Identifying brain activity related to visual target detection in single trial EEG data

Fuhrmann G Alpert; R Manor; AB Spanier; LY Deouell; AB Geva

doi:10.1007/s12031-011-9491-9

Abstract

Recent advances in Neuroscience have led to an emerging interest in Brain Computer Interface (BCI) applications for both disabled and healthy populations. These applications critically depend on online decoding of brain activity in single trials. The goal of the present study was to detect distinctive spatio-temporal brain patterns within a set of event related responses.

Subjects were looking for targets (a given category out of five) within a rapid serial visual presentation (RSVP, 10 Hz). EEG data was collected from 64 channels at a high temporal resolution, yielding large spatio-temporal data matrices for the representation of single trial brain activity. These matrices are used to classify brain activity to several categories (or brain states), using machine learning, based on the statistical properties of the activity matrices.

Original language	English
Pages (from-to)	S40-S40
Number of pages	1
Journal	Journal of Molecular Neuroscience
Volume	45
Issue number	Supplement 1
DOIs	https://doi.org/10.1007/s12031-011-9491-9
State	Published - Nov 2011

Access to Document

10.1007/s12031-011-9491-9

Cite this

@article{2c60942b056f4481b9989a6adfe4fa27,

title = "Identifying brain activity related to visual target detection in single trial EEG data",

abstract = "Recent advances in Neuroscience have led to an emerging interest in Brain Computer Interface (BCI) applications for both disabled and healthy populations. These applications critically depend on online decoding of brain activity in single trials. The goal of the present study was to detect distinctive spatio-temporal brain patterns within a set of event related responses.Subjects were looking for targets (a given category out of five) within a rapid serial visual presentation (RSVP, 10 Hz). EEG data was collected from 64 channels at a high temporal resolution, yielding large spatio-temporal data matrices for the representation of single trial brain activity. These matrices are used to classify brain activity to several categories (or brain states), using machine learning, based on the statistical properties of the activity matrices.",

author = "Alpert, {Fuhrmann G} and R Manor and AB Spanier and LY Deouell and AB Geva",

year = "2011",

month = nov,

doi = "10.1007/s12031-011-9491-9",

language = "English",

volume = "45",

pages = "S40--S40",

journal = "Journal of Molecular Neuroscience",

issn = "0895-8696",

publisher = "Springer",

number = "Supplement 1",

}

TY - JOUR

T1 - Identifying brain activity related to visual target detection in single trial EEG data

AU - Alpert, Fuhrmann G

AU - Manor, R

AU - Spanier, AB

AU - Deouell, LY

AU - Geva, AB

PY - 2011/11

Y1 - 2011/11

N2 - Recent advances in Neuroscience have led to an emerging interest in Brain Computer Interface (BCI) applications for both disabled and healthy populations. These applications critically depend on online decoding of brain activity in single trials. The goal of the present study was to detect distinctive spatio-temporal brain patterns within a set of event related responses.Subjects were looking for targets (a given category out of five) within a rapid serial visual presentation (RSVP, 10 Hz). EEG data was collected from 64 channels at a high temporal resolution, yielding large spatio-temporal data matrices for the representation of single trial brain activity. These matrices are used to classify brain activity to several categories (or brain states), using machine learning, based on the statistical properties of the activity matrices.

AB - Recent advances in Neuroscience have led to an emerging interest in Brain Computer Interface (BCI) applications for both disabled and healthy populations. These applications critically depend on online decoding of brain activity in single trials. The goal of the present study was to detect distinctive spatio-temporal brain patterns within a set of event related responses.Subjects were looking for targets (a given category out of five) within a rapid serial visual presentation (RSVP, 10 Hz). EEG data was collected from 64 channels at a high temporal resolution, yielding large spatio-temporal data matrices for the representation of single trial brain activity. These matrices are used to classify brain activity to several categories (or brain states), using machine learning, based on the statistical properties of the activity matrices.

U2 - 10.1007/s12031-011-9491-9

DO - 10.1007/s12031-011-9491-9

M3 - Meeting Abstract

SN - 0895-8696

VL - 45

SP - S40-S40

JO - Journal of Molecular Neuroscience

JF - Journal of Molecular Neuroscience

IS - Supplement 1

ER -

Identifying brain activity related to visual target detection in single trial EEG data

Abstract

Access to Document

Fingerprint

Cite this