials. 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). 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 these obtained with the SL computed from 26 electrodes (full resolution SL). More importantly, satisfactorily 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%). These results demonstrated also the utility of linear classifiers for the detection of mental patterns in the BCI field.

KW - Brain Computer Interface

KW - Linear classifiers

KW - Signal Space Projection

KW - Surface Laplacian

UR - http://www.scopus.com/inward/record.url?scp=0034955692&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034955692&partnerID=8YFLogxK

U2 - 10.1016/S1350-4533(01)00049-2

DO - 10.1016/S1350-4533(01)00049-2

M3 - Article

C2 - 11435146

AN - SCOPUS:0034955692

VL - 23

SP - 323

EP - 328

JO - Medical Engineering and Physics

JF - Medical Engineering and Physics

SN - 1350-4533

IS - 5

ER -