Implicit emotion communication: EEG classification and haptic feedback

Rodrigo Ceballos, Beatrice Ionascu, Wanjoo Park, Mohamad Eid

Research output: Contribution to journalArticle

Abstract

Today, ubiquitous digital communication systems do not have an intuitive, natural way of communicating emotion, which, in turn, affects the degree to which humans can emotionally connect and interact with one another. To address this problem, a more natural, intuitive, and implicit emotion communication system was designed and created that employs asymmetry-based EEG emotion classification for detecting the emotional state of the sender and haptic feedback (in the form of tactile gestures) for displaying emotions for a receiver. Emotions are modeled in terms of valence (positive/negative emotions) and arousal (intensity of the emotion). Performance analysis shows that the proposed EEG subject-dependent emotion classification model with Free Asymmetry features allows for more flexible feature-generation schemes than other existing algorithms and attains an average accuracy of 92.5% for valence and 96.5% for arousal, outperforming previous-generation schemes in high feature space. As for the haptic feedback, a tactile gesture authoring tool and a haptic jacket were developed to design tactile gestures that can intensify emotional reactions in terms of valence and arousal. Experimental study demonstrated that subject-independent emotion transmission through tactile gestures is effective for the arousal dimension of an emotion but is less effective for valence. Consistency in subject-dependent responses for both valence and arousal suggests that personalized tactile gestures would be more effective.

Original languageEnglish (US)
Article number3
JournalACM Transactions on Multimedia Computing, Communications and Applications
Volume14
Issue number1
DOIs
StatePublished - Dec 1 2017

Fingerprint

Electroencephalography
Feedback
Digital communication systems
Communication
Communication systems

Keywords

  • Affective computing
  • Affective haptics
  • Multimodal interaction
  • Tactile gestures

ASJC Scopus subject areas

  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Implicit emotion communication : EEG classification and haptic feedback. / Ceballos, Rodrigo; Ionascu, Beatrice; Park, Wanjoo; Eid, Mohamad.

In: ACM Transactions on Multimedia Computing, Communications and Applications, Vol. 14, No. 1, 3, 01.12.2017.

Research output: Contribution to journalArticle

@article{0f4ad8571b9a4f92bc649b420e047df6,
title = "Implicit emotion communication: EEG classification and haptic feedback",
abstract = "Today, ubiquitous digital communication systems do not have an intuitive, natural way of communicating emotion, which, in turn, affects the degree to which humans can emotionally connect and interact with one another. To address this problem, a more natural, intuitive, and implicit emotion communication system was designed and created that employs asymmetry-based EEG emotion classification for detecting the emotional state of the sender and haptic feedback (in the form of tactile gestures) for displaying emotions for a receiver. Emotions are modeled in terms of valence (positive/negative emotions) and arousal (intensity of the emotion). Performance analysis shows that the proposed EEG subject-dependent emotion classification model with Free Asymmetry features allows for more flexible feature-generation schemes than other existing algorithms and attains an average accuracy of 92.5{\%} for valence and 96.5{\%} for arousal, outperforming previous-generation schemes in high feature space. As for the haptic feedback, a tactile gesture authoring tool and a haptic jacket were developed to design tactile gestures that can intensify emotional reactions in terms of valence and arousal. Experimental study demonstrated that subject-independent emotion transmission through tactile gestures is effective for the arousal dimension of an emotion but is less effective for valence. Consistency in subject-dependent responses for both valence and arousal suggests that personalized tactile gestures would be more effective.",
keywords = "Affective computing, Affective haptics, Multimodal interaction, Tactile gestures",
author = "Rodrigo Ceballos and Beatrice Ionascu and Wanjoo Park and Mohamad Eid",
year = "2017",
month = "12",
day = "1",
doi = "10.1145/3152128",
language = "English (US)",
volume = "14",
journal = "ACM Transactions on Multimedia Computing, Communications and Applications",
issn = "1551-6857",
publisher = "Association for Computing Machinery (ACM)",
number = "1",

}

TY - JOUR

T1 - Implicit emotion communication

T2 - EEG classification and haptic feedback

AU - Ceballos, Rodrigo

AU - Ionascu, Beatrice

AU - Park, Wanjoo

AU - Eid, Mohamad

PY - 2017/12/1

Y1 - 2017/12/1

N2 - Today, ubiquitous digital communication systems do not have an intuitive, natural way of communicating emotion, which, in turn, affects the degree to which humans can emotionally connect and interact with one another. To address this problem, a more natural, intuitive, and implicit emotion communication system was designed and created that employs asymmetry-based EEG emotion classification for detecting the emotional state of the sender and haptic feedback (in the form of tactile gestures) for displaying emotions for a receiver. Emotions are modeled in terms of valence (positive/negative emotions) and arousal (intensity of the emotion). Performance analysis shows that the proposed EEG subject-dependent emotion classification model with Free Asymmetry features allows for more flexible feature-generation schemes than other existing algorithms and attains an average accuracy of 92.5% for valence and 96.5% for arousal, outperforming previous-generation schemes in high feature space. As for the haptic feedback, a tactile gesture authoring tool and a haptic jacket were developed to design tactile gestures that can intensify emotional reactions in terms of valence and arousal. Experimental study demonstrated that subject-independent emotion transmission through tactile gestures is effective for the arousal dimension of an emotion but is less effective for valence. Consistency in subject-dependent responses for both valence and arousal suggests that personalized tactile gestures would be more effective.

AB - Today, ubiquitous digital communication systems do not have an intuitive, natural way of communicating emotion, which, in turn, affects the degree to which humans can emotionally connect and interact with one another. To address this problem, a more natural, intuitive, and implicit emotion communication system was designed and created that employs asymmetry-based EEG emotion classification for detecting the emotional state of the sender and haptic feedback (in the form of tactile gestures) for displaying emotions for a receiver. Emotions are modeled in terms of valence (positive/negative emotions) and arousal (intensity of the emotion). Performance analysis shows that the proposed EEG subject-dependent emotion classification model with Free Asymmetry features allows for more flexible feature-generation schemes than other existing algorithms and attains an average accuracy of 92.5% for valence and 96.5% for arousal, outperforming previous-generation schemes in high feature space. As for the haptic feedback, a tactile gesture authoring tool and a haptic jacket were developed to design tactile gestures that can intensify emotional reactions in terms of valence and arousal. Experimental study demonstrated that subject-independent emotion transmission through tactile gestures is effective for the arousal dimension of an emotion but is less effective for valence. Consistency in subject-dependent responses for both valence and arousal suggests that personalized tactile gestures would be more effective.

KW - Affective computing

KW - Affective haptics

KW - Multimodal interaction

KW - Tactile gestures

UR - http://www.scopus.com/inward/record.url?scp=85040311565&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040311565&partnerID=8YFLogxK

U2 - 10.1145/3152128

DO - 10.1145/3152128

M3 - Article

AN - SCOPUS:85040311565

VL - 14

JO - ACM Transactions on Multimedia Computing, Communications and Applications

JF - ACM Transactions on Multimedia Computing, Communications and Applications

SN - 1551-6857

IS - 1

M1 - 3

ER -