On using EEG signals for emotion modeling and biometry

Miguel Arevalillo-Herráez; Guillermo Chicote-Huete; Francesc J. Ferri; Aladdin Ayesh; Jesús G. Boticario; Stamos Katsigiannis; Naeem Ramzan; Pablo Arnau González

On using EEG signals for emotion modeling and biometry

Miguel Arevalillo-Herráez, Guillermo Chicote-Huete, Francesc J. Ferri, Aladdin Ayesh, Jesús G. Boticario, Stamos Katsigiannis, Naeem Ramzan, Pablo Arnau González

School of Computing, Engineering and Physical Sciences

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

96 Downloads (Pure)

Abstract

A number of previous works have adopted a subject independent approach for recognizing emotions from Electroencephalography (EEG) signals, and attempted to build a global model by treating data from different subjects as if they belong to the same individual. In this paper we visually explore the data provided in four different standard datasets when using Power Spectral Density features, and show that the subject-dependent component in the EEG signal is far stronger than the emotion-related component. In addition, the session-dependency that is also found discourages the application of this type of features from EEG signals in a biometric context.

Original language	English
Title of host publication	ESM '2019 Conference Proceedings
Editors	Pilar Fuster-Parra, Oscar Valero Sierra
Publisher	European Multidisciplinary Society for Modelling and Simulation Technology
Pages	229-233
Number of pages	5
ISBN (Electronic)	9789492859099
Publication status	Published - 15 Oct 2019
Event	33rd European Simulation and Modelling Conference - Universitat de les Illes Balears, Palma de Mallorca, Spain Duration: 28 Oct 2019 → 30 Oct 2019 https://www.eurosis.org/conf/esm/2019/index.html

Conference

Conference	33rd European Simulation and Modelling Conference
Abbreviated title	ESM'2019
Country/Territory	Spain
City	Palma de Mallorca
Period	28/10/19 → 30/10/19
Internet address	https://www.eurosis.org/conf/esm/2019/index.html

Keywords

EEG
Affect
Biometrics
Emotion modeling

Access to Document

2019 09 04 Arevalillo-Herraez et al EEGAccepted author manuscript, 281 KB

https://www.eurosis.org/cms/?q=taxonomy/term/58

Cite this

Arevalillo-Herráez, M., Chicote-Huete, G., Ferri, F. J., Ayesh, A., Boticario, J. G., Katsigiannis, S., Ramzan, N., & Arnau González, P. (2019). On using EEG signals for emotion modeling and biometry. In P. Fuster-Parra, & O. V. Sierra (Eds.), ESM '2019 Conference Proceedings (pp. 229-233). European Multidisciplinary Society for Modelling and Simulation Technology. https://www.eurosis.org/cms/?q=taxonomy/term/58

@inproceedings{b0f077429bd8455faa866b25a9784e14,

title = "On using EEG signals for emotion modeling and biometry",

abstract = "A number of previous works have adopted a subject independent approach for recognizing emotions from Electroencephalography (EEG) signals, and attempted to build a global model by treating data from different subjects as if they belong to the same individual. In this paper we visually explore the data provided in four different standard datasets when using Power Spectral Density features, and show that the subject-dependent component in the EEG signal is far stronger than the emotion-related component. In addition, the session-dependency that is also found discourages the application of this type of features from EEG signals in a biometric context.",

keywords = "EEG, Affect, Biometrics, Emotion modeling",

author = "Miguel Arevalillo-Herr{\'a}ez and Guillermo Chicote-Huete and Ferri, {Francesc J.} and Aladdin Ayesh and Boticario, {Jes{\'u}s G.} and Stamos Katsigiannis and Naeem Ramzan and {Arnau Gonz{\'a}lez}, Pablo",

year = "2019",

month = oct,

day = "15",

language = "English",

pages = "229--233",

editor = "Pilar Fuster-Parra and Sierra, {Oscar Valero}",

booktitle = "ESM '2019 Conference Proceedings",

publisher = "European Multidisciplinary Society for Modelling and Simulation Technology",

address = "Belgium",

note = "33rd European Simulation and Modelling Conference, ESM'2019 ; Conference date: 28-10-2019 Through 30-10-2019",

url = "https://www.eurosis.org/conf/esm/2019/index.html",

}

Arevalillo-Herráez, M, Chicote-Huete, G, Ferri, FJ, Ayesh, A, Boticario, JG, Katsigiannis, S, Ramzan, N & Arnau González, P 2019, On using EEG signals for emotion modeling and biometry. in P Fuster-Parra & OV Sierra (eds), ESM '2019 Conference Proceedings. European Multidisciplinary Society for Modelling and Simulation Technology, pp. 229-233, 33rd European Simulation and Modelling Conference, Palma de Mallorca, Spain, 28/10/19. <https://www.eurosis.org/cms/?q=taxonomy/term/58>

On using EEG signals for emotion modeling and biometry. / Arevalillo-Herráez, Miguel; Chicote-Huete, Guillermo; Ferri, Francesc J. et al.
ESM '2019 Conference Proceedings. ed. / Pilar Fuster-Parra; Oscar Valero Sierra. European Multidisciplinary Society for Modelling and Simulation Technology, 2019. p. 229-233.

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

TY - GEN

T1 - On using EEG signals for emotion modeling and biometry

AU - Arevalillo-Herráez, Miguel

AU - Chicote-Huete, Guillermo

AU - Ferri, Francesc J.

AU - Ayesh, Aladdin

AU - Boticario, Jesús G.

AU - Katsigiannis, Stamos

AU - Ramzan, Naeem

AU - Arnau González, Pablo

PY - 2019/10/15

Y1 - 2019/10/15

N2 - A number of previous works have adopted a subject independent approach for recognizing emotions from Electroencephalography (EEG) signals, and attempted to build a global model by treating data from different subjects as if they belong to the same individual. In this paper we visually explore the data provided in four different standard datasets when using Power Spectral Density features, and show that the subject-dependent component in the EEG signal is far stronger than the emotion-related component. In addition, the session-dependency that is also found discourages the application of this type of features from EEG signals in a biometric context.

AB - A number of previous works have adopted a subject independent approach for recognizing emotions from Electroencephalography (EEG) signals, and attempted to build a global model by treating data from different subjects as if they belong to the same individual. In this paper we visually explore the data provided in four different standard datasets when using Power Spectral Density features, and show that the subject-dependent component in the EEG signal is far stronger than the emotion-related component. In addition, the session-dependency that is also found discourages the application of this type of features from EEG signals in a biometric context.

KW - EEG

KW - Affect

KW - Biometrics

KW - Emotion modeling

UR - https://www.eurosis.org/conf/esm/2019/preliminary-programme.html

M3 - Conference contribution

SP - 229

EP - 233

BT - ESM '2019 Conference Proceedings

A2 - Fuster-Parra, Pilar

A2 - Sierra, Oscar Valero

PB - European Multidisciplinary Society for Modelling and Simulation Technology

T2 - 33rd European Simulation and Modelling Conference

Y2 - 28 October 2019 through 30 October 2019

ER -

On using EEG signals for emotion modeling and biometry

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this