The electroencephalogram (EEG) is the sum of electrical activation of thousands of neurons distorted by the head volume conductor. Hence, it lacks spatial resolution and thereby complicates brain state predictions. Source localization (SL) methods aim to restore spatial resolution by reconstructing the origin of the electric activity in the brain. In this PhD thesis SL is applied to EEG single trials in order i) to improve the prediction performance of voluntary movements, and ii) to exploit SL capabilities to further specify a movement, e.g., the performing body part. After presenting the developed reference system for online movement prediction (that does not use SL), a comparsion between three well established SL methods is shown. Then the talk focuses on the classification results obtained when SL is applied and describes the conducted experiments that provide data of, e.g., moving body parts.
Online Movement Prediction for Brain Reading – Application of Source Localization to EEG Single Trials
VenueRoom Seminarraum 117, Robert-Hooke-Str. 5 in Bremen
In der Regel sind die Vorträge Teil von Lehrveranstaltungsreihen der Universität Bremen und nicht frei zugänglich. Bei Interesse wird um Rücksprache mit dem Sekretariat unter sek-ric(at)dfki.de gebeten.