Real-time support vector classification and feedback of multiple emotional brain states

Ranganatha Sitaram, Sangkyun Lee, Sergio Ruiz, Mohit Rana, Ralf Veit, Niels Birbaumer

Research output: Contribution to journalArticle

113 Citations (Scopus)

Abstract

An important question that confronts current research in affective neuroscience as well as in the treatment of emotional disorders is whether it is possible to determine the emotional state of a person based on the measurement of brain activity alone. Here, we first show that an online support vector machine (SVM) can be built to recognize two discrete emotional states, such as happiness and disgust from fMRI signals, in healthy individuals instructed to recall emotionally salient episodes from their lives. We report the first application of real-time head motion correction, spatial smoothing and feature selection based on a new method called Effect mapping. The classifier also showed robust prediction rates in decoding three discrete emotional states (happiness, disgust and sadness) in an extended group of participants. Subjective reports ascertained that participants performed emotion imagery and that the online classifier decoded emotions and not arbitrary states of the brain. Offline whole brain classification as well as region-of-interest classification in 24 brain areas previously implicated in emotion processing revealed that the frontal cortex was critically involved in emotion induction by imagery. We also demonstrate an fMRI-BCI based on real-time classification of BOLD signals from multiple brain regions, for each repetition time (TR) of scanning, providing visual feedback of emotional states to the participant for potential applications in the clinical treatment of dysfunctional affect.

Original languageEnglish
Pages (from-to)753-765
Number of pages13
JournalNeuroImage
Volume56
Issue number2
DOIs
Publication statusPublished - May 15 2011

Fingerprint

Emotions
Brain
Happiness
Imagery (Psychotherapy)
Magnetic Resonance Imaging
Sensory Feedback
Frontal Lobe
Neurosciences
Head
Therapeutics
Research

ASJC Scopus subject areas

  • Cognitive Neuroscience
  • Neurology

Cite this

Real-time support vector classification and feedback of multiple emotional brain states. / Sitaram, Ranganatha; Lee, Sangkyun; Ruiz, Sergio; Rana, Mohit; Veit, Ralf; Birbaumer, Niels.

In: NeuroImage, Vol. 56, No. 2, 15.05.2011, p. 753-765.

Research output: Contribution to journalArticle

Sitaram, R, Lee, S, Ruiz, S, Rana, M, Veit, R & Birbaumer, N 2011, 'Real-time support vector classification and feedback of multiple emotional brain states', NeuroImage, vol. 56, no. 2, pp. 753-765. https://doi.org/10.1016/j.neuroimage.2010.08.007
Sitaram, Ranganatha ; Lee, Sangkyun ; Ruiz, Sergio ; Rana, Mohit ; Veit, Ralf ; Birbaumer, Niels. / Real-time support vector classification and feedback of multiple emotional brain states. In: NeuroImage. 2011 ; Vol. 56, No. 2. pp. 753-765.
@article{dfbc6b1957734e56ba332e3293dba0f0,
title = "Real-time support vector classification and feedback of multiple emotional brain states",
abstract = "An important question that confronts current research in affective neuroscience as well as in the treatment of emotional disorders is whether it is possible to determine the emotional state of a person based on the measurement of brain activity alone. Here, we first show that an online support vector machine (SVM) can be built to recognize two discrete emotional states, such as happiness and disgust from fMRI signals, in healthy individuals instructed to recall emotionally salient episodes from their lives. We report the first application of real-time head motion correction, spatial smoothing and feature selection based on a new method called Effect mapping. The classifier also showed robust prediction rates in decoding three discrete emotional states (happiness, disgust and sadness) in an extended group of participants. Subjective reports ascertained that participants performed emotion imagery and that the online classifier decoded emotions and not arbitrary states of the brain. Offline whole brain classification as well as region-of-interest classification in 24 brain areas previously implicated in emotion processing revealed that the frontal cortex was critically involved in emotion induction by imagery. We also demonstrate an fMRI-BCI based on real-time classification of BOLD signals from multiple brain regions, for each repetition time (TR) of scanning, providing visual feedback of emotional states to the participant for potential applications in the clinical treatment of dysfunctional affect.",
author = "Ranganatha Sitaram and Sangkyun Lee and Sergio Ruiz and Mohit Rana and Ralf Veit and Niels Birbaumer",
year = "2011",
month = "5",
day = "15",
doi = "10.1016/j.neuroimage.2010.08.007",
language = "English",
volume = "56",
pages = "753--765",
journal = "NeuroImage",
issn = "1053-8119",
publisher = "Academic Press Inc.",
number = "2",

}

TY - JOUR

T1 - Real-time support vector classification and feedback of multiple emotional brain states

AU - Sitaram, Ranganatha

AU - Lee, Sangkyun

AU - Ruiz, Sergio

AU - Rana, Mohit

AU - Veit, Ralf

AU - Birbaumer, Niels

PY - 2011/5/15

Y1 - 2011/5/15

N2 - An important question that confronts current research in affective neuroscience as well as in the treatment of emotional disorders is whether it is possible to determine the emotional state of a person based on the measurement of brain activity alone. Here, we first show that an online support vector machine (SVM) can be built to recognize two discrete emotional states, such as happiness and disgust from fMRI signals, in healthy individuals instructed to recall emotionally salient episodes from their lives. We report the first application of real-time head motion correction, spatial smoothing and feature selection based on a new method called Effect mapping. The classifier also showed robust prediction rates in decoding three discrete emotional states (happiness, disgust and sadness) in an extended group of participants. Subjective reports ascertained that participants performed emotion imagery and that the online classifier decoded emotions and not arbitrary states of the brain. Offline whole brain classification as well as region-of-interest classification in 24 brain areas previously implicated in emotion processing revealed that the frontal cortex was critically involved in emotion induction by imagery. We also demonstrate an fMRI-BCI based on real-time classification of BOLD signals from multiple brain regions, for each repetition time (TR) of scanning, providing visual feedback of emotional states to the participant for potential applications in the clinical treatment of dysfunctional affect.

AB - An important question that confronts current research in affective neuroscience as well as in the treatment of emotional disorders is whether it is possible to determine the emotional state of a person based on the measurement of brain activity alone. Here, we first show that an online support vector machine (SVM) can be built to recognize two discrete emotional states, such as happiness and disgust from fMRI signals, in healthy individuals instructed to recall emotionally salient episodes from their lives. We report the first application of real-time head motion correction, spatial smoothing and feature selection based on a new method called Effect mapping. The classifier also showed robust prediction rates in decoding three discrete emotional states (happiness, disgust and sadness) in an extended group of participants. Subjective reports ascertained that participants performed emotion imagery and that the online classifier decoded emotions and not arbitrary states of the brain. Offline whole brain classification as well as region-of-interest classification in 24 brain areas previously implicated in emotion processing revealed that the frontal cortex was critically involved in emotion induction by imagery. We also demonstrate an fMRI-BCI based on real-time classification of BOLD signals from multiple brain regions, for each repetition time (TR) of scanning, providing visual feedback of emotional states to the participant for potential applications in the clinical treatment of dysfunctional affect.

UR - http://www.scopus.com/inward/record.url?scp=79955011391&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955011391&partnerID=8YFLogxK

U2 - 10.1016/j.neuroimage.2010.08.007

DO - 10.1016/j.neuroimage.2010.08.007

M3 - Article

VL - 56

SP - 753

EP - 765

JO - NeuroImage

JF - NeuroImage

SN - 1053-8119

IS - 2

ER -