Emotion recognition system using short-term monitoring of physiological signals

Kyunghwan Kim, S. W. Bang, S. R. Kim

Research output: Contribution to journalArticle

497 Citations (Scopus)

Abstract

A physiological signal-based emotion recognition system is reported. The system was developed to operate as a user-independent system, based on physiological signal databases obtained from multiple subjects. The input signals were electrocardiogram, skin temperature variation and electrodermal activity, all of which were acquired without much discomfort from the body surface, and can reflect the influence of emotion on the autonomic nervous system. The system consisted of preprocessing, feature extraction and pattern classification stages. Preprocessing and feature extraction methods were devised so that emotion-specific characteristics could be extracted from short-segment signals. Although the features were carefully extracted, their distribution formed a classification problem, with large overlap among clusters and large variance within clusters. A support vector machine was adopted as a pattern classifier to resolve this difficulty. Correct-classification ratios for 50 subjects were 78.4% and 61.8%, for the recognition of three and four categories, respectively.

Original languageEnglish
Pages (from-to)419-427
Number of pages9
JournalMedical and Biological Engineering and Computing
Volume42
Issue number3
DOIs
Publication statusPublished - 2004 May 1

Fingerprint

Feature extraction
Monitoring
Neurology
Electrocardiography
Pattern recognition
Support vector machines
Skin
Classifiers
Temperature

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Computer Science Applications

Cite this

@article{92c1f555b945453ba018edb2d011a002,
title = "Emotion recognition system using short-term monitoring of physiological signals",
abstract = "A physiological signal-based emotion recognition system is reported. The system was developed to operate as a user-independent system, based on physiological signal databases obtained from multiple subjects. The input signals were electrocardiogram, skin temperature variation and electrodermal activity, all of which were acquired without much discomfort from the body surface, and can reflect the influence of emotion on the autonomic nervous system. The system consisted of preprocessing, feature extraction and pattern classification stages. Preprocessing and feature extraction methods were devised so that emotion-specific characteristics could be extracted from short-segment signals. Although the features were carefully extracted, their distribution formed a classification problem, with large overlap among clusters and large variance within clusters. A support vector machine was adopted as a pattern classifier to resolve this difficulty. Correct-classification ratios for 50 subjects were 78.4{\%} and 61.8{\%}, for the recognition of three and four categories, respectively.",
author = "Kyunghwan Kim and Bang, {S. W.} and Kim, {S. R.}",
year = "2004",
month = "5",
day = "1",
doi = "10.1007/BF02344719",
language = "English",
volume = "42",
pages = "419--427",
journal = "Medical and Biological Engineering and Computing",
issn = "0140-0118",
publisher = "Springer Verlag",
number = "3",

}

Emotion recognition system using short-term monitoring of physiological signals. / Kim, Kyunghwan; Bang, S. W.; Kim, S. R.

In: Medical and Biological Engineering and Computing, Vol. 42, No. 3, 01.05.2004, p. 419-427.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Emotion recognition system using short-term monitoring of physiological signals

AU - Kim, Kyunghwan

AU - Bang, S. W.

AU - Kim, S. R.

PY - 2004/5/1

Y1 - 2004/5/1

N2 - A physiological signal-based emotion recognition system is reported. The system was developed to operate as a user-independent system, based on physiological signal databases obtained from multiple subjects. The input signals were electrocardiogram, skin temperature variation and electrodermal activity, all of which were acquired without much discomfort from the body surface, and can reflect the influence of emotion on the autonomic nervous system. The system consisted of preprocessing, feature extraction and pattern classification stages. Preprocessing and feature extraction methods were devised so that emotion-specific characteristics could be extracted from short-segment signals. Although the features were carefully extracted, their distribution formed a classification problem, with large overlap among clusters and large variance within clusters. A support vector machine was adopted as a pattern classifier to resolve this difficulty. Correct-classification ratios for 50 subjects were 78.4% and 61.8%, for the recognition of three and four categories, respectively.

AB - A physiological signal-based emotion recognition system is reported. The system was developed to operate as a user-independent system, based on physiological signal databases obtained from multiple subjects. The input signals were electrocardiogram, skin temperature variation and electrodermal activity, all of which were acquired without much discomfort from the body surface, and can reflect the influence of emotion on the autonomic nervous system. The system consisted of preprocessing, feature extraction and pattern classification stages. Preprocessing and feature extraction methods were devised so that emotion-specific characteristics could be extracted from short-segment signals. Although the features were carefully extracted, their distribution formed a classification problem, with large overlap among clusters and large variance within clusters. A support vector machine was adopted as a pattern classifier to resolve this difficulty. Correct-classification ratios for 50 subjects were 78.4% and 61.8%, for the recognition of three and four categories, respectively.

UR - http://www.scopus.com/inward/record.url?scp=2942731250&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942731250&partnerID=8YFLogxK

U2 - 10.1007/BF02344719

DO - 10.1007/BF02344719

M3 - Article

VL - 42

SP - 419

EP - 427

JO - Medical and Biological Engineering and Computing

JF - Medical and Biological Engineering and Computing

SN - 0140-0118

IS - 3

ER -