Document Type : Full Research Paper


1 Phd Student, Faculty of biomedical Engineering, Islamic Azad University, science and Research Branch

2 Associate Professor, Biomedical Engineering Group, Shahed University

3 Biomedical Engineering Group, Tarbiat Modarres University



In this study, electroencephalogram (EEG) signals have been analyzed in positive, negative and neutral emotions. Here it is supposed that the brain has different independent sources during an emotional activity which will be extractable by Independent Component Analysis (ICA) algorithm. For resolving the illposeness problem of extracted components by ICA algorithm, first these sources were sorted by Shannon entropy and then the features of Katz fractal dimension and the first local minimum of the mutual information based on the time delay (tau) have been extracted for representing determinism. The results show that the determinism ratio of the sorted sources has significant difference during the time in three emotional states: positive, negative and neutral. The determinism ratio increases in neutral, negative and positive emotional states, respectively.


Main Subjects

[1]     Kim, M & et al. (2013). A Review on the Computational Methods for Emotional State Estimation from the Human EEG, Computational and Mathematical Methods in Medicine
[2]     Adolphs, R. (2009). The social brain: neural basis of social knowledge. Annu Rev Psychol, vol. 60, pp. 693–716.
[3]     Agrawal, D & et al. (2013). Electrophysiological responses to emotional prosody perception in cochlear implant users, NeuroImage: Clinical , pp.229–238
[4]     Zhang, Q & et al. (2010). A hierarchical positive and negative emotion understanding system based on integrated analysis of visual and brain signals, Neurocomputing, vol. 73, pp. 3264–3272
[5]     Chanel, Emotion assessment for affective computing based on brain and peripheral signals, PhD thesis, UNIVERSITE DE GENEVE, (2009)
[6]     Colombo, C & et al. (1999). Semantics in visual information retrieval, IEEE Multimedia, vol. 6(3), pp. 38–53.
[7]     Assfalg, j & et al. (2002), Semantic annotation of sports videos, IEEE Multimedia, vol. 9(2), pp.52–60.
[8]     Yu, C and Xu, L. An emotion-based approach to decision making and self-learning in autonomous robot control, The Fifth World Congress on Intelligent Control and Automation, vol.3, pp. 2386–2390.
[9]     Almedia, L.(2003). MISEP – Linear and Nonlinear ICA Based on Mutual Information, Journal of Machine Learning Research, vol. 4, pp. 1297-1318.
[10]  Hyvärinen, A & Oja, E. (2000). Independent Component Analysis: Algorithms and Applications, Neural Networks, vol. 13(4-5), pp.411-430.
[11]  Knyazev, G & et al. (2012).  Extraversion and fronto-posterior EEG spectral power gradient: An independent component analysis. Biological Psychology, vol. 89, pp. 515– 524
[12]  Jansen B, Brandt M. (1993). Nonlinear dynamical analysis of the EEG, World Scientific
[13]  F. Takens. (1981). Detecting strange attractors in fluid turbulence. In D. Rand and L.-S. Young, editors, Dynamical Systems and Turbulence, pp 366
[14]  R. R. Cornelius, "Theoretical approaches to emotion," Proc. Int. Speech Communication Association (ISCA) Workshop on Speech and Emotion, Belfast, Ireland, 2000.
[15]  Comparison of fractal dimension estimation algorithms for epileptic seizure onset detection, J. Neural Eng. 7 (2010) 046007 (18pp)
[16]  Mandelbrot BB. The fractal geometry of nature. Freeman, New York, 1983
[17]  Recurrence plots for the analysis of complex systems, N. Marwan et al. / Physics Reports 438 (2007) 237– 329
[18]  Encounters with neighbours, N. Marwan, Dissertation, , university of POTSDOM, 2003
[19]  Abdossalehi, M & et al. (under publish). Combining Independent Component Analysis with chaotic quantifiers for the recognition of positive, negative and neutral emotions using EEG signals. Iranian journal of science and technology