Ambulatory EEG

Wearable computers allow ubiquitous computing as we move around and interact with the world. EEG sensors, unfortunately, are designed for use in controlled laboratory settings. This project aims to autonomously classify the states the ambularoty user is engaged in from multiple sensor sources. The system will apply a different noise model in different situations to non-causally filter the EEG data. This will allow the EEG sensors to be used in a wide variety of situations and contexts.