• Skip to main content
  • Skip to header right navigation
  • Skip to site footer
HCI Games Group

HCI Games Group

Researching Affective Systems and Engaging Interactions

  • Home
  • Blog
  • People
  • Opportunities
  • Projects
  • Publications
  • Teaching
  • Contact
  • CLICK ME!!!

Download

You are here: Home / Download

Proceedings

A Hybrid Approach at Emotional State Detection: Merging Theoretical Models of Emotion with Data-Driven Statistical Classifiers

Pedro Nogueira, Rui Rodrigues, Eugénio Oliveira, and Lennart Nacke. 2013. A Hybrid Approach at Emotional State Detection: Merging Theoretical Models of Emotion with Data-Driven Statistical Classifiers. In Proceedings of WI-IAT 2013. Atlanta, GA, United States. IEEE, 253-260. doi:10.1109/WI-IAT.2013.117
PDFDOIBibTeX
@inproceedings{nogueira2013hybrid,
Abstract = {With the rising popularity of affective computing techniques, there have been several advances in the field of emotion recognition systems. However, despite the several advances in the field, these systems still face scenario adaptability and practical implementation issues. In light of these issues, we developed a nonspecific method for emotional state classification in interactive environments. The proposed method employs a two-layer classification process to detect Arousal and Valence (the emotion's hedonic component), based on four psychophysiological metrics: Skin Conductance, Heart Rate and Electromyography measured at the corrugator supercilii and zygomaticus major muscles. The first classification layer applies multiple regression models to correctly scale the aforementioned metrics across participants and experimental conditions, while also correlating them to the Arousal or Valence dimensions. The second layer then explores several machine learning techniques to merge the regression outputs into one final rating. The obtained results indicate we are able to classify Arousal and Valence independently from participant and experimental conditions with satisfactory accuracy (97\% for Arousal and 91\% for Valence).},
Address = {Atlanta, GA, United States},
Author = {P. A. Nogueira, R. A. Rodrigues, E. Oliveira, and L. E. Nacke},
Booktitle = {Proceedings of WI-IAT 2013},
Doi = {10.1109/WI-IAT.2013.117},
Img = {http://hcigames.com/wp-content/uploads/2015/02/A-Hybrid-Approach-at-Emotional-State-Detection-Merging-Theoretical-Models-of-Emotion-with-Data-Driven-Statistical-Classifiers.png},
Organization = {IEEE},
Pages = {253-260},
Publisher = {IEEE},
Title = {A Hybrid Approach at Emotional State Detection: Merging Theoretical Models of Emotion with Data-Driven Statistical Classifiers},
Url = {https://hcigames.com/download/a-hybrid-approach-at-emotional-state-detection-merging-theoretical-models-of-emotion-with-data-driven-statistical-classifiers},
Volume = {2},
Year = {2013},

Abstract

With the rising popularity of affective computing techniques, there have been several advances in the field of emotion recognition systems. However, despite the several advances in the field, these systems still face scenario adaptability and practical implementation issues. In light of these issues, we developed a nonspecific method for emotional state classification in interactive environments. The proposed method employs a two-layer classification process to detect Arousal and Valence (the emotion's hedonic component), based on four psychophysiological metrics: Skin Conductance, Heart Rate and Electromyography measured at the corrugator supercilii and zygomaticus major muscles. The first classification layer applies multiple regression models to correctly scale the aforementioned metrics across participants and experimental conditions, while also correlating them to the Arousal or Valence dimensions. The second layer then explores several machine learning techniques to merge the regression outputs into one final rating. The obtained results indicate we are able to classify Arousal and Valence independently from participant and experimental conditions with satisfactory accuracy (97\% for Arousal and 91\% for Valence).
  • Facebook
  • Twitter
  • LinkedIn
  • Instagram
  • YouTube

Copyright © 2023 · HCI Games Group · All Rights Reserved. We acknowledge that we live and work on the traditional territory of the Neutral, Anishinaabeg, and Haudenosaunee peoples. The University of Waterloo is situated on the Haldimand Tract, the land promised to the Six Nations that includes six miles on each side of the Grand River. We wish to honour the ancestral guardians of this land and its waterways: the Anishinaabe, the Haudenosaunee Confederacy, the Wendat, and the Neutrals. Many Indigenous peoples continue to call this land home and act as its stewards, and this responsibility extends to all peoples, to share and care for this land for generations to come.