Klasifikacija afektivnih poremećaja korištenjem linearnih značajki signala EEG-a

undergraduate thesis

• Title (english): Classification of Affective Disorders using Linear Features of EEG signal
• Author: Tamara Ćorić
• Mentor: Mario Cifrek (mentor)
• Committee member: Mario Cifrek (predsjednik povjerenstva)
• Committee member: Eda Jovičić (član povjerenstva)
• Committee member: Luka Klaić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-09-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Elektroencefalografija je postupak snimanja aktivnosti mozga pomoću elektroda postavljenih na površinu glave. Povratni depresivni poremećaj spada u afektivne poremećaje, odnosno psihičke poremećaje raspoloženja. Strojno učenje se bavi razvojem metoda za što precizniju i učinkovitiju klasifikaciju podataka. U ovom radu korištene su snimke EEG signala zdravih ispitanika te ispitanika sa dijagnozom povratnog depresivnog poremećaja. Na signalima je provedena predobrada signala s ciljem uklanjanja šuma i izdvajanja relevantnog dijela snimke signala, te su izdvojene linearne značajke. Korištenjem metoda strojnog učenja, signali su klasificirani kao "zdravi" i "depresivni". Za klasifikaciju su korišteni modeli logističke regresije i algoritam stabla odluke, te su rezultati prikazani u radu.

Abstract (english)

Electroencephalography is a procedure for recording brain activity using electrodes placed on the surface of the head. Recurrent depressive disorder belongs to affective disorders, that is, psychological mood disorders. Machine learning deals with the development of methods for the most accurate and efficient classification of data. In this work, recordings of EEG signals of healthy subjects and subjects with a diagnosis of recurrent depressive disorder were used. The signals were pre-processed with the aim of removing noise and extracting the relevant part of the signal recording, and linear features were extracted. Using machine learning methods, the signals are classified as "healthy" and "depressed". Logistic regression models and the decision tree algorithm were used for classification, and the results are presented in the paper.

• Keywords: elektroencefalografija; EEG; strojno učenje; afektivni poremećaji
• Keywords (english): electroencephalography; EEG; machine learning; affective disorders
• Language: croatian
• URN:NBN: urn:nbn:hr:168:901630
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 08:40:47