Data Mining an EEG Dataset With an Emphasis on Dimensionality Reduction

The human brain is obviously a complex system, and exhibits rich spatiotemporal dynamics. Among the non-invasive techniques for probing human brain dynamics, electroencephalography (EEG) provides a direct measure of cortical activity with millisecond temporal resolution. Early attempts to analyse EEG data relied on visual inspection of EEG records. Since the introduction of EEG recordings, the volume of data generated from a study involving a single patient has increased exponentially. Therefore, automation based on pattern classification techniques have been applied with considerable success. In this study, a multi-step approach for the classification of EEG signal has been adopted. We have analysed sets of EEG time series recording from healthy volunteers with open eyes and intracranial EEG recordings from patients with epilepsy during ictal (seizure) periods. In the present work, we have employed a discrete wavelet transform to the EEG data in order to extract temporal information in the form of changes in the frequency domain over time - that is they are able to extract non-stationary signals embedded in the noisy background of the human brain. Principal components analysis (PCA) and rough sets have been used to reduce the data dimensionality. A multi-classifier scheme consists of LVQ2.1 neural networks have been developed for the classification task. The experimental results validated the proposed methodology