Dijagnostički indeks depresije kao kvantitativna metoda klasifikacije afektivnih poremećaja

master's thesis

• Title (english): Depression Diagnosis Index as a Quantitative Classification Method of Affective Disorders
• Author: Ivan Skorupan
• Mentor: Mario Cifrek (mentor)
• Committee member: Mario Cifrek (predsjednik povjerenstva)
• Committee member: Tomislav Pribanić (član povjerenstva)
• Committee member: Alan Jović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-06-28, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Iz dostupne baze signala EEG-a izdvojeno je nekoliko linearnih i nelinearnih značajki koje su uspoređene statističkim metodama. Iz dobivene usporedbe odabrano je
nekoliko najboljih značajki koje su iskorištene u formuli za dijagnostički indeks depre-
sije. Uz spomenuti indeks, provedena je klasifikacija dostupnih signala EEG-a pomoću
nekoliko odabranih metoda strojnog učenja. Sve metode potrebne za izradu ovog rada,
od izdvajanja značajki sve do računanja indeksa depresije i provedbe klasifikacije modelima
strojnog učenja implementirane su u web aplikaciji za analizu signala EEG-a.

Abstract (english)

Several linear and non-linear EEG signal features have been extracted from the available signal database and compared using statistical methods. Several best features have been chosen from this comparison and were used in the formula for the diagnostic depression index. Along with the aforementioned index, classification of available EEG signals has been done using several chosen machine learning methods. Classification results were compared to the constructed model of diagnostic depression index. All methods needed to make this thesis, from feature extraction, depression index calculation all the way to classification using machine learning models have been implemented in a web application for EEG signal analysis.

• Keywords: eeg; elektroencefalografija; indeks; depresija; dijagnostika; nelinearne značajke; klasifikacija; statistički test
• Keywords (english): eeg; electroencephalography; index; depression; diagnostics; nonlinear features; classification; statistical test
• Language: croatian
• URN:NBN: urn:nbn:hr:168:394623
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 09:56:23