Towards emotion recognition for virtual environments: an evaluation of eeg features on benchmark dataset

M. L. R. Menezes, A Samara, L Galway, A Sant’Anna, A Verikas, F Alonso-Fernandez, H Wang, R Bond

Research output: Contribution to journalArticle

11 Citations (Scopus)

Abstract

One of the challenges in virtual environments is the difficulty users have in interacting with these increasingly complex systems. Ultimately, endowing machines with the ability to perceive users emotions will enable a more intuitive and reliable interaction. Consequently, using the electroencephalogram as a bio-signal sensor, the affective state of a user can be modelled and subsequently utilised in order to achieve a system that can recognise and react to the user’s emotions. This paper investigates features extracted from electroencephalogram signals for the purpose of affective state modelling based on Russell’s Circumplex Model. Investigations are presented that aim to provide the foundation for future work in modelling user affect to enhance interaction experience in virtual environments. The DEAP dataset was used within this work, along with a Support Vector Machine and Random Forest, which yielded reasonable classification accuracies for Valence and Arousal using feature vectors based on statistical measurements and band power from the α, β, δ, and θ waves and High Order Crossing of the EEG signal.
LanguageEnglish
Pages1003-1013
JournalPersonal and Ubiquitous Computing
Volume21
Issue number6
Early online date22 Aug 2017
DOIs
Publication statusE-pub ahead of print - 22 Aug 2017

Fingerprint

Electroencephalography
Virtual reality
Support vector machines
Large scale systems
Sensors
Virtual environments
Benchmark
Evaluation
Emotion
Electroencephalogram
Interaction

Keywords

  • Affective Computing
  • Virtual Environment
  • EEG
  • Emotion Recognition
  • Feature Extraction

Cite this

Menezes, M. L. R. ; Samara, A ; Galway, L ; Sant’Anna, A ; Verikas, A ; Alonso-Fernandez, F ; Wang, H ; Bond, R. / Towards emotion recognition for virtual environments: an evaluation of eeg features on benchmark dataset. In: Personal and Ubiquitous Computing. 2017 ; Vol. 21, No. 6. pp. 1003-1013.
@article{0f1c2b2bbb204e7e97b6cfb057d1172e,
title = "Towards emotion recognition for virtual environments: an evaluation of eeg features on benchmark dataset",
abstract = "One of the challenges in virtual environments is the difficulty users have in interacting with these increasingly complex systems. Ultimately, endowing machines with the ability to perceive users emotions will enable a more intuitive and reliable interaction. Consequently, using the electroencephalogram as a bio-signal sensor, the affective state of a user can be modelled and subsequently utilised in order to achieve a system that can recognise and react to the user’s emotions. This paper investigates features extracted from electroencephalogram signals for the purpose of affective state modelling based on Russell’s Circumplex Model. Investigations are presented that aim to provide the foundation for future work in modelling user affect to enhance interaction experience in virtual environments. The DEAP dataset was used within this work, along with a Support Vector Machine and Random Forest, which yielded reasonable classification accuracies for Valence and Arousal using feature vectors based on statistical measurements and band power from the α, β, δ, and θ waves and High Order Crossing of the EEG signal.",
keywords = "Affective Computing, Virtual Environment, EEG, Emotion Recognition, Feature Extraction",
author = "Menezes, {M. L. R.} and A Samara and L Galway and A Sant’Anna and A Verikas and F Alonso-Fernandez and H Wang and R Bond",
year = "2017",
month = "8",
day = "22",
doi = "10.1007/s00779-017-1072-7",
language = "English",
volume = "21",
pages = "1003--1013",
journal = "Personal and Ubiquitous Computing",
issn = "1617-4909",
number = "6",

}

Towards emotion recognition for virtual environments: an evaluation of eeg features on benchmark dataset. / Menezes, M. L. R.; Samara, A; Galway, L; Sant’Anna, A; Verikas, A; Alonso-Fernandez, F; Wang, H; Bond, R.

In: Personal and Ubiquitous Computing, Vol. 21, No. 6, 22.08.2017, p. 1003-1013.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Towards emotion recognition for virtual environments: an evaluation of eeg features on benchmark dataset

AU - Menezes, M. L. R.

AU - Samara, A

AU - Galway, L

AU - Sant’Anna, A

AU - Verikas, A

AU - Alonso-Fernandez, F

AU - Wang, H

AU - Bond, R

PY - 2017/8/22

Y1 - 2017/8/22

N2 - One of the challenges in virtual environments is the difficulty users have in interacting with these increasingly complex systems. Ultimately, endowing machines with the ability to perceive users emotions will enable a more intuitive and reliable interaction. Consequently, using the electroencephalogram as a bio-signal sensor, the affective state of a user can be modelled and subsequently utilised in order to achieve a system that can recognise and react to the user’s emotions. This paper investigates features extracted from electroencephalogram signals for the purpose of affective state modelling based on Russell’s Circumplex Model. Investigations are presented that aim to provide the foundation for future work in modelling user affect to enhance interaction experience in virtual environments. The DEAP dataset was used within this work, along with a Support Vector Machine and Random Forest, which yielded reasonable classification accuracies for Valence and Arousal using feature vectors based on statistical measurements and band power from the α, β, δ, and θ waves and High Order Crossing of the EEG signal.

AB - One of the challenges in virtual environments is the difficulty users have in interacting with these increasingly complex systems. Ultimately, endowing machines with the ability to perceive users emotions will enable a more intuitive and reliable interaction. Consequently, using the electroencephalogram as a bio-signal sensor, the affective state of a user can be modelled and subsequently utilised in order to achieve a system that can recognise and react to the user’s emotions. This paper investigates features extracted from electroencephalogram signals for the purpose of affective state modelling based on Russell’s Circumplex Model. Investigations are presented that aim to provide the foundation for future work in modelling user affect to enhance interaction experience in virtual environments. The DEAP dataset was used within this work, along with a Support Vector Machine and Random Forest, which yielded reasonable classification accuracies for Valence and Arousal using feature vectors based on statistical measurements and band power from the α, β, δ, and θ waves and High Order Crossing of the EEG signal.

KW - Affective Computing

KW - Virtual Environment

KW - EEG

KW - Emotion Recognition

KW - Feature Extraction

U2 - 10.1007/s00779-017-1072-7

DO - 10.1007/s00779-017-1072-7

M3 - Article

VL - 21

SP - 1003

EP - 1013

JO - Personal and Ubiquitous Computing

T2 - Personal and Ubiquitous Computing

JF - Personal and Ubiquitous Computing

SN - 1617-4909

IS - 6

ER -