prikaz prve stranice dokumenta Valićna transformacija u sustavima sučelja mozga i računala
No public access
master's thesis
Valićna transformacija u sustavima sučelja mozga i računala
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. urn:nbn:hr:168:111846
Friganović, Krešimir
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Friganović, K. (2016). Valićna transformacija u sustavima sučelja mozga i računala (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:111846

Friganović, Krešimir. "Valićna transformacija u sustavima sučelja mozga i računala." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. https://urn.nsk.hr/urn:nbn:hr:168:111846

Friganović, Krešimir. "Valićna transformacija u sustavima sučelja mozga i računala." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2016. https://urn.nsk.hr/urn:nbn:hr:168:111846

Friganović, K. (2016). 'Valićna transformacija u sustavima sučelja mozga i računala', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 23 November 2024, https://urn.nsk.hr/urn:nbn:hr:168:111846

Friganović K. Valićna transformacija u sustavima sučelja mozga i računala [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2016 [cited 2024 November 23] Available at: https://urn.nsk.hr/urn:nbn:hr:168:111846

K. Friganović, "Valićna transformacija u sustavima sučelja mozga i računala", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2016. Available at: https://urn.nsk.hr/urn:nbn:hr:168:111846

Metadata
TitleValićna transformacija u sustavima sučelja mozga i računala
Title (english)Wavelet transformation in brain-computer interfaces
AuthorKrešimir Friganović
MentorMario Cifrek (mentor)
Committee memberMario Cifrek (član povjerenstva)
Committee memberIgor Lacković (član povjerenstva)
Committee memberIgor Krois (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2016-02-05, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
Sustavi sučelja mozga i računala (engl. Brain-computer interfaces, BCI) predstavljaju rješenja komunikacije između čovjeka i računala putem mjerene bioelektrične aktivnosti mozga. Komunikacija je tako nezavisna o neuromišićnim putevima te se uspostavlja namjerom ili zamisli putem senzoričke obrade informacija u mozgu ili pak kognitivnim procesima. U ovom radu obrađeni su EEG signali prilikom zamišljanja pokreta lijeve i desne ruke. Kao oruđe analize korištena je metoda valićne transformacije s devet različitih prototipnih valića. Multirezolucijska analiza diskretnom valićnom transformacijom provedena je za detalje četvrte razine. Za usporedbu uspješnosti klasifikacije signal je analiziran Fourierovom transformacijom na vremenskom otvoru (engl. Short-time Fourier Transform, STFT). Klasifikacija je provedena linearnom diskriminantnom analizom (engl. Linear discriminant analysis, LDA). Korištenje valićne transformacije polučilo je slične rezultate u klasifikaciji EEG signala prilikom zamišljanja pokreta kao i korištenje Fourierove transformacije na vremenskom otvoru. Jedna od pogodnosti koji donosi valićna transformacija je smanjenje mogućih frekvencijskih, odnosno skalarnih, blokova koje je potrebno obraditi za pojedinog ispitanika.
Abstract (english)
Brain-computer interfaces (BCI) give solutions for communication between human and computer with measured bioelectrical activity of the brain. In such way, communication is independent of the normal neuromuscular pathways. Communication is established by the means of attention or thought with sensory or cognitive brain processes. In this paper EEG signals during right and left hand motor imagery are analyzed. Wavelet transform with nine different mother wavelets was used as a tool of analysis. Multiresolution analysis with discrete wavelet transform (DWT) was done for level 4 details. For comparison of classification results, signal was also analyzed with short-time Fourier transform (STFT). Classification was done with linear discriminant analysis (LDA). Wavelet transform gave similar results in classification accuracy of motor imagery EEG signals as short-time Fourier transform. Benefit of wavelet transform approach is reduction of number of frequency (scalar) bands analyzed for individual subject.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:111846
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2018-02-06 08:47:11