Building predictive models of emotion with functional near-infrared spectroscopy

Danushka Bandara, Senem Velipasalar, Sarah Bratt, Leanne M Hirshfield

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

We demonstrate the capability of discriminating between affective states on the valence and arousal dimensions using functional near-infrared spectroscopy (fNIRS), a practical non-invasive device that benefits from its ability to localize activation in functional brain regions with spatial resolution superior to the Electroencephalograph (EEG). The high spatial resolution of fNIRS enables us to identify the neural correlates of emotion with spatial precision comparable to fMRI, but without requiring the use of the constricting and impractical fMRI scanner. We make these predictions across subjects, creating the capacity to generalize the model to new participants. We designed the experiment and evaluated our results in the context of a prior experiment—based on the same basic protocol and stimulus materials—which used EEG to measure participants’ valence and arousal. The F1-scores achieved by our classifiers suggest that fNIRS is particularly useful at distinguishing between high and low levels of valence (F1-score of 0.739), which has proven to be difficult to measure with physiological sensors.

Original languageEnglish (US)
Pages (from-to)75-85
Number of pages11
JournalInternational Journal of Human Computer Studies
Volume110
DOIs
StatePublished - Feb 1 2018

Fingerprint

Near infrared spectroscopy
predictive model
emotion
activation
brain
stimulus
Brain
experiment
ability
Classifiers
Chemical activation
Sensors
Experiments
Magnetic Resonance Imaging

Keywords

  • Affective computing
  • Arousal classification
  • Brain signal processing
  • Emotion classification
  • fNIRS
  • Valence classification

ASJC Scopus subject areas

  • Software
  • Human Factors and Ergonomics
  • Education
  • Engineering(all)
  • Human-Computer Interaction
  • Hardware and Architecture

Cite this

Building predictive models of emotion with functional near-infrared spectroscopy. / Bandara, Danushka; Velipasalar, Senem; Bratt, Sarah; Hirshfield, Leanne M.

In: International Journal of Human Computer Studies, Vol. 110, 01.02.2018, p. 75-85.

Research output: Contribution to journalArticle

@article{7b35fb34c6ce452192eaa056a2a0be9f,
title = "Building predictive models of emotion with functional near-infrared spectroscopy",
abstract = "We demonstrate the capability of discriminating between affective states on the valence and arousal dimensions using functional near-infrared spectroscopy (fNIRS), a practical non-invasive device that benefits from its ability to localize activation in functional brain regions with spatial resolution superior to the Electroencephalograph (EEG). The high spatial resolution of fNIRS enables us to identify the neural correlates of emotion with spatial precision comparable to fMRI, but without requiring the use of the constricting and impractical fMRI scanner. We make these predictions across subjects, creating the capacity to generalize the model to new participants. We designed the experiment and evaluated our results in the context of a prior experiment—based on the same basic protocol and stimulus materials—which used EEG to measure participants’ valence and arousal. The F1-scores achieved by our classifiers suggest that fNIRS is particularly useful at distinguishing between high and low levels of valence (F1-score of 0.739), which has proven to be difficult to measure with physiological sensors.",
keywords = "Affective computing, Arousal classification, Brain signal processing, Emotion classification, fNIRS, Valence classification",
author = "Danushka Bandara and Senem Velipasalar and Sarah Bratt and Hirshfield, {Leanne M}",
year = "2018",
month = "2",
day = "1",
doi = "10.1016/j.ijhcs.2017.10.001",
language = "English (US)",
volume = "110",
pages = "75--85",
journal = "International Journal of Human Computer Studies",
issn = "1071-5819",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Building predictive models of emotion with functional near-infrared spectroscopy

AU - Bandara, Danushka

AU - Velipasalar, Senem

AU - Bratt, Sarah

AU - Hirshfield, Leanne M

PY - 2018/2/1

Y1 - 2018/2/1

N2 - We demonstrate the capability of discriminating between affective states on the valence and arousal dimensions using functional near-infrared spectroscopy (fNIRS), a practical non-invasive device that benefits from its ability to localize activation in functional brain regions with spatial resolution superior to the Electroencephalograph (EEG). The high spatial resolution of fNIRS enables us to identify the neural correlates of emotion with spatial precision comparable to fMRI, but without requiring the use of the constricting and impractical fMRI scanner. We make these predictions across subjects, creating the capacity to generalize the model to new participants. We designed the experiment and evaluated our results in the context of a prior experiment—based on the same basic protocol and stimulus materials—which used EEG to measure participants’ valence and arousal. The F1-scores achieved by our classifiers suggest that fNIRS is particularly useful at distinguishing between high and low levels of valence (F1-score of 0.739), which has proven to be difficult to measure with physiological sensors.

AB - We demonstrate the capability of discriminating between affective states on the valence and arousal dimensions using functional near-infrared spectroscopy (fNIRS), a practical non-invasive device that benefits from its ability to localize activation in functional brain regions with spatial resolution superior to the Electroencephalograph (EEG). The high spatial resolution of fNIRS enables us to identify the neural correlates of emotion with spatial precision comparable to fMRI, but without requiring the use of the constricting and impractical fMRI scanner. We make these predictions across subjects, creating the capacity to generalize the model to new participants. We designed the experiment and evaluated our results in the context of a prior experiment—based on the same basic protocol and stimulus materials—which used EEG to measure participants’ valence and arousal. The F1-scores achieved by our classifiers suggest that fNIRS is particularly useful at distinguishing between high and low levels of valence (F1-score of 0.739), which has proven to be difficult to measure with physiological sensors.

KW - Affective computing

KW - Arousal classification

KW - Brain signal processing

KW - Emotion classification

KW - fNIRS

KW - Valence classification

UR - http://www.scopus.com/inward/record.url?scp=85032677223&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85032677223&partnerID=8YFLogxK

U2 - 10.1016/j.ijhcs.2017.10.001

DO - 10.1016/j.ijhcs.2017.10.001

M3 - Article

AN - SCOPUS:85032677223

VL - 110

SP - 75

EP - 85

JO - International Journal of Human Computer Studies

JF - International Journal of Human Computer Studies

SN - 1071-5819

ER -