Analysis of Brain Signals for the Discrimination of Observations of Correct and Incorrect Actions
P. A. Asvestas 1, S. A. Kostopoulos 1, E. M. Ventouras 1, A. Korda 2,
G. K. Matsopoulos 2, and
I. S. Karanasiou 3
1. Department of Biomedical Engineering, Technological Educational Institute of Athens, Greece
2. School of Electrical and Computer Engineering, National Technical University of Athens, Greece
3. Institute of Communications and Computer Systems, Athens, Greece
2. School of Electrical and Computer Engineering, National Technical University of Athens, Greece
3. Institute of Communications and Computer Systems, Athens, Greece
Abstract—The aim of this paper is to present a methodology that is capable to discriminate between observations of correct actions and observations of incorrect. Towards this end, Event-Related Potentials (ERPs) were recorded from 47 locations on the scalp of 16 healthy volunteers, who observed correct or incorrect actions of other subjects. The recorded signals were analyzed in the frequency domain and the normalized signal power at various frequency bands was calculated. Feature selection was applied in order to reduce the number of available features. Finally, the obtained feature vectors were clustered using the fuzzy c-means algorithm resulting in clustering accuracy 84.4%.
Index Terms—event-related potentials, EEG rhythms, frequency analysis, clustering, fuzzy c-means
Cite: P. A. Asvestas, S. A. Kostopoulos, E. M. Ventouras, A. Korda, G. K. Matsopoulos, and I. S. Karanasiou, "Analysis of Brain Signals for the Discrimination of Observations of Correct and Incorrect Actions," International Journal of Signal Processing Systems, Vol. 3, No. 2, pp. 100-105, December 2015. doi: 10.12720/ijsps.3.2.100-105