Display options
Share it on

Front Neurosci. 2016 Jun 10;10:244. doi: 10.3389/fnins.2016.00244. eCollection 2016.

EEG Responses to Auditory Stimuli for Automatic Affect Recognition.

Frontiers in neuroscience

Dirk T Hettich, Elaina Bolinger, Tamara Matuz, Niels Birbaumer, Wolfgang Rosenstiel, Martin Spüler

Affiliations

  1. Developmental Aspects of Sleep, Memory, and Emotion, Institute of Medical Psychology and Behavioural Neurobiology, University of TübingenTübingen, Germany; Neural Interfaces and Brain Signal Decoding, Wilhelm-Schickard-Institute for Computer Science, University of TübingenTübingen, Germany.
  2. Developmental Aspects of Sleep, Memory, and Emotion, Institute of Medical Psychology and Behavioural Neurobiology, University of Tübingen Tübingen, Germany.
  3. Developmental Aspects of Sleep, Memory, and Emotion, Institute of Medical Psychology and Behavioural Neurobiology, University of TübingenTübingen, Germany; Ospedale San Camillo, IRCCSVenezia, Italy.
  4. Neural Interfaces and Brain Signal Decoding, Wilhelm-Schickard-Institute for Computer Science, University of Tübingen Tübingen, Germany.

PMID: 27375410 PMCID: PMC4901068 DOI: 10.3389/fnins.2016.00244

Abstract

Brain state classification for communication and control has been well established in the area of brain-computer interfaces over the last decades. Recently, the passive and automatic extraction of additional information regarding the psychological state of users from neurophysiological signals has gained increased attention in the interdisciplinary field of affective computing. We investigated how well specific emotional reactions, induced by auditory stimuli, can be detected in EEG recordings. We introduce an auditory emotion induction paradigm based on the International Affective Digitized Sounds 2nd Edition (IADS-2) database also suitable for disabled individuals. Stimuli are grouped in three valence categories: unpleasant, neutral, and pleasant. Significant differences in time domain domain event-related potentials are found in the electroencephalogram (EEG) between unpleasant and neutral, as well as pleasant and neutral conditions over midline electrodes. Time domain data were classified in three binary classification problems using a linear support vector machine (SVM) classifier. We discuss three classification performance measures in the context of affective computing and outline some strategies for conducting and reporting affect classification studies.

Keywords: affective computing; brain-computer interface; classification; event-related potential; late positive potential; machine learning; support vector machine

References

  1. Clin Neurophysiol. 1999 Nov;110(11):1842-57 - PubMed
  2. J Neurosci Methods. 2015 Jul 30;250:126-36 - PubMed
  3. J Pers Soc Psychol. 1990 Feb;58(2):330-41 - PubMed
  4. Biol Psychol. 2010 Jul;84(3):451-62 - PubMed
  5. Comput Intell Neurosci. 2011;2011:156869 - PubMed
  6. J Cogn Neurosci. 2010 Sep;22(9):1970-9 - PubMed
  7. Trends Cogn Sci. 2012 Sep;16(9):458-66 - PubMed
  8. Clin Neurophysiol. 2002 Jun;113(6):767-91 - PubMed
  9. Biol Psychol. 2008 Mar;77(3):247-65 - PubMed
  10. Front Neurosci. 2015 Apr 30;9:136 - PubMed
  11. J Behav Ther Exp Psychiatry. 1994 Mar;25(1):49-59 - PubMed
  12. Clin Neurophysiol. 2007 Jan;118(1):98-104 - PubMed
  13. Neuropsychologia. 2016 Feb;82:110-22 - PubMed
  14. Biol Psychol. 2004 Oct;67(1-2):7-49 - PubMed
  15. Annu Rev Psychol. 1983;34:33-61 - PubMed
  16. J Neural Eng. 2011 Apr;8(2):025005 - PubMed
  17. Biol Psychol. 2000 Mar;52(2):95-111 - PubMed
  18. J Neural Eng. 2007 Jun;4(2):R1-R13 - PubMed
  19. PLoS One. 2016 Feb 05;11(2):e0148037 - PubMed
  20. J Pers Soc Psychol. 1999 May;76(5):805-19 - PubMed
  21. Science. 1982 Dec 17;218(4578):1235-7 - PubMed
  22. Science. 1983 Sep 16;221(4616):1208-10 - PubMed
  23. Nature. 1999 Mar 25;398(6725):297-8 - PubMed
  24. Hum Brain Mapp. 2004 Aug;22(4):290-9 - PubMed
  25. Arch Gen Psychiatry. 1999 Jan;56(1):78-84 - PubMed
  26. J Pers Soc Psychol. 1988 Jun;54(6):1063-70 - PubMed

Publication Types