Smanjenje smetnji u elektroencefalogramu pomoću analize nezavisnih komponenata

undergraduate thesis

• Title (english): Artefact reduction in electroencephalogram using independent component analysis
• Author: Matea Mihalj
• Mentor: Mario Cifrek (mentor)
• Committee member: Mario Cifrek (predsjednik povjerenstva)
• Committee member: Tomislav Pribanić (član povjerenstva)
• Committee member: Željka Lučev Vasić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-09-10, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Elektroencefalografija (EEG) je neinvazivna metoda mjerenja električne moždane aktivnosti. Valovite promjene na snimkama električnih potencijala zovu se moždani ritmovi, a cijela snimka elektroencefalogram.
EEG sadrži smetnje što otežava njegovu obradu. Jedna od tehnika koja omogućava smanjenje smetnji je slijepa separacija signala.
Postoji nekoliko metoda slijepe separacije od kojih su najpopularnije metoda analize glavnih osi (engl. Principal Component Analysis, PCA) i metoda nezavisnih komponenti (engl. Independent Component Analysis, ICA).
PCA je linearna metoda transformacije kojom se minimizira statistička ovisnost drugog reda promatranih signala.
Ako su ispunjene pretpostavke za ICA-u primjenjuje se nakon PCA. ICA je linearna transformacija koja minimizira statističku ovisnost viših redova signala čije razdiobe odstupaju od Gaussove razdiobe.
Kod ICA-e frekvencija signala ostaje očuvana a amplituda ne.

Abstract (english)

Electroencephalography (EEG) is non-invasive method of measuring electrical brain activity. Oscillatory changes on recordings of electrical potentials are called brain waves, and the whole recording electroencephalogram.
EEG contains interference that complicates its processing. One of the techniques that allow the reduction of interference is called blind source separation.
There are some methods of blind source separation, and the most popular are principal component analysis (PCA) and independent component analysis (ICA).
PCA is a linear transformation method that minimizes the statistical dependence of the second order of the observed signal.
If preconditions of ICA are satisfied ICA is applied after PCA. If the conditions are not satisfied it is possible to use only PCA. ICA is a linear transformation that minimizes the statistical dependence of higher ranks of non-Gaussian signals.
In ICA frequency of signals is preserved, but amplitude not.

• Keywords: elektroencefalografija (EEG); slijepa separacija signala (BSS); metoda nezavisnih komponenti (ICA); metoda analize glavnih osi (PCA); JADE
• Keywords (english): electroencephalography (EEG); blind source separation (BSS); independent component analysis (ICA); principal component analysis (PCA); Joint Approximate Diagonalization of Eigen-matrices (JADE)
• Language: croatian
• URN:NBN: urn:nbn:hr:168:310694
• 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: 2018-02-06 10:39:44