Emotional Valence Detection based on a Novel Wavelet Feature Extraction Strategy using EEG Signals

Hao Zhang, Shin'ichi Warisawa, Ichiro Yamada

2014

Abstract

This paper presents a novel feature extraction strategy in the time-frequency domain using discrete wavelet transform (DWT) for valence level detection using electroencephalography (EEG) signals. Signals from different EEG electrodes are considered independently for the first time in order to find an optimum combination through different levels of wavelet coefficients based on the genetic algorithm (GA). Thus, we take into consideration useful information obtained from different frequency bands of brain activity along the scalp in valence level detection, and we introduce a new set of features named the cross-level wavelet feature group (CLWF). The effectiveness of this approach is strongly supported by the analytical results of experiments in which EEG signals with valence level labels were collected from 50 healthy subjects. High accuracy was achieved for both 2-level (98%) and 3-level valence detection (90%) by applying leave-one-out cross validation using a probabilistic neural network (PNN). In addition, light-weighted sets with less than half EEG recording electrodes are proposed, which can achieve a high accuracy (86% for 3-level valence detection) with offering convenience of users and reducing computational complexity.

References

  1. Adolphs, R., Tranel, D., and Damasio, A. R. (2003). Dissociable neural systems for recognizing emotions. Brain and Cognition, 52(1):61-69.
  2. Alves, N. T., Fukusima, S. S., and Aznar-Casanova, J. A. (2008). Models of brain asymmetry in emotional processing. Psychology & Neuroscience, 1(1):63-66.
  3. Arnold, M. (1950). An Excitatory Theory of Emotion. McGraw-Hill, New York, xxiii edition.
  4. Arvaneh, M., Guan, C., Ang, K. K., and Quek, C. (2011). Optimizing the channel selection and classification accuracy in eeg-based bci. IEEE Transactions on Biomedical Engineering, 58(6):1865-1873.
  5. Borod, J. C. (1992). Interhemispheric and intrahemispheric control of emotion: a focus on unilateral brain damage. J Consult Clin Psychol, 60(3):339-348.
  6. Chu, C., Hsu, A.-l., Chou, K.-h., Bandettini, P., and Lin, C. (2012). NeuroImage Does feature selection improve classification accuracy? Impact of sample size and feature selection on classification using anatomical magnetic resonance images. NeuroImage, 60(1):59- 70.
  7. Constantinou, E., Bogaerts, K., Diest, L. V., and den Bergh, O. V. (2013). Inducing symptoms in high symptom reporters via emotional pictures: The interactive effects of valence and arousal. Journal of Psychosomatic Research, 74(3):191-196.
  8. Darwin, C. (1872). The Expression of the Emotions in Man and Animals, with an Introduction, Afterword, and Commentaries by Paul Ekman. Oxford Univ Press, Oxford, 3rd edition.
  9. Heller, W. (1993). Neuropsychological mechanisms of individual differences in emotion, personality, and arousal. Neuropsychology, 7,:476-489.
  10. Holland, J. H. (1975). Adaptation in Neural and Artificial Systems. University of Michigan Press, Ann Arbor, Michigan, 1st edition.
  11. Hosseini, S. A. (2011). Emotion recognition method using entropy analysis of eeg signals. International Journal of Images, Graphics, and Signal Processing, 3(5):30- 36.
  12. Jolliffe, I. T. (2002). Principal Component Analysis. Springer,, 2nd edition.
  13. Katsis, C., Katertsidis, N., and Fotiadis, D. (2011). An integrated system based on physiological signals for the assessment of affective states in patients with anxiety disorders. Biomedical Signal Processing and Control, 6:261-268.
  14. Lang, P. J., Bradley, M. M., and Cuthbert, B. N. (2008). International affective picture system (iaps): Technical manual and affective ratings. Technical Report A-8.
  15. Liu, J. and Xu, J. (2010). Compared study of the analyzing methods for eeg data. In Proc. of 3rd IEEE International Conference on Computer Science and Information Technology, volume 9, pages 445-448.
  16. Morlet, J. (1984). Decomposition of hardy functions into square integrable wavelets of constant shape. SIAM. Math. Anal, 15(4):723-736.
  17. Murugappan, M., Ramachandran, N., and Sazali, Y. (2010). Classification of human emotion from eeg using discrete wavelet transform. Journal of Biomedical Science and Engineering, 3:390-396.
  18. Murugappan, M., Rizon, M., Nagarajan, R., Yaacob, S., Zunaidi, I., and Hazry, D. (2007). Eeg feature extraction for classifying emotions using fcm and fkm. International Journal of Computers and Communications, 1(2):299-304.
  19. Nardi, D. (2011). Neuroscience of Personality: Brain Savvy Insights for All Types of People. Radiance House, 1.0 edition.
  20. Picard, R. W., Vyzas, E., and Healey, J. (2001). Toward machine emotional intelligence: analysis of affective physiological state. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(1):1175-1191.
  21. Russell, J. (1980). A circumplex model of affect. Journal of Personality and Social Psychology, 39(6):1161-1178.
  22. Salovey, P. and Rothman, A. J. (2000). Emotional states and physical health. The American psychologist, 55(1):110-121.
  23. Schaaff, K. and Schultz, T. (2009). Towards emotion recognition from electroencephalography signals. In 3rd International Conference on Affective Computing and Intelligent Interaction. Institute of Electrical and Electronics Engineers.
  24. Sherwood, J. (2009). On classifiability of wavelet features for eeg-based brain-computer interfaces. In Proceedings of International Joint Conference on Neural Networks. Institute of Electrical and Electronics Engineers.
  25. Sirois, B. C. (2003.). Negative emotion and coronary heart disease. Behavior Modification, 27(1):83-102.
  26. Sivakumar, A. and .Kannan, K. (2009). A novel feature selection technique for number classification problem using pnn - a plausible scheme for boiler flue gas analysis. Sensors and Actuators B: Chemical, 139:280- 286.
  27. Specht, D. F. (1990). Probabilistic neural networks. Neural Networks, 3:110-118.
  28. Tahon, M., Degottex, G., and Devillers, L. (2012). Usual voice quality features and glottal features for emotional valence detection. In the 6th International Conference of Speech Prosody. Tongji University Press.
  29. Takahashi, K. and Tsukaguchi, A. (2003). Remarks on emotion recognition from multi-modal bio-potential signals. In Proc. of IEEE International Conference on Systems, Man, and Cybernetics. Institute of Electrical and Electronics Engineers.
  30. Van den Broek, E. L. and Westerink, J. H. D. M. (2009). Considerations for emotion-aware consumer products. Applied ergonomics, 40(6):1055-64.
  31. Wundt, W. (1905). Grundriss der Psychologie [Fundamentals of Psychology]. Engelman, Leipzig, 7th edition.
Download


Paper Citation


in Harvard Style

Zhang H., Warisawa S. and Yamada I. (2014). Emotional Valence Detection based on a Novel Wavelet Feature Extraction Strategy using EEG Signals . In Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2014) ISBN 978-989-758-010-9, pages 52-59. DOI: 10.5220/0004764600520059


in Bibtex Style

@conference{healthinf14,
author={Hao Zhang and Shin'ichi Warisawa and Ichiro Yamada},
title={Emotional Valence Detection based on a Novel Wavelet Feature Extraction Strategy using EEG Signals},
booktitle={Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2014)},
year={2014},
pages={52-59},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004764600520059},
isbn={978-989-758-010-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2014)
TI - Emotional Valence Detection based on a Novel Wavelet Feature Extraction Strategy using EEG Signals
SN - 978-989-758-010-9
AU - Zhang H.
AU - Warisawa S.
AU - Yamada I.
PY - 2014
SP - 52
EP - 59
DO - 10.5220/0004764600520059