Brain-Computer Interface for Generating Personally Attractive Images
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Brain-Computer Interface for Generating Personally Attractive Images. / Spape, Michiel; Davis, Keith M.; Kangassalo, Lauri; Ravaja, Niklas; Sovijarvi-Spape, Zania; Ruotsalo, Tuukka.
In: IEEE Transactions on Affective Computing, Vol. 14, No. 1, 2023, p. 637-649.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Brain-Computer Interface for Generating Personally Attractive Images
AU - Spape, Michiel
AU - Davis, Keith M.
AU - Kangassalo, Lauri
AU - Ravaja, Niklas
AU - Sovijarvi-Spape, Zania
AU - Ruotsalo, Tuukka
N1 - Publisher Copyright: © 2010-2012 IEEE.
PY - 2023
Y1 - 2023
N2 - While we instantaneously recognize a face as attractive, it is much harder to explain what exactly defines personal attraction. This suggests that attraction depends on implicit processing of complex, culturally and individually defined features. Generative adversarial neural networks (GANs), which learn to mimic complex data distributions, can potentially model subjective preferences unconstrained by pre-defined model parameterization. Here, we present generative brain-computer interfaces (GBCI), coupling GANs with brain-computer interfaces. GBCI first presents a selection of images and captures personalized attractiveness reactions toward the images via electroencephalography. These reactions are then used to control a GAN model, finding a representation that matches the features constituting an attractive image for an individual. We conducted an experiment (N = 30) to validate GBCI using a face-generating GAN and producing images that are hypothesized to be individually attractive. In double-blind evaluation of the GBCI-produced images against matched controls, we found GBCI yielded highly accurate results. Thus, the use of EEG responses to control a GAN presents a valid tool for interactive information-generation. Furthermore, the GBCI-derived images visually replicated known effects from social neuroscience, suggesting that the individually responsive, generative nature of GBCI provides a powerful, new tool in mapping individual differences and visualizing cognitive-affective processing.
AB - While we instantaneously recognize a face as attractive, it is much harder to explain what exactly defines personal attraction. This suggests that attraction depends on implicit processing of complex, culturally and individually defined features. Generative adversarial neural networks (GANs), which learn to mimic complex data distributions, can potentially model subjective preferences unconstrained by pre-defined model parameterization. Here, we present generative brain-computer interfaces (GBCI), coupling GANs with brain-computer interfaces. GBCI first presents a selection of images and captures personalized attractiveness reactions toward the images via electroencephalography. These reactions are then used to control a GAN model, finding a representation that matches the features constituting an attractive image for an individual. We conducted an experiment (N = 30) to validate GBCI using a face-generating GAN and producing images that are hypothesized to be individually attractive. In double-blind evaluation of the GBCI-produced images against matched controls, we found GBCI yielded highly accurate results. Thus, the use of EEG responses to control a GAN presents a valid tool for interactive information-generation. Furthermore, the GBCI-derived images visually replicated known effects from social neuroscience, suggesting that the individually responsive, generative nature of GBCI provides a powerful, new tool in mapping individual differences and visualizing cognitive-affective processing.
KW - attraction
KW - Brain-computer interfaces
KW - electroencephalography (EEG)
KW - generative adversarial networks (GAN)
KW - image generation
KW - individual differences
KW - personal preferences
UR - http://www.scopus.com/inward/record.url?scp=85100846399&partnerID=8YFLogxK
U2 - 10.1109/TAFFC.2021.3059043
DO - 10.1109/TAFFC.2021.3059043
M3 - Journal article
AN - SCOPUS:85100846399
VL - 14
SP - 637
EP - 649
JO - IEEE Transactions on Affective Computing
JF - IEEE Transactions on Affective Computing
SN - 1949-3045
IS - 1
ER -
ID: 340546860