Izdvajanje značajki vidnih evociranih potencijala stabilnog stanja

undergraduate thesis

• Title (english): Steady State Visual Evoked Potentials Feature Extraction
• Author: Eda Jovičić
• Mentor: Mario Cifrek (mentor)
• Committee member: Mario Cifrek (predsjednik povjerenstva)
• Committee member: Željka Lučev Vasić (član povjerenstva)
• Committee member: Krešimir Friganović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-07-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Ostvarivanje sučelja mozga i računala (engl. Brain-computer interface, BCI) temelji se na mjerenju bioelektrične aktivnosti mozga. U ovom radu promatraju se vidni evocirani potencijali stabilnog stanja (engl. steady state visually evoked potentials, SSVEP) koji se pojavljuju kada osoba prima treptajući svjetlosni podražaj. Evocirani potencijali mjereni su elektroencefalogramom (EEG) na okcipitalnoj regiji mozga. EEG signali obrađeni su brzom Fourierovom transformacijom i kanonskom korelacijskom analizom, te je provedena klasifikacija dobivenih značajki. Obrada se provodila na različitim vremenskim odsječcima signala s ciljem smanjenja potrebne količine podataka za uspješnu klasifikaciju. Uspoređene su točnosti klasificiranja dviju navedenih metoda na različitim vremenskim odsječcima temeljem čega su izdvojene korisne značajke.

Abstract (english)

Creating brain-computer interface (BCI) is based on measuring bioelectric brain activity. This paper observes steady state visually evoked potentials (SSVEP). SSVEP occurs when a person receives flashing light stimulus. SSVEPs were measured by electroencephalogram (EEG) on the occipital region of the brain. EEG signals were processed by Fast Fourier Transformation (FFT) and Canonical Correlation Analysis (CCA) and a classification of the obtained features was performed. The processing was carried out at different time slots of the signal with the goal of reducing required amount of data for a successful classification. We compared the classification accuracy of the two listed methods on different time slots. This was used to select features which are useful for further processing.

• Keywords: elektroencefalografija (EEG); vidni evocirani potencijali stabilnog stanja; Fourierova transformacija; kanonska korelacijska analiza
• Keywords (english): electroencephalography (EEG); steady state visually evoked potentials; Fourier transformation; canonical correlation analysis
• Language: croatian
• URN:NBN: urn:nbn:hr:168:093339
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-03-13 21:14:50