DWT Approach Based on Analysis of Seizures in EEG Signal

Seizures are neurological disorders that affect approximately 50 million people worldwide. It occurs unusually and unpredictably due to transient electrical brain disruption. The electroencephalogram (EEG) signal was decomposed using the discrete wavelet transform into five frequency bands are delta, theta, alpha beta and gamma. Signals were reprocessed, decomposed by using discrete wavelet transform DWT till 7th level of decomposition tree. Various features like mean. Standard deviation, median, entropy and energy were computed and consequently used for classification of signals. The range of these features in non-epileptic and epileptic group of 100 subjects each from data set is analyzed and interpreted. the parameters with distinct non-overlapping zone are identified. The results shows the compared frequency band beta frequency band of the entropy parameter decreased by 86% among seizure subjects among all frequencies and parameters. The enhanced beta activity reflects greater attention and hyperactivity. In the future, a large number of seizure data can be used and more statistical features to train and test the CNN to obtain higher accuracy.