Estimating cognitive state using EEG signals

Tian Lan, Andre Adami, Deniz Erdogmus, Misha Pavel

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

4 Citations (Scopus)

Abstract

Using EEG signals to estimate cognitive state has drawn increasing attention in recently years, especially in the context of brain-computer interface (BCI) design. However, this goal is extremely difficult because, in addition to the complex relationships between the cognitive state and EEG signals that yields the non-stationarity of the features extracted from EEG signals, there are artefacts introduced by eye blinks and head and body motion. In this paper, we present a classification system, which can estimate the subject's cognitive state from the measured EEG signals. In the proposed system, a mutual information based method is employed to reduce the dimensionality of the features as well as to increase the robustness of the system. A committee of three classifiers was implemented and the majority voting results of the committee are taken to be the final decisions. The results of a preliminary test with data from freely moving subjects performing various tasks as opposed to the strictly controlled experimental set-ups of BCI provide strong support for this approach.

Original languageEnglish (US)
Title of host publication13th European Signal Processing Conference, EUSIPCO 2005
Pages1387-1390
Number of pages4
StatePublished - 2005
Event13th European Signal Processing Conference, EUSIPCO 2005 - Antalya, Turkey
Duration: Sep 4 2005Sep 8 2005

Other

Other13th European Signal Processing Conference, EUSIPCO 2005
CountryTurkey
CityAntalya
Period9/4/059/8/05

Fingerprint

Electroencephalography
Brain computer interface
Classifiers

ASJC Scopus subject areas

  • Signal Processing

Cite this

Lan, T., Adami, A., Erdogmus, D., & Pavel, M. (2005). Estimating cognitive state using EEG signals. In 13th European Signal Processing Conference, EUSIPCO 2005 (pp. 1387-1390)

Estimating cognitive state using EEG signals. / Lan, Tian; Adami, Andre; Erdogmus, Deniz; Pavel, Misha.

13th European Signal Processing Conference, EUSIPCO 2005. 2005. p. 1387-1390.

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

Lan, T, Adami, A, Erdogmus, D & Pavel, M 2005, Estimating cognitive state using EEG signals. in 13th European Signal Processing Conference, EUSIPCO 2005. pp. 1387-1390, 13th European Signal Processing Conference, EUSIPCO 2005, Antalya, Turkey, 9/4/05.
Lan T, Adami A, Erdogmus D, Pavel M. Estimating cognitive state using EEG signals. In 13th European Signal Processing Conference, EUSIPCO 2005. 2005. p. 1387-1390
Lan, Tian ; Adami, Andre ; Erdogmus, Deniz ; Pavel, Misha. / Estimating cognitive state using EEG signals. 13th European Signal Processing Conference, EUSIPCO 2005. 2005. pp. 1387-1390
@inproceedings{dec346aec3954b01bb7132fe76befe54,
title = "Estimating cognitive state using EEG signals",
abstract = "Using EEG signals to estimate cognitive state has drawn increasing attention in recently years, especially in the context of brain-computer interface (BCI) design. However, this goal is extremely difficult because, in addition to the complex relationships between the cognitive state and EEG signals that yields the non-stationarity of the features extracted from EEG signals, there are artefacts introduced by eye blinks and head and body motion. In this paper, we present a classification system, which can estimate the subject's cognitive state from the measured EEG signals. In the proposed system, a mutual information based method is employed to reduce the dimensionality of the features as well as to increase the robustness of the system. A committee of three classifiers was implemented and the majority voting results of the committee are taken to be the final decisions. The results of a preliminary test with data from freely moving subjects performing various tasks as opposed to the strictly controlled experimental set-ups of BCI provide strong support for this approach.",
author = "Tian Lan and Andre Adami and Deniz Erdogmus and Misha Pavel",
year = "2005",
language = "English (US)",
isbn = "1604238216",
pages = "1387--1390",
booktitle = "13th European Signal Processing Conference, EUSIPCO 2005",

}

TY - GEN

T1 - Estimating cognitive state using EEG signals

AU - Lan, Tian

AU - Adami, Andre

AU - Erdogmus, Deniz

AU - Pavel, Misha

PY - 2005

Y1 - 2005

N2 - Using EEG signals to estimate cognitive state has drawn increasing attention in recently years, especially in the context of brain-computer interface (BCI) design. However, this goal is extremely difficult because, in addition to the complex relationships between the cognitive state and EEG signals that yields the non-stationarity of the features extracted from EEG signals, there are artefacts introduced by eye blinks and head and body motion. In this paper, we present a classification system, which can estimate the subject's cognitive state from the measured EEG signals. In the proposed system, a mutual information based method is employed to reduce the dimensionality of the features as well as to increase the robustness of the system. A committee of three classifiers was implemented and the majority voting results of the committee are taken to be the final decisions. The results of a preliminary test with data from freely moving subjects performing various tasks as opposed to the strictly controlled experimental set-ups of BCI provide strong support for this approach.

AB - Using EEG signals to estimate cognitive state has drawn increasing attention in recently years, especially in the context of brain-computer interface (BCI) design. However, this goal is extremely difficult because, in addition to the complex relationships between the cognitive state and EEG signals that yields the non-stationarity of the features extracted from EEG signals, there are artefacts introduced by eye blinks and head and body motion. In this paper, we present a classification system, which can estimate the subject's cognitive state from the measured EEG signals. In the proposed system, a mutual information based method is employed to reduce the dimensionality of the features as well as to increase the robustness of the system. A committee of three classifiers was implemented and the majority voting results of the committee are taken to be the final decisions. The results of a preliminary test with data from freely moving subjects performing various tasks as opposed to the strictly controlled experimental set-ups of BCI provide strong support for this approach.

UR - http://www.scopus.com/inward/record.url?scp=84863691855&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84863691855&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1604238216

SN - 9781604238211

SP - 1387

EP - 1390

BT - 13th European Signal Processing Conference, EUSIPCO 2005

ER -