Predicting BCI subject performance using probabilistic spatio-temporal filters

Heung Il Suk, Siamac Fazli, Jan Mehnert, Klaus Robert Müller, Seong Whan Lee

Research output: Contribution to journalArticle

19 Citations (Scopus)

Abstract

Recently, spatio-temporal filtering to enhance decoding for Brain-Computer-Interfacing (BCI) has become increasingly popular. In this work, we discuss a novel, fully Bayesian-and thereby probabilistic-framework, called Bayesian Spatio-Spectral Filter Optimization (BSSFO) and apply it to a large data set of 80 non-invasive EEG-based BCI experiments. Across the full frequency range, the BSSFO framework allows to analyze which spatio-spectral parameters are common and which ones differ across the subject population. As expected, large variability of brain rhythms is observed between subjects. We have clustered subjects according to similarities in their corresponding spectral characteristics from the BSSFO model, which is found to reflect their BCI performances well. In BCI, a considerable percentage of subjects is unable to use a BCI for communication, due to their missing ability to modulate their brain rhythms-a phenomenon sometimes denoted as BCI-illiteracy or inability. Predicting individual subjects' performance preceding the actual, time-consuming BCI-experiment enhances the usage of BCIs, e.g., by detecting users with BCI inability. This work additionally contributes by using the novel BSSFO method to predict the BCI-performance using only 2 minutes and 3 channels of resting-state EEG data recorded before the actual BCI-experiment. Specifically, by grouping the individual frequency characteristics we have nicely classified them into the subject 'prototypes' (like μ- or β-rhythm type subjects) or users without ability to communicate with a BCI, and then by further building a linear regression model based on the grouping we could predict subjects' performance with the maximum correlation coefficient of 0.581 with the performance later seen in the actual BCI session.

Original languageEnglish
Article numbere87056
JournalPLoS One
Volume9
Issue number2
DOIs
Publication statusPublished - Feb 14 2014
Externally publishedYes

Fingerprint

Brain
brain
Aptitude
Electroencephalography
Linear Models
literacy
system optimization
Experiments
prototypes
animal communication
Linear regression
Decoding
Communication

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Predicting BCI subject performance using probabilistic spatio-temporal filters. / Suk, Heung Il; Fazli, Siamac; Mehnert, Jan; Müller, Klaus Robert; Lee, Seong Whan.

In: PLoS One, Vol. 9, No. 2, e87056, 14.02.2014.

Research output: Contribution to journalArticle

Suk, Heung Il ; Fazli, Siamac ; Mehnert, Jan ; Müller, Klaus Robert ; Lee, Seong Whan. / Predicting BCI subject performance using probabilistic spatio-temporal filters. In: PLoS One. 2014 ; Vol. 9, No. 2.
@article{625780b977304e568402f311e4dff9ed,
title = "Predicting BCI subject performance using probabilistic spatio-temporal filters",
abstract = "Recently, spatio-temporal filtering to enhance decoding for Brain-Computer-Interfacing (BCI) has become increasingly popular. In this work, we discuss a novel, fully Bayesian-and thereby probabilistic-framework, called Bayesian Spatio-Spectral Filter Optimization (BSSFO) and apply it to a large data set of 80 non-invasive EEG-based BCI experiments. Across the full frequency range, the BSSFO framework allows to analyze which spatio-spectral parameters are common and which ones differ across the subject population. As expected, large variability of brain rhythms is observed between subjects. We have clustered subjects according to similarities in their corresponding spectral characteristics from the BSSFO model, which is found to reflect their BCI performances well. In BCI, a considerable percentage of subjects is unable to use a BCI for communication, due to their missing ability to modulate their brain rhythms-a phenomenon sometimes denoted as BCI-illiteracy or inability. Predicting individual subjects' performance preceding the actual, time-consuming BCI-experiment enhances the usage of BCIs, e.g., by detecting users with BCI inability. This work additionally contributes by using the novel BSSFO method to predict the BCI-performance using only 2 minutes and 3 channels of resting-state EEG data recorded before the actual BCI-experiment. Specifically, by grouping the individual frequency characteristics we have nicely classified them into the subject 'prototypes' (like μ- or β-rhythm type subjects) or users without ability to communicate with a BCI, and then by further building a linear regression model based on the grouping we could predict subjects' performance with the maximum correlation coefficient of 0.581 with the performance later seen in the actual BCI session.",
author = "Suk, {Heung Il} and Siamac Fazli and Jan Mehnert and M{\"u}ller, {Klaus Robert} and Lee, {Seong Whan}",
year = "2014",
month = "2",
day = "14",
doi = "10.1371/journal.pone.0087056",
language = "English",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

TY - JOUR

T1 - Predicting BCI subject performance using probabilistic spatio-temporal filters

AU - Suk, Heung Il

AU - Fazli, Siamac

AU - Mehnert, Jan

AU - Müller, Klaus Robert

AU - Lee, Seong Whan

PY - 2014/2/14

Y1 - 2014/2/14

N2 - Recently, spatio-temporal filtering to enhance decoding for Brain-Computer-Interfacing (BCI) has become increasingly popular. In this work, we discuss a novel, fully Bayesian-and thereby probabilistic-framework, called Bayesian Spatio-Spectral Filter Optimization (BSSFO) and apply it to a large data set of 80 non-invasive EEG-based BCI experiments. Across the full frequency range, the BSSFO framework allows to analyze which spatio-spectral parameters are common and which ones differ across the subject population. As expected, large variability of brain rhythms is observed between subjects. We have clustered subjects according to similarities in their corresponding spectral characteristics from the BSSFO model, which is found to reflect their BCI performances well. In BCI, a considerable percentage of subjects is unable to use a BCI for communication, due to their missing ability to modulate their brain rhythms-a phenomenon sometimes denoted as BCI-illiteracy or inability. Predicting individual subjects' performance preceding the actual, time-consuming BCI-experiment enhances the usage of BCIs, e.g., by detecting users with BCI inability. This work additionally contributes by using the novel BSSFO method to predict the BCI-performance using only 2 minutes and 3 channels of resting-state EEG data recorded before the actual BCI-experiment. Specifically, by grouping the individual frequency characteristics we have nicely classified them into the subject 'prototypes' (like μ- or β-rhythm type subjects) or users without ability to communicate with a BCI, and then by further building a linear regression model based on the grouping we could predict subjects' performance with the maximum correlation coefficient of 0.581 with the performance later seen in the actual BCI session.

AB - Recently, spatio-temporal filtering to enhance decoding for Brain-Computer-Interfacing (BCI) has become increasingly popular. In this work, we discuss a novel, fully Bayesian-and thereby probabilistic-framework, called Bayesian Spatio-Spectral Filter Optimization (BSSFO) and apply it to a large data set of 80 non-invasive EEG-based BCI experiments. Across the full frequency range, the BSSFO framework allows to analyze which spatio-spectral parameters are common and which ones differ across the subject population. As expected, large variability of brain rhythms is observed between subjects. We have clustered subjects according to similarities in their corresponding spectral characteristics from the BSSFO model, which is found to reflect their BCI performances well. In BCI, a considerable percentage of subjects is unable to use a BCI for communication, due to their missing ability to modulate their brain rhythms-a phenomenon sometimes denoted as BCI-illiteracy or inability. Predicting individual subjects' performance preceding the actual, time-consuming BCI-experiment enhances the usage of BCIs, e.g., by detecting users with BCI inability. This work additionally contributes by using the novel BSSFO method to predict the BCI-performance using only 2 minutes and 3 channels of resting-state EEG data recorded before the actual BCI-experiment. Specifically, by grouping the individual frequency characteristics we have nicely classified them into the subject 'prototypes' (like μ- or β-rhythm type subjects) or users without ability to communicate with a BCI, and then by further building a linear regression model based on the grouping we could predict subjects' performance with the maximum correlation coefficient of 0.581 with the performance later seen in the actual BCI session.

UR - http://www.scopus.com/inward/record.url?scp=84895856793&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84895856793&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0087056

DO - 10.1371/journal.pone.0087056

M3 - Article

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 2

M1 - e87056

ER -