Emotion detection using noisy EEG data

Mina Mikhail, Khaled El-Ayat, Rana El Kaliouby, James Coan, John JB Allen

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

17 Citations (Scopus)

Abstract

Emotion is an important aspect in the interaction between humans. It is fundamental to human experience and rational decision-making. There is a great interest for detecting emotions automatically. A number of techniques have been employed for this purpose using channels such as voice and facial expressions. However, these channels are not very accurate because they can be affected by users' intentions. Other techniques use physiological signals along with electroencephalography (EEG) for emotion detection. However, these approaches are not very practical for real time applications because they either ask the participants to reduce any motion and facial muscle movement or reject EEG data contaminated with artifacts. In this paper, we propose an approach that analyzes highly contaminated EEG data produced from a new emotion elicitation technique. We also use a feature selection mechanism to extract features that are relevant to the emotion detection task based on neuroscience findings. We reached an average accuracy of 51% for joy emotion, 53% for anger, 58% for fear and 61% for sadness.

Original languageEnglish (US)
Title of host publicationACM International Conference Proceeding Series
DOIs
StatePublished - 2010
Event1st Augmented Human International Conference, AH'10 - Megeve, France
Duration: Apr 2 2010Apr 3 2010

Other

Other1st Augmented Human International Conference, AH'10
CountryFrance
CityMegeve
Period4/2/104/3/10

Fingerprint

Electroencephalography
Muscle
Feature extraction
Decision making

Keywords

  • affective computing
  • brain signals
  • feature extraction
  • support vector machines

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Mikhail, M., El-Ayat, K., El Kaliouby, R., Coan, J., & Allen, J. JB. (2010). Emotion detection using noisy EEG data. In ACM International Conference Proceeding Series [1785462] https://doi.org/10.1145/1785455.1785462

Emotion detection using noisy EEG data. / Mikhail, Mina; El-Ayat, Khaled; El Kaliouby, Rana; Coan, James; Allen, John JB.

ACM International Conference Proceeding Series. 2010. 1785462.

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

Mikhail, M, El-Ayat, K, El Kaliouby, R, Coan, J & Allen, JJB 2010, Emotion detection using noisy EEG data. in ACM International Conference Proceeding Series., 1785462, 1st Augmented Human International Conference, AH'10, Megeve, France, 4/2/10. https://doi.org/10.1145/1785455.1785462
Mikhail M, El-Ayat K, El Kaliouby R, Coan J, Allen JJB. Emotion detection using noisy EEG data. In ACM International Conference Proceeding Series. 2010. 1785462 https://doi.org/10.1145/1785455.1785462
Mikhail, Mina ; El-Ayat, Khaled ; El Kaliouby, Rana ; Coan, James ; Allen, John JB. / Emotion detection using noisy EEG data. ACM International Conference Proceeding Series. 2010.
@inproceedings{b62244b4078445e59d2cbe2fd48093dc,
title = "Emotion detection using noisy EEG data",
abstract = "Emotion is an important aspect in the interaction between humans. It is fundamental to human experience and rational decision-making. There is a great interest for detecting emotions automatically. A number of techniques have been employed for this purpose using channels such as voice and facial expressions. However, these channels are not very accurate because they can be affected by users' intentions. Other techniques use physiological signals along with electroencephalography (EEG) for emotion detection. However, these approaches are not very practical for real time applications because they either ask the participants to reduce any motion and facial muscle movement or reject EEG data contaminated with artifacts. In this paper, we propose an approach that analyzes highly contaminated EEG data produced from a new emotion elicitation technique. We also use a feature selection mechanism to extract features that are relevant to the emotion detection task based on neuroscience findings. We reached an average accuracy of 51{\%} for joy emotion, 53{\%} for anger, 58{\%} for fear and 61{\%} for sadness.",
keywords = "affective computing, brain signals, feature extraction, support vector machines",
author = "Mina Mikhail and Khaled El-Ayat and {El Kaliouby}, Rana and James Coan and Allen, {John JB}",
year = "2010",
doi = "10.1145/1785455.1785462",
language = "English (US)",
isbn = "9781605588254",
booktitle = "ACM International Conference Proceeding Series",

}

TY - GEN

T1 - Emotion detection using noisy EEG data

AU - Mikhail, Mina

AU - El-Ayat, Khaled

AU - El Kaliouby, Rana

AU - Coan, James

AU - Allen, John JB

PY - 2010

Y1 - 2010

N2 - Emotion is an important aspect in the interaction between humans. It is fundamental to human experience and rational decision-making. There is a great interest for detecting emotions automatically. A number of techniques have been employed for this purpose using channels such as voice and facial expressions. However, these channels are not very accurate because they can be affected by users' intentions. Other techniques use physiological signals along with electroencephalography (EEG) for emotion detection. However, these approaches are not very practical for real time applications because they either ask the participants to reduce any motion and facial muscle movement or reject EEG data contaminated with artifacts. In this paper, we propose an approach that analyzes highly contaminated EEG data produced from a new emotion elicitation technique. We also use a feature selection mechanism to extract features that are relevant to the emotion detection task based on neuroscience findings. We reached an average accuracy of 51% for joy emotion, 53% for anger, 58% for fear and 61% for sadness.

AB - Emotion is an important aspect in the interaction between humans. It is fundamental to human experience and rational decision-making. There is a great interest for detecting emotions automatically. A number of techniques have been employed for this purpose using channels such as voice and facial expressions. However, these channels are not very accurate because they can be affected by users' intentions. Other techniques use physiological signals along with electroencephalography (EEG) for emotion detection. However, these approaches are not very practical for real time applications because they either ask the participants to reduce any motion and facial muscle movement or reject EEG data contaminated with artifacts. In this paper, we propose an approach that analyzes highly contaminated EEG data produced from a new emotion elicitation technique. We also use a feature selection mechanism to extract features that are relevant to the emotion detection task based on neuroscience findings. We reached an average accuracy of 51% for joy emotion, 53% for anger, 58% for fear and 61% for sadness.

KW - affective computing

KW - brain signals

KW - feature extraction

KW - support vector machines

UR - http://www.scopus.com/inward/record.url?scp=77954461646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77954461646&partnerID=8YFLogxK

U2 - 10.1145/1785455.1785462

DO - 10.1145/1785455.1785462

M3 - Conference contribution

SN - 9781605588254

BT - ACM International Conference Proceeding Series

ER -