Fuzzy model of dominance emotions in affective computing

Kaveh Bakhtiyari, Hafizah Husain

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

To date, most of the human emotion recognition systems are intended to sense the emotions and their dominance individually. This paper discusses a fuzzy model for multilevel affective computing based on the dominance dimensional model of emotions. This model can detect any other possible emotions simultaneously at the time of recognition. One hundred and thirty volunteers from various countries with different cultural backgrounds were selected to record their emotional states. These volunteers have been selected from various races and different geographical locations. Twenty-seven different emotions with their strengths in a scale of 5 were questioned through a survey. Recorded emotions were analyzed with the other possible emotions and their levels of dominance to build the fuzzy model. Then this model was integrated into a fuzzy emotion recognition system using three input devices of mouse, keyboard and the touch screen display. Support vector machine classifier detected the other possible emotions of the users along with the directly sensed emotion. The binary system (non-fuzzy) sensed emotions with an incredible accuracy of 93 %. However, it only could sense limited emotions. By integrating this model, the system was able to detect more possible emotions at a time with slightly lower recognition accuracy of 86 %. The recorded false positive rates of this model for four emotions were measured at 16.7 %. The resulted accuracy and its false positive rate are among the top three accurate human emotion recognition (affective computing) systems.

Original languageEnglish
Pages (from-to)1467-1477
Number of pages11
JournalNeural Computing and Applications
Volume25
Issue number6
DOIs
Publication statusPublished - 14 Oct 2014

Fingerprint

Touch screens
Support vector machines
Classifiers
Display devices

Keywords

  • Affective computing
  • Dominance emotion
  • Fuzzy emotion
  • Human–computer interaction
  • Multilevel emotion

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Fuzzy model of dominance emotions in affective computing. / Bakhtiyari, Kaveh; Husain, Hafizah.

In: Neural Computing and Applications, Vol. 25, No. 6, 14.10.2014, p. 1467-1477.

Research output: Contribution to journalArticle

Bakhtiyari, Kaveh ; Husain, Hafizah. / Fuzzy model of dominance emotions in affective computing. In: Neural Computing and Applications. 2014 ; Vol. 25, No. 6. pp. 1467-1477.
@article{6771be29fd91445ea93c7460dec47294,
title = "Fuzzy model of dominance emotions in affective computing",
abstract = "To date, most of the human emotion recognition systems are intended to sense the emotions and their dominance individually. This paper discusses a fuzzy model for multilevel affective computing based on the dominance dimensional model of emotions. This model can detect any other possible emotions simultaneously at the time of recognition. One hundred and thirty volunteers from various countries with different cultural backgrounds were selected to record their emotional states. These volunteers have been selected from various races and different geographical locations. Twenty-seven different emotions with their strengths in a scale of 5 were questioned through a survey. Recorded emotions were analyzed with the other possible emotions and their levels of dominance to build the fuzzy model. Then this model was integrated into a fuzzy emotion recognition system using three input devices of mouse, keyboard and the touch screen display. Support vector machine classifier detected the other possible emotions of the users along with the directly sensed emotion. The binary system (non-fuzzy) sensed emotions with an incredible accuracy of 93 {\%}. However, it only could sense limited emotions. By integrating this model, the system was able to detect more possible emotions at a time with slightly lower recognition accuracy of 86 {\%}. The recorded false positive rates of this model for four emotions were measured at 16.7 {\%}. The resulted accuracy and its false positive rate are among the top three accurate human emotion recognition (affective computing) systems.",
keywords = "Affective computing, Dominance emotion, Fuzzy emotion, Human–computer interaction, Multilevel emotion",
author = "Kaveh Bakhtiyari and Hafizah Husain",
year = "2014",
month = "10",
day = "14",
doi = "10.1007/s00521-014-1637-6",
language = "English",
volume = "25",
pages = "1467--1477",
journal = "Neural Computing and Applications",
issn = "0941-0643",
publisher = "Springer London",
number = "6",

}

TY - JOUR

T1 - Fuzzy model of dominance emotions in affective computing

AU - Bakhtiyari, Kaveh

AU - Husain, Hafizah

PY - 2014/10/14

Y1 - 2014/10/14

N2 - To date, most of the human emotion recognition systems are intended to sense the emotions and their dominance individually. This paper discusses a fuzzy model for multilevel affective computing based on the dominance dimensional model of emotions. This model can detect any other possible emotions simultaneously at the time of recognition. One hundred and thirty volunteers from various countries with different cultural backgrounds were selected to record their emotional states. These volunteers have been selected from various races and different geographical locations. Twenty-seven different emotions with their strengths in a scale of 5 were questioned through a survey. Recorded emotions were analyzed with the other possible emotions and their levels of dominance to build the fuzzy model. Then this model was integrated into a fuzzy emotion recognition system using three input devices of mouse, keyboard and the touch screen display. Support vector machine classifier detected the other possible emotions of the users along with the directly sensed emotion. The binary system (non-fuzzy) sensed emotions with an incredible accuracy of 93 %. However, it only could sense limited emotions. By integrating this model, the system was able to detect more possible emotions at a time with slightly lower recognition accuracy of 86 %. The recorded false positive rates of this model for four emotions were measured at 16.7 %. The resulted accuracy and its false positive rate are among the top three accurate human emotion recognition (affective computing) systems.

AB - To date, most of the human emotion recognition systems are intended to sense the emotions and their dominance individually. This paper discusses a fuzzy model for multilevel affective computing based on the dominance dimensional model of emotions. This model can detect any other possible emotions simultaneously at the time of recognition. One hundred and thirty volunteers from various countries with different cultural backgrounds were selected to record their emotional states. These volunteers have been selected from various races and different geographical locations. Twenty-seven different emotions with their strengths in a scale of 5 were questioned through a survey. Recorded emotions were analyzed with the other possible emotions and their levels of dominance to build the fuzzy model. Then this model was integrated into a fuzzy emotion recognition system using three input devices of mouse, keyboard and the touch screen display. Support vector machine classifier detected the other possible emotions of the users along with the directly sensed emotion. The binary system (non-fuzzy) sensed emotions with an incredible accuracy of 93 %. However, it only could sense limited emotions. By integrating this model, the system was able to detect more possible emotions at a time with slightly lower recognition accuracy of 86 %. The recorded false positive rates of this model for four emotions were measured at 16.7 %. The resulted accuracy and its false positive rate are among the top three accurate human emotion recognition (affective computing) systems.

KW - Affective computing

KW - Dominance emotion

KW - Fuzzy emotion

KW - Human–computer interaction

KW - Multilevel emotion

UR - http://www.scopus.com/inward/record.url?scp=84918785570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84918785570&partnerID=8YFLogxK

U2 - 10.1007/s00521-014-1637-6

DO - 10.1007/s00521-014-1637-6

M3 - Article

AN - SCOPUS:84918785570

VL - 25

SP - 1467

EP - 1477

JO - Neural Computing and Applications

JF - Neural Computing and Applications

SN - 0941-0643

IS - 6

ER -