Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos

S. Koelstra; A. Yazdani; M. Soleymani; C. Mühl; J.-L. Lee; Antinus Nijholt; T. Pun; T. Ebrahimi; I. Patras

doi:10.1007/978-3-642-15314-3_9

Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos

S. Koelstra, A. Yazdani, M. Soleymani, C. Mühl, J.-L. Lee, Antinus Nijholt, T. Pun, T. Ebrahimi, I. Patras

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

158 Citations (Scopus)

1 Downloads (Pure)

Abstract

Recently, the field of automatic recognition of users' affective states has gained a great deal of attention. Automatic, implicit recognition of affective states has many applications, ranging from personalized content recommendation to automatic tutoring systems. In this work, we present some promising results of our research in classification of emotions induced by watching music videos. We show robust correlations between users' self-assessments of arousal and valence and the frequency powers of their EEG activity. We present methods for single trial classification using both EEG and peripheral physiological signals. For EEG, an average (maximum) classification rate of 55.7% (67.0%) for arousal and 58.8% (76.0%) for valence was obtained. For peripheral physiological signals, the results were 58.9% (85.5%) for arousal and 54.2% (78.5%) for valence.

Original language	Undefined
Title of host publication	Proceedings 2010 International Conference on Brain Informatics (BI 2010)
Editors	Y. Yao, R. Sun, T. Poggio, J. Liu, N. Zhong, J. Huang
Place of Publication	Berlin
Publisher	Springer
Pages	89-100
Number of pages	12
ISBN (Print)	978-3-642-15313-6
DOIs	https://doi.org/10.1007/978-3-642-15314-3_9
Publication status	Published - 4 Sept 2010
Event	Proceedings 2010 International Conference on Brain Informatics (BI 2010), Toronto: Proceedings 2010 International Conference on Brain Informatics (BI 2010) - Berlin Duration: 4 Sept 2010 → …

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Verlag
Volume	6334
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Proceedings 2010 International Conference on Brain Informatics (BI 2010), Toronto
City	Berlin
Period	4/09/10 → …

Keywords

METIS-271010
MUSIC
Affective Computing
IR-73064
EWI-18368
EEG
Emotion induction
HMI-MI: MULTIMODAL INTERACTIONS
Physiological Signals

Access to Document

10.1007/978-3-642-15314-3_9

http://eprints.eemcs.utwente.nl/secure2/18368/01/bi2010.pdf

Cite this

Koelstra, S., Yazdani, A., Soleymani, M., Mühl, C., Lee, J.-L., Nijholt, A., Pun, T., Ebrahimi, T., & Patras, I. (2010). Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos. In Y. Yao, R. Sun, T. Poggio, J. Liu, N. Zhong, & J. Huang (Eds.), Proceedings 2010 International Conference on Brain Informatics (BI 2010) (pp. 89-100). (Lecture Notes in Computer Science; Vol. 6334). Springer. https://doi.org/10.1007/978-3-642-15314-3_9

Koelstra, S. ; Yazdani, A. ; Soleymani, M. et al. / Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos. Proceedings 2010 International Conference on Brain Informatics (BI 2010). editor / Y. Yao ; R. Sun ; T. Poggio ; J. Liu ; N. Zhong ; J. Huang. Berlin : Springer, 2010. pp. 89-100 (Lecture Notes in Computer Science).

@inproceedings{abc05f4f7ac849b2be884a5bd3b316da,

title = "Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos",

abstract = "Recently, the field of automatic recognition of users' affective states has gained a great deal of attention. Automatic, implicit recognition of affective states has many applications, ranging from personalized content recommendation to automatic tutoring systems. In this work, we present some promising results of our research in classification of emotions induced by watching music videos. We show robust correlations between users' self-assessments of arousal and valence and the frequency powers of their EEG activity. We present methods for single trial classification using both EEG and peripheral physiological signals. For EEG, an average (maximum) classification rate of 55.7% (67.0%) for arousal and 58.8% (76.0%) for valence was obtained. For peripheral physiological signals, the results were 58.9% (85.5%) for arousal and 54.2% (78.5%) for valence.",

keywords = "METIS-271010, MUSIC, Affective Computing, IR-73064, EWI-18368, EEG, Emotion induction, HMI-MI: MULTIMODAL INTERACTIONS, Physiological Signals",

author = "S. Koelstra and A. Yazdani and M. Soleymani and C. M{\"u}hl and J.-L. Lee and Antinus Nijholt and T. Pun and T. Ebrahimi and I. Patras",

note = "10.1007/978-3-642-15314-3_9 ; Proceedings 2010 International Conference on Brain Informatics (BI 2010), Toronto ; Conference date: 04-09-2010",

year = "2010",

month = sep,

day = "4",

doi = "10.1007/978-3-642-15314-3_9",

language = "Undefined",

isbn = "978-3-642-15313-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "89--100",

editor = "Y. Yao and R. Sun and T. Poggio and J. Liu and N. Zhong and J. Huang",

booktitle = "Proceedings 2010 International Conference on Brain Informatics (BI 2010)",

address = "Germany",

}

Koelstra, S, Yazdani, A, Soleymani, M, Mühl, C, Lee, J-L, Nijholt, A, Pun, T, Ebrahimi, T & Patras, I 2010, Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos. in Y Yao, R Sun, T Poggio, J Liu, N Zhong & J Huang (eds), Proceedings 2010 International Conference on Brain Informatics (BI 2010). Lecture Notes in Computer Science, vol. 6334, Springer, Berlin, pp. 89-100, Proceedings 2010 International Conference on Brain Informatics (BI 2010), Toronto, Berlin, 4/09/10. https://doi.org/10.1007/978-3-642-15314-3_9

Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos. / Koelstra, S.; Yazdani, A.; Soleymani, M. et al.
Proceedings 2010 International Conference on Brain Informatics (BI 2010). ed. / Y. Yao; R. Sun; T. Poggio; J. Liu; N. Zhong; J. Huang. Berlin: Springer, 2010. p. 89-100 (Lecture Notes in Computer Science; Vol. 6334).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos

AU - Koelstra, S.

AU - Yazdani, A.

AU - Soleymani, M.

AU - Mühl, C.

AU - Lee, J.-L.

AU - Nijholt, Antinus

AU - Pun, T.

AU - Ebrahimi, T.

AU - Patras, I.

N1 - 10.1007/978-3-642-15314-3_9

PY - 2010/9/4

Y1 - 2010/9/4

N2 - Recently, the field of automatic recognition of users' affective states has gained a great deal of attention. Automatic, implicit recognition of affective states has many applications, ranging from personalized content recommendation to automatic tutoring systems. In this work, we present some promising results of our research in classification of emotions induced by watching music videos. We show robust correlations between users' self-assessments of arousal and valence and the frequency powers of their EEG activity. We present methods for single trial classification using both EEG and peripheral physiological signals. For EEG, an average (maximum) classification rate of 55.7% (67.0%) for arousal and 58.8% (76.0%) for valence was obtained. For peripheral physiological signals, the results were 58.9% (85.5%) for arousal and 54.2% (78.5%) for valence.

AB - Recently, the field of automatic recognition of users' affective states has gained a great deal of attention. Automatic, implicit recognition of affective states has many applications, ranging from personalized content recommendation to automatic tutoring systems. In this work, we present some promising results of our research in classification of emotions induced by watching music videos. We show robust correlations between users' self-assessments of arousal and valence and the frequency powers of their EEG activity. We present methods for single trial classification using both EEG and peripheral physiological signals. For EEG, an average (maximum) classification rate of 55.7% (67.0%) for arousal and 58.8% (76.0%) for valence was obtained. For peripheral physiological signals, the results were 58.9% (85.5%) for arousal and 54.2% (78.5%) for valence.

KW - METIS-271010

KW - MUSIC

KW - Affective Computing

KW - IR-73064

KW - EWI-18368

KW - EEG

KW - Emotion induction

KW - HMI-MI: MULTIMODAL INTERACTIONS

KW - Physiological Signals

U2 - 10.1007/978-3-642-15314-3_9

DO - 10.1007/978-3-642-15314-3_9

M3 - Conference contribution

SN - 978-3-642-15313-6

T3 - Lecture Notes in Computer Science

SP - 89

EP - 100

BT - Proceedings 2010 International Conference on Brain Informatics (BI 2010)

A2 - Yao, Y.

A2 - Sun, R.

A2 - Poggio, T.

A2 - Liu, J.

A2 - Zhong, N.

A2 - Huang, J.

PB - Springer

CY - Berlin

T2 - Proceedings 2010 International Conference on Brain Informatics (BI 2010), Toronto

Y2 - 4 September 2010

ER -

Koelstra S, Yazdani A, Soleymani M, Mühl C, Lee JL, Nijholt A et al. Single Trial Classification of EEG and Peripheral Physiological Signals for Recognition of Emotions Induced by Music Videos. In Yao Y, Sun R, Poggio T, Liu J, Zhong N, Huang J, editors, Proceedings 2010 International Conference on Brain Informatics (BI 2010). Berlin: Springer. 2010. p. 89-100. (Lecture Notes in Computer Science). doi: 10.1007/978-3-642-15314-3_9