Interpretation of Autoencoders and PCA with Adaboost Classifier for Classification of Epilepsy from EEG Signals

Epilepsy is a kind of biomedical disturbance that results in abnormal electrical activity in some neurons and later it spreads to the entire brain. The normal cognitive behaviour is severely affected with this abnormal activity of the neurons. Seizure is the characteristic hallmark of epilepsy and it poses a huge threat to the entire mankind. Electroencephalography (EEG) signals are used for the analysis, detection and treatment of epilepsy. The recordings of EEG signals are too huge and so effective dimensionality reduction techniques like Autoencoders and Principal Component Analysis (PCA) are employed to reduce the dimensions of the original EEG data. The dimensionally reduced values are then fed inside the Adaboost classifier to classify the epilepsy risk levels from EEG signals.