Advertisement

Evaluation of Cepstral Coefficients as Features in EEG-Based Recognition of Emotional States

  • Firgan Feradov
  • Iosif Mporas
  • Todor Ganchev
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 679)

Abstract

The study of physiological signals and the evaluation of their features are of great importance for the automated emotion detection, as these are directly connected with the successful modelling and classification of the states of interest. In the presented work, we present an evaluation of the appropriateness of LFCC and the logarithmic energy of signals as features for automated recognition of negative emotional states in terms of recognition accuracy. In particular, three sets of features are compared – features computed after frame-level segmentation of the signal; features computed after averaging of frame level descriptors; and features extracted from an entire EEG recording. The performance of the extracted features is evaluated using C4.5 classifier for 10, 15, 20, 30, 45, and 60 filters.

Keywords

LFCC features Cepstral coefficients Emotion recognition EEG 

References

  1. 1.
    Ahern, G.L., Schwartz, G.E.: Differential lateralization for positive and negative emotion in the human brain: EEG spectral analysis. Neuropsychologia 23(6), 745–755 (1985). doi: 10.1016/0028-3932(85)90081-8 CrossRefGoogle Scholar
  2. 2.
    Rowland, N., Meile, M.J., Nicolaidis, S.: EEG alpha activity reflects attentional demands, and beta activity reflects emotional and cognitive processes. Science 228(4700), 750–752 (1985)CrossRefGoogle Scholar
  3. 3.
    Othman, M., Wahab, A., Khosrowabadi, R.: MFCC for robust emotion detection using EEG. In: 2009 IEEE 9th Malaysia International Conference on Communications (MICC), Kuala Lumpur, pp. 98–101 (2009). doi: 10.1109/MICC.2009.5431473
  4. 4.
    Wahab, A., Kamaruddin, N., Palaniappan, L.K., Li, M., Khosrowabadi, R.: EEG signals for emotion recognition. J. Comput. Methods Sci. Eng. 10(s1), 1–11 (2010). doi: 10.3233/JCM-2010-0263 zbMATHGoogle Scholar
  5. 5.
    Handayani, D., Yaacob, H., Wahab, A., Alshaikli, I.F.T.: Statistical approach for a complex emotion recognition based on EEG features. In: 2015 4th International Conference on Advanced Computer Science Applications and Technologies (ACSAT), Kuala Lumpur, pp. 202–207 (2015). doi: 10.1109/ACSAT.2015.54
  6. 6.
    Pazhanirajan, S., Dhanalakshmi, P.: EEG signal classification using linear predictive cepstral coefficient features. Int. J. Comput. Appl. 73(1), 28–31 (2013)Google Scholar
  7. 7.
    Feradov, F.: Study of the quality of Linear Frequency Cepstral Coefficients for automated recognition of negative emotional states from EEG signals, Scientific works of the Union of Scientist in Bulgaria – Plovdiv, Series G. Med. Pharm. Dent. Med. XIX, 106–109 (2016). ISSN 1311-9427Google Scholar
  8. 8.
    Koelstra, S., et al.: DEAP: a database for emotion analysis; using physiological signals. IEEE Trans. Affect. Comput. 3(1), 18–31 (2012). doi: 10.1109/T-AFFC.2011.15 CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Technical University of VarnaVarnaBulgaria
  2. 2.University of HertfordshireHatfieldUK

Personalised recommendations