Wavelet family and differential evolution are proposed for categorization of epilepsy cases based on electroencephalogram (EEG) signals. Discrete wavelet transform is widely used in feature extraction step because it efficiently works in this field, as confirmed by the results of previous studies. The feature selection step is used to minimize dimensionality by excluding irrelevant features. This step is conducted using differential evolution. This article presents an efficient model for EEG classification by considering feature extraction and selection. Seven different types of common wavelets were tested in our research work. These are Discrete Meyer (dmey), Reverse biorthogonal (rbio), Biorthogonal (bior), Daubechies (db), Symlets (sym), Coiflets (coif), and Haar (Haar). Several kinds of discrete wavelet transform are used to produce a wide variety of features. Afterwards, we use differential evolution to choose appropriate features that will achieve the best performance of signal classification. For classification step, we have used Bonn databases to build the classifiers and test their performance. The results prove the effectiveness of the proposed model.
Determination of the Optimum Wavelet Basis Function for Indonesian Vowel Voice Recognition
