The study proposes a new method for the diagnosis of epilepsy from EEG signals based on complex classifiers. First of all, 8 effective feature extraction algorithms were used in order to identify meaningful information from EEG signals. In later phases, 8 feature values were presented as introduction to the complex valued neural network (CVANN). Two different classification experiments were undertaken with the help of the developed model: 1) the classification of healthy volunteers, epilepsy patients during seizure and epilepsy patients during a seizure-free interval, 2) the classification of epilepsy patients during seizure and healthy volunteers. The evolution of the proposed system is conducted using k-fold cross-validation, classification accuracy (CA), sensitivity and specificity values. The proposed approach identified EEG signals with 97.01% and 100% accuracy in the first and second experiments respectively. The stated results show that the proposed method is capable of designing a new intelligent assistance diagnostic system. Keywords: Complex-valued neural network, EEG signals, epilepsy disease;
[1]
Huan Liu,et al.
Feature Selection for High-Dimensional Data: A Fast Correlation-Based Filter Solution
,
2003,
ICML.
[2]
Daniel Rivero,et al.
Automatic feature extraction using genetic programming: An application to epileptic EEG classification
,
2011,
Expert Syst. Appl..
[3]
Abdulhamit Subasi,et al.
EEG signal classification using wavelet feature extraction and a mixture of expert model
,
2007,
Expert Syst. Appl..
[4]
T. Nitta,et al.
A back-propagation algorithm for complex numbered neural networks
,
1993,
Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).
[5]
Igor N. Aizenberg,et al.
Complex-Valued Neural Networks with Multi-Valued Neurons
,
2011,
Studies in Computational Intelligence.