Programska potpora za analizu značajki fizioloških reakcija na emocionalne podražaje primjenom statističkih metoda i strojnog učenja

master's thesis

• Title (english): Software for Analysis of Physiological Response Features to Emotional Stimuli Based on Statistical Methods and Machine Learning
• Author: Tomislav Marković
• Mentor: Siniša Popović (mentor)
• Committee member: Siniša Popović (predsjednik povjerenstva)
• Committee member: Mile Šikić (član povjerenstva)
• Committee member: Leonardo Jelenković (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru ovog diplomskog rada prikazan je proces oblikovanja i izrade programske potpore za analizu značajki fizioloških reakcija na emocionalne podražaje primjenom statističkih metoda i strojnog učenja. Prvo je dan pregled dostupnih programskih rješenja i teorijska osnova nekih metoda primijenjenih u izradi programske potpore. Zatim je opisan model strukture programske potpore. Glavni dio rada bavi se opisom implementacije programske potpore, pri čemu se upotrebljavaju već postojeći fiziološki podatci iz ranije provedenih laboratorijskih eksperimenata. Nakon implementacije opisano je novo laboratorijsko mjerenje koje je provedeno u okviru ovog rada zajedno s postupkom prilagodbe programske potpore za rad s novim podatcima, te su ilustrirani rezultati provedene analize podataka.

Abstract (english)

The thesis shows the design and development of the software for analysis of physiological features of responses to emotional stimuli based on statistical methods and machine learning. The first part of the thesis gives an overview of existing software solutions and theoretic basis of some methods that were applied during software development. Afterwards, the model of the software structure is described. The main part of the thesis deals with implementation of the software, which relies on existing physiological data obtained from prior laboratory experiments. Finally, a new laboratory measurement that was conducted in this thesis is explained together with the process of needed software modifications and extensions to work with these data, and the obtained results of data analysis are illustrated.

• Keywords: fiziološke reakcije; emocionalni podražaji; strukture podataka; značajke; statističke metode; vizualizacija; strojno učenje
• Keywords (english): physiological reactions; emotional stimuli; data structures; features; statistical methods; visualization; machine learning
• Language: croatian
• URN:NBN: urn:nbn:hr:168:868862
• 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: 2018-02-06 10:28:25