diplomsko delo univerzitetnega študijskega programa
Luka Bratoš (Author), Aleš Holobar (Mentor)

Abstract

V diplomskem delu smo sistematično preučili in ovrednotili učinkovitost različnih algoritmov slepe ločitve signalov (SOBI, JADER, FASTICA, RUNICA) pri odstranjevanju artefaktov v večkanalnih elektroencefalogramih (EEG). Osredotočili smo se na časovno zahtevnost, na stopnjo dušenja artefaktov in na stabilnost konvergence omenjenih algoritmov. Podrobneje smo preučili učinkovitost odstranjevanja artefaktov zaradi utripanja z očmi, premikanja jezika, žvečenja, lateralnega premikanja oči ter premikanja glave. Ugotovili smo, da vsi testirani algoritmi, razen algoritma RUNICA, učinkovito odstranjujejo artefakte, in potrdili v uvodu zastavljeno tezo diplomskega dela, da je s postopki slepe ločitve signalov mogoče, tudi v primeru manjšega nabora kanalov EEG, učinkovito odstraniti šum in artefakte v signalih EEG.

Keywords

elektroencefalogram;EEG;slepa ločitev signalov;anotacija signalov;

Data

Language: Slovenian
Year of publishing:
Source: Maribor
Typology: 2.11 - Undergraduate Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [L. Bratoš]
UDC: 621.3:[591.185:616.8](043.2)
COBISS: 15658774 Link will open in a new window
Views: 1760
Downloads: 167
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Artefact rejection in multichannel electroencephalograms
Secondary abstract: We have systematically studied and assessed the efficiency of various blind source separation algorithms (SOBI, JADER, FASTICA, RUNICA) in removing the artefacts in multichannel electroencephalograms (EEG). We have mainly focused on computational complexity of tested algorithms, level of their suppression of artefacts and on stability of their convergence. In particular, the efficiency in removing of the artefacts due to eye blinking, tongue movements, chewing, lateral eye movements and head movements has been assessed. All tested algorithms, except RUNICA, have demonstrated significant level of artefact suppression at relatively low computational costs. Out of the algorithms tested, SOBI offered the superior performance. We therefore conclude that blind signal separation is effective in removing of noise and artefacts in multichannel EEG, even in the case of small number of EEG channels.
Secondary keywords: razmerje artefakt-signal;electroencephalogram;blind signal separation;EEGLAB;sLORETA;signal annotation;artefact;
URN: URN:SI:UM:
Type (COBISS): Bachelor thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko
Pages: VIII, 33 f.
Keywords (UDC): applied sciences;medicine;technology;uporabne znanosti;medicina;tehnika;engineering;technology in general;inženirstvo;tehnologija na splošno;mechanical engineering in general;nuclear technology;electrical engineering;machinery;strojništvo;electrical engineering;elektrotehnika;applied sciences;medicine;technology;uporabne znanosti;medicina;tehnika;medical sciences;medicina;pathology;clinical medicine;patologija;klinična medicina;neurology;neuropathology;nervous system;nevrologija;nevropatologija;živčevje;
ID: 1016075
Recommended works:
, diplomsko delo univerzitetnega študijskega programa
, diplomsko delo univerzitetnega študijskega programa
, raziskovalna naloga