ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Development of an eyes-moving based brain-computer interface

Luka Loboda (2017) Development of an eyes-moving based brain-computer interface. EngD thesis.

[img]
Preview
PDF
Download (2052Kb)

    Abstract

    This diploma thesis represents a process of development of a Brain-Computer Interface (BCI) based on eyes movement. The BCI systems acquire and analyse the brain activity and convert it to suitable commands. The goal of this diploma thesis was to develop an interface that enables a user to move the cursor on the screen. For measuring the brain activities, we used the Emotiv EPOC headset, which is a representative of very affordable systems that enable acquisition of the electroencephalogram (EEG). In the scope of this thesis, we also developed an application for acquiring and visualizing the EEG signals and their spectra in real time. We used the application to assess a various of techniques of conscious influence on the EEG signals, of which the most suitable appeared to be the technique of moving the eyes to the left and right. On the basis of this technique, we defined a protocol, which using initial calibration, allows a user moving of the cursor on the screen in the horizontal direction. We tested the functionality of the interface using a test by which the test subjects performed movements of the cursor, as required by the testing program. In 85.5% of the attempts, the test subjects managed to perform the requested cursor movement within two seconds.

    Item Type: Thesis (EngD thesis)
    Keywords: Brain-computer interface, Eyes-movement, Electroencephalogram, Realtime acquiring and analysing, Conscious influence on brain activity
    Number of Pages: 54
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    prof. dr. Franc Jager235Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537559747)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 3952
    Date Deposited: 14 Sep 2017 18:11
    Last Modified: 02 Oct 2017 14:08
    URI: http://eprints.fri.uni-lj.si/id/eprint/3952

    Actions (login required)

    View Item