Određivanje usmjerenosti pažnje na različite vizualne podražaje iz elektroencefalograma pomoću BCILAB-a

undergraduate thesis

• Title (english): Detecting direction of attention on different visual stimuli from electroencephalogram using BCILAB
• Author: Petra Franjić
• Mentor: Mario Cifrek (mentor)
• Committee member: Mario Cifrek (predsjednik povjerenstva)
• Committee member: Željka Lučev Vasić (član povjerenstva)
• Committee member: Sara Žulj (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Sučelje mozga i računala (engl. Brain Computer Interface, BCI) omogućuje korisniku da s okolinom komunicira bez potrebe za voljnom kontrolom mišića, oslanjajući se pritom najčešće na analizu električne aktivnosti mozga. Jedan od BCI sustava koji radi na tom načelu je i P300 sustav za slovkanje koji se temelji na izazivanju P300 vala. U sklopu ovog rada u BCILAB alatu za MATLAB analizirani su podaci dobiveni korištenjem navedene paradigme za slovkanje. Na jednostrukim repeticijama je provedena usporedba klasifikatora za različite vremenske intervale ekstrakcije prostorno-vremenskih obilježja, gdje se kao najtočnija pokazala linearna diskriminantna analiza (engl. Linear Discriminant Analysis, LDA). U sklopu rada je u BCILAB-u na temelju specifičnosti klasifikatora uspješno provedena detekcija slova na koje je ispitanik pri ispitivanju usmjerio pažnju.

Abstract (english)

A brain-computer interface is a system which allows users to communicate without the need for them to use voluntary muscle control. To realise this, the system usually analyses electrical brain activity. An example of this approach is the P300 spelling system which is based on the evocation of the P300 wave. As a part of this thesis the MATLAB toolbox BCILAB was used for analysing data collected using the P300 speller paradigm. Different classifiers were compared on a single-trial basis using different time windows for spatiotemporal feature extraction, where linear discriminant analysis (LDA) proved itself as the most accurate classifier. BCILAB was also used to successfully detect the letter the test subject had attended to, by analysing classifier specificity for different letters of the spelling matrix.

• Keywords: sučelje mozga i računala; (BCI); P300 val; prostorno-vremenska obilježja; linearna diskriminantna analiza (LDA)
• Keywords (english): brain-computer interface (BCI); P300; linear discriminant analysis (LDA); spatio-temporal features
• Language: croatian
• URN:NBN: urn:nbn:hr:168:883841
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 08:46:47