Chronic disorders and diseases that affect the cerebrum and the central nervous system, e.g. motor neuron disease, cerebrovascular accident, etc., incapacitate the individual and place a burden on societies and global health systems. The associated health problems of such conditions cannot be eased until further advances are made in neurology and medicine. Potentially, Computing Science can assist individuals with these types of afflictions by providing alternative methods for communication and control. The research discussed herein undertakes the design and evaluation of a collaborative Brain-Computer Interface (BCI) as an Assistive Technology (AT), referred to as a hybrid BCI (/zBCI). The research weaved together three computing topics: BCI, Eye Tracking (ET), and smart environments. A solution was devised with the intention to improve upon conventional BCIs as an AT for those that could potentially benefit from it the most. Five systems were evaluated as a smart environment control mechanism: 1) Steady State Visually Evoked Potential (SSVEP) BCI; 2) an ET-based AT; 3) an ET collaboration with a brain-neuronal computer interaction component; 4) SSVEP BCI with on-screen stimulation; and 5) a hybrid BCI. Significant contributions to knowledge were gathered from the experimentation and evaluation of healthy and brain-injured participants. The development of the ABCI enhanced the performance and usability of both BCI and ET technology. It provided accuracy of 99.84% in healthy volunteers and 99.14% in brain-injured participants. In addition, information transfer rate reached 24.41 bits/min in healthy volunteers and 15.87 bits/min in brain-injured participants. The inclusion of ET did not introduce further intrusion and offered a cost-effective supplementary modality to the BCI. This research has provided an important advance on the state of the art in brain-computer interaction; indeed, the multimodal approach provided deeper understanding o f the decision process by providing insight to behavioural interaction and neural processes in real time.
| Identifer | oai:union.ndltd.org:bl.uk/oai:ethos.bl.uk:734613 |
| Date | January 2018 |
| Creators | Brennan, Christopher P. |
| Publisher | Ulster University |
| Source Sets | Ethos UK |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
Page generated in 0.0014 seconds