In Partial Fulfillment of the Requirements for the Degree of Master of Science
will defend his thesis
Development of a Hybrid EEG-NIRS Brain-Computer Interface for Multiple Motor Tasks
Non-invasive Brain Computer Interfaces (BCI) have demonstrated great promise for neuroprosthetics and assistive devices. Here we aim to investigate methods to combine Electroencephalography (EEG) and Near-Infrared-Spectroscopy (NIRS) in an asynchronous Sensory Motor rhythm (SMR)-based BCI. We attempted to classify 4 different executed and imagined movements: right arm-left arm and right hand-left hand tasks.
Previous studies demonstrated the benefit of EEG-NIRS combination, without processing NIRS signal with online implementable methods. Since normally NIRS hemodynamic response shows a long delay, we investigated new features, involving slope indicators, in order to immediately detect changes in the signals. Moreover, Common Spatial Patterns (CSP) have been applied to both EEG and NIRS signals. 15 healthy subjects took part in the experiments and since only 25 trials per class were available, CSP have been regularized with information from the entire population of participants and optimized using genetic algorithms.
Different approaches have been investigated for feature extrac tion, classification and signal association. The results showed that a hybrid EEG-NIRS approach enhances the performance of EEG or NIRS alone. Better performances are achieved for motor execution paradigm probably due to the subjects' inexperience in motor imagery, despite the small dataset available.
Date: Friday, July 24, 2015
Time: 2:00 PM
Place: PGH 550
Advisor: Prof. Marc Garbey & Prof. Ahmet Omurtag
Faculty, students, and the general public are invited.