Adaptation and Control State Detection Techniques for Brain-Computer Interfaces

A brain computer interface (BCI) is an alternate channel of communication between the user and the computer, without having to go through the usual neuromuscular pathways. Using BCI, disabled patients can communicate with a computer or control a prosthetic device just by modulating his/her brain activity. This thesis focuses on two of the desirable capabilities of a usable and practical BCI system - adaptation and control state detection. Adaptation is the ability of the BCI system to adapt to incoming data, and control state detection refers to its ability to determine whether the user is actively giving input. A co-training based approach is proposed for constructing adaptive classifiers for P300 BCIs, which were trained from very little data. The proposed approach is able to build high-performance classifiers from just a few minutes of labeled data by making efficient use of unlabeled data. An asynchronous BCI system combining P300 and steady-state visually evoked potentials (SSVEP) paradigms is also proposed. Information transfer is accomplished using P300 event related potential (ERP) paradigm and control state detection is achieved using SSVEP. The system is shown to achieve fast and accurate control state detection. Techniques for improving the performance of the proposed techniques are also suggested.

Author dc:creator

• RAJESH CHANDRASEKHARA PANICKER

• Brain-Computer Interface, Adaptation, Control State Detection, P300, Steady-state visually evoked potentials (SSVEP), Biosignal processing