Artificial immune recognition system with fuzzy resource allocation mechanism classifier, principal component analysis and FFT method based new hybrid automated identification system for classification of EEG signals

The aim of this study is to classification of EEG signals using a new hybrid automated identification system based on Artificial immune recognition system (AIRS) with fuzzy resource allocation mechanism, principal component analysis (PCA) and fast Fourier transform (FFT) method. EEG signals used belong to normal subject and patient that has epileptic seizure. The proposed system has three stages: (i) feature extraction using Welch (FFT) method, (ii) dimensionality reduction using PCA, and (iii) EEG classification using AIRS with fuzzy resource allocation. We have used the 10-fold cross-validation, classification accuracy, sensitivity and specificity analysis, and confusion matrix to show the robustness and efficient of proposed system. The obtained classification accuracy is about 100% and it is very promising compared to the previously reported classification techniques.