User-independent classification of emotions in a mixed arousal-valence model

Mauro Nascimben; Thomas Zoëga  Ramsøy; Luis Emilio Bruni

doi:10.1109/BIBE.2019.00086

User-independent classification of emotions in a mixed arousal-valence model

Mauro Nascimben^*, Thomas Zoëga Ramsøy, Luis Emilio Bruni

^*Corresponding author for this work

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

Abstract

In this work we classified EEG features connected with emotions elicited by musical videos. To detect emotions, we used a user-independent approach with data coming from multiple participants in order to test the "peak-end rule". Participant's video ratings were processed to create a mixed valence-arousal labelling. Input features were refined using a combination of feature ranking and data reduction based on intrinsic dimensionality search. Compared to previous literature, our results show that the proposed mixed arousal-valence classification is compatible with previous works applying a distinct arousal or valence classification.

Original language	English
Title of host publication	Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019
Number of pages	5
Publisher	IEEE
Publication date	Oct 2019
Pages	445 - 449
Article number	8941735
ISBN (Electronic)	9781728146171
DOIs	https://doi.org/10.1109/BIBE.2019.00086
Publication status	Published - Oct 2019
Event	2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE) - Duration: 28 Oct 2019 → 30 Oct 2019 https://ieeexplore.ieee.org/xpl/conhome/8936463/proceeding

Conference

Conference	2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)
Period	28/10/2019 → 30/10/2019
Internet address	https://ieeexplore.ieee.org/xpl/conhome/8936463/proceeding

Series	International Conference on Bioinformatics and Bioengineering
ISSN	2471-7819

Keywords

EEG
emotion recognition
human-computer interaction

Access to Document

10.1109/BIBE.2019.00086

https://zenodo.org/record/4227854/files/IEEEBIBE2019Emot.pdf

Cite this

Nascimben, M., Ramsøy, T. Z., & Bruni, L. E. (2019). User-independent classification of emotions in a mixed arousal-valence model. In Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019 (pp. 445 - 449). [8941735] IEEE. International Conference on Bioinformatics and Bioengineering https://doi.org/10.1109/BIBE.2019.00086

@inproceedings{ae00249ffa85460f9c13cf251d0719be,

title = "User-independent classification of emotions in a mixed arousal-valence model",

abstract = "In this work we classified EEG features connected with emotions elicited by musical videos. To detect emotions, we used a user-independent approach with data coming from multiple participants in order to test the {"}peak-end rule{"}. Participant's video ratings were processed to create a mixed valence-arousal labelling. Input features were refined using a combination of feature ranking and data reduction based on intrinsic dimensionality search. Compared to previous literature, our results show that the proposed mixed arousal-valence classification is compatible with previous works applying a distinct arousal or valence classification.",

keywords = "EEG, emotion recognition, human-computer interaction",

author = "Mauro Nascimben and Rams{\o}y, {Thomas Zo{\"e}ga} and Bruni, {Luis Emilio}",

year = "2019",

month = oct,

doi = "10.1109/BIBE.2019.00086",

language = "English",

series = "International Conference on Bioinformatics and Bioengineering",

pages = "445 -- 449",

booktitle = "Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019",

publisher = "IEEE",

address = "United States",

note = "2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE) ; Conference date: 28-10-2019 Through 30-10-2019",

url = "https://ieeexplore.ieee.org/xpl/conhome/8936463/proceeding",

}

Nascimben, M, Ramsøy, TZ & Bruni, LE 2019, User-independent classification of emotions in a mixed arousal-valence model. in Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019., 8941735, IEEE, International Conference on Bioinformatics and Bioengineering, pp. 445 - 449, 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE), 28/10/2019. https://doi.org/10.1109/BIBE.2019.00086

User-independent classification of emotions in a mixed arousal-valence model. / Nascimben, Mauro; Ramsøy, Thomas Zoëga ; Bruni, Luis Emilio.

Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019. IEEE, 2019. p. 445 - 449 8941735 (International Conference on Bioinformatics and Bioengineering).

Research output: Contribution to book/anthology/report/conference proceeding › Article in proceeding › Research › peer-review

TY - GEN

T1 - User-independent classification of emotions in a mixed arousal-valence model

AU - Nascimben, Mauro

AU - Ramsøy, Thomas Zoëga

AU - Bruni, Luis Emilio

PY - 2019/10

Y1 - 2019/10

N2 - In this work we classified EEG features connected with emotions elicited by musical videos. To detect emotions, we used a user-independent approach with data coming from multiple participants in order to test the "peak-end rule". Participant's video ratings were processed to create a mixed valence-arousal labelling. Input features were refined using a combination of feature ranking and data reduction based on intrinsic dimensionality search. Compared to previous literature, our results show that the proposed mixed arousal-valence classification is compatible with previous works applying a distinct arousal or valence classification.

AB - In this work we classified EEG features connected with emotions elicited by musical videos. To detect emotions, we used a user-independent approach with data coming from multiple participants in order to test the "peak-end rule". Participant's video ratings were processed to create a mixed valence-arousal labelling. Input features were refined using a combination of feature ranking and data reduction based on intrinsic dimensionality search. Compared to previous literature, our results show that the proposed mixed arousal-valence classification is compatible with previous works applying a distinct arousal or valence classification.

KW - EEG

KW - emotion recognition

KW - human-computer interaction

UR - http://www.scopus.com/inward/record.url?scp=85078071003&partnerID=8YFLogxK

U2 - 10.1109/BIBE.2019.00086

DO - 10.1109/BIBE.2019.00086

M3 - Article in proceeding

T3 - International Conference on Bioinformatics and Bioengineering

SP - 445

EP - 449

BT - Proceedings - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering, BIBE 2019

PB - IEEE

T2 - 2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)

Y2 - 28 October 2019 through 30 October 2019

ER -

User-independent classification of emotions in a mixed arousal-valence model

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

ViZARTS: Visualization and Adaptive Real-Time Storytelling - for Film, Animation and Games

Cite this

User-independent classification of emotions in a mixed arousal-valence model

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

ViZARTS: Visualization and Adaptive Real-Time Storytelling - for Film, Animation and Games

Cite this