On modelling user's eeg response during a human-computer interaction: A mirror neuron system-based approach

P. C. Petrantonakis, L. J. Hadjileontiadis

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

One of the most challenging issues in Human-Computer Interaction (HCI) is to imbue computers with the ability to identify emotions and taking them into account during the interaction process. Towards that, we have created a user interface in order to elicit effective states through an imitation procedure. Recent brain imaging experiments have shown that two regions of the brain (inferior frontal cortex and superior parietal lobe) are active even when a person performs an action or s/he observes the same action be done by another individual. In accordance with those findings, we try to trigger the Mirror Neuron System, which is responsible for this behavior, by showing pictures with faces expressing different emotions. The user's response is reflected in the acquired electroencephalograms (EEGs), which, after processing with higher-order crossings, are used for classification and identification of any emotional state. Experimental results of the analysis of EEGs from two users when looking at 60 reference-images with six main emotions, i.e., happiness, surprise, anger, disgust, sadness and fear, justify the potential of the proposed approach to successfully detect the emotions using only one EEG channel. These preliminary results pave the way for extended EEG-based emotion recognition.

Original languageBritish English
Title of host publication4th European Conference of the International Federation for Medical and Biological Engineering - ECIFMBE 2008
Pages1241-1245
Number of pages5
DOIs
StatePublished - 2008
Event4th European Conference of the International Federation for Medical and Biological Engineering, ECIFMBE 2008 - Antwerp, Belgium
Duration: 23 Nov 200827 Nov 2008

Publication series

NameIFMBE Proceedings
Volume22
ISSN (Print)1680-0737

Conference

Conference4th European Conference of the International Federation for Medical and Biological Engineering, ECIFMBE 2008
Country/TerritoryBelgium
CityAntwerp
Period23/11/0827/11/08

Keywords

  • Affective computing
  • EEG
  • Higher order crossings analysis
  • Mirror neuron system

Fingerprint

Dive into the research topics of 'On modelling user's eeg response during a human-computer interaction: A mirror neuron system-based approach'. Together they form a unique fingerprint.

Cite this