magistrsko delo
David Penca (Author), Zoran Bosnić (Mentor)

Abstract

V magistrskem delu predstavimo sistem za ohranjanje uporabnikovega sodelovanja pri igranju računalniških iger, ki deluje na podlagi merjenja psihofizičnih značilk, kot so povprečni srčni utrip, galvanski odziv kože in električna aktivnost v možganih. Pokazati želimo, da je ročno prilagajanje karakteristik računalniških iger možno prepustiti avtomatiziranemu sistemu za ohranjanje uporabnikove vključenosti. Implementacijo takšnega sistema smo razdelili na dva funkcijska sklopa. Prvi sklop predstavlja model vključenosti igralca, ki na podlagi karakteristik igranja in izmerjenih psihofizičnih značilk, ocenjuje uporabnikovo trenutno vključenost. Model uporabnikove vključenosti smo zgradili z uporabo metod nadzorovanega strojnega učenja. Drugi sklop sistema predstavlja algoritem, ki ob zaznanem padcu vključenosti igralca spreminja karakteristike igre z namenom ohranjati uporabnikovo vključenost. Za učenje optimalne strategije spreminjanja karakteristik igre smo uporabili spodbujevano učenje.

Keywords

vključenost v igro;računalniška igra;ADABoost;Q-učenje;magisteriji;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [D. Penca]
UDC: 004.85(043.2)
COBISS: 91293443 Link will open in a new window
Views: 191
Downloads: 20
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: A system for maintaining user’s engagement in computer games
Secondary abstract: In our master thesis, we present a system for maintaining a user's engagement in computer games based on measured psychophysical indicators such as average heartbeat, galvanic skin response and electric activity in the brain. We wish to prove that hand adjustment of video game parameters can instead be performed by an automated system for maintaining player engagement. We split the implementation of such a system into two separate sections. The first section consists of a user-engagement model that predicts the current user engagement based on the player's gameplay characteristics and measured psychophysical indicators. We have built the engagement model using supervised machine learning techniques. The second section of the system is represented by an algorithm that, when a drop in user engagement is detected, adjusts game parameters in order to maintain user engagement. The optimal strategy for changing game parameters was learned through the use of reinforcement learning.
Secondary keywords: game engagement;machine learning;computer game;ADABoost;Q-learning;computer science;computer and information science;master's degree;Videoigre;Strojno učenje;Računalništvo;Univerzitetna in visokošolska dela;
Type (COBISS): Master's thesis/paper
Study programme: 1000471
Embargo end date (OpenAIRE): 1970-01-01
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 61 str.
ID: 14060817