A method for classifying mental tasks in the space of EEG transforms

Renato Cordeiro De Amorim; Boris Mirkin; John Q. Gan

A method for classifying mental tasks in the space of EEG transforms

Renato Cordeiro De Amorim, Boris Mirkin, John Q. Gan

Research output: Contribution to conference › Paper › peer-review

39 Downloads (Pure)

Abstract

In this article we describe a new method for supervised classification of EEG signals. This method applies to the power spectrum density data and assigns
class-dependent information weights to individual pixels, so that the decision is defined by the summary weights of the most informative pixel features. We
experimentally analyze several versions of the approach. The informative features appear to be rather similar among different individuals, thus supporting the view that there are subject independent general brain patterns for the same mental task

Original language	English
Publication status	Published - 2009
Event	UK Workshop on Computational Intelligence - University of Nottingham, Nottingham, United Kingdom Duration: 7 Sept 2009 → 9 Sept 2009

Workshop

Workshop	UK Workshop on Computational Intelligence
Country/Territory	United Kingdom
City	Nottingham
Period	7/09/09 → 9/09/09

Access to Document

907274Accepted author manuscript, 209 KB

Cite this

@conference{617a12789a60483e912c406f9ddc29fd,

title = "A method for classifying mental tasks in the space of EEG transforms",

abstract = "In this article we describe a new method for supervised classification of EEG signals. This method applies to the power spectrum density data and assignsclass-dependent information weights to individual pixels, so that the decision is defined by the summary weights of the most informative pixel features. Weexperimentally analyze several versions of the approach. The informative features appear to be rather similar among different individuals, thus supporting the view that there are subject independent general brain patterns for the same mental task",

author = "{Cordeiro De Amorim}, Renato and Boris Mirkin and {Q. Gan}, John",

note = "Renato Cordeiro De Amorim, Boris Mirkin, John Q. Gan, {\textquoteleft}A method for classifying mental tasks in the space of EEG transforms{\textquoteright}, paper presented at the UK Workshop on Computational Intelligence, Nottingham, UK, 7-9 September, 2009. ; UK Workshop on Computational Intelligence ; Conference date: 07-09-2009 Through 09-09-2009",

year = "2009",

language = "English",

}

TY - CONF

T1 - A method for classifying mental tasks in the space of EEG transforms

AU - Cordeiro De Amorim, Renato

AU - Mirkin, Boris

AU - Q. Gan, John

N1 - Renato Cordeiro De Amorim, Boris Mirkin, John Q. Gan, ‘A method for classifying mental tasks in the space of EEG transforms’, paper presented at the UK Workshop on Computational Intelligence, Nottingham, UK, 7-9 September, 2009.

PY - 2009

Y1 - 2009

N2 - In this article we describe a new method for supervised classification of EEG signals. This method applies to the power spectrum density data and assignsclass-dependent information weights to individual pixels, so that the decision is defined by the summary weights of the most informative pixel features. Weexperimentally analyze several versions of the approach. The informative features appear to be rather similar among different individuals, thus supporting the view that there are subject independent general brain patterns for the same mental task

AB - In this article we describe a new method for supervised classification of EEG signals. This method applies to the power spectrum density data and assignsclass-dependent information weights to individual pixels, so that the decision is defined by the summary weights of the most informative pixel features. Weexperimentally analyze several versions of the approach. The informative features appear to be rather similar among different individuals, thus supporting the view that there are subject independent general brain patterns for the same mental task

M3 - Paper

T2 - UK Workshop on Computational Intelligence

Y2 - 7 September 2009 through 9 September 2009

ER -

A method for classifying mental tasks in the space of EEG transforms

Abstract

Workshop

Access to Document

Fingerprint

Cite this