Pinky : interactively analyzing large EEG datasets

Abstract

In this thesis, I describe a system I designed and implemented for interactively analyzing large electroencephalogram (EEG) datasets. Trained experts, known as encephalographers, analyze EEG data to determine if a patient has experienced an epileptic seizure. Since EEG analysis is time intensive for large datasets, there is a growing corpus of unanalyzed EEG data. Fast analysis is essential for building a set of example data of EEG results, allowing doctors to quickly classify the behavior of future EEG scans. My system aims to reduce the cost of analysis by providing near real-time interaction with the datasets. The system has three optimized layers handling the storage, computation, and visualization of the data. I evaluate the design choices for each layer and compare three dierent implementations across dierent workloads.