prikaz prve stranice dokumenta Kvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida
No public access
doctoral thesis
Kvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2002. urn:nbn:hr:168:428253
Matetić, Maja
University of Zagreb
Faculty of Electrical Engineering and Computing
Department of Electronics, Microelectronics, Computer and Intelligent Systems

Institutional repository: FER Repository

Cite this document

Matetić, M. (2002). Kvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida (Doctoral thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:428253

Matetić, Maja. "Kvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida." Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2002. https://urn.nsk.hr/urn:nbn:hr:168:428253

Matetić, Maja. "Kvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida." Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2002. https://urn.nsk.hr/urn:nbn:hr:168:428253

Matetić, M. (2002). 'Kvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida', Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 18 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:428253

Matetić M. Kvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida [Doctoral thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2002 [cited 2024 December 18] Available at: https://urn.nsk.hr/urn:nbn:hr:168:428253

M. Matetić, "Kvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida", Doctoral thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2002. Available at: https://urn.nsk.hr/urn:nbn:hr:168:428253

Metadata
TitleKvalitativno modeliranje i zaključivanje o ponašanju objekata u sustavu dinamičkog vida
Title (english)Qualitative Modelling and Reasoning About Behavior of Objects in the Dynamic Vision System
AuthorMaja Matetić
MentorSlobodan Ribarić (mentor)
Committee memberLeo Budin (član povjerenstva)
Committee memberSlobodan Ribarić (član povjerenstva)
Committee memberNikola Pavešić (član povjerenstva)
Committee memberNikola Bogunović (član povjerenstva)
Committee memberLjubo Marangunić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
(Department of Electronics, Microelectronics, Computer and Intelligent Systems)
Zagreb
Defense date and country2002-10-25, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Universal decimal classification
(UDC)		004 - Computer science and technology. Computing. Data processing
Abstract
U radu je predstavljen sustav LABAQM koji je razvijen za analizu ponašanja laboratorijske životinje. Sustav se temelji na kvalitativnom modeliranju kretanja životinje. Bavimo se fazom raspoznavanja, koja predstavlja višu razinu analize ponašanja laboratorijske životinje, tijekom farmakoloških eksperimenata. Ulazni podaci sustava su kvantitativni podaci koje dobiva od aplikacije za praćenje, te nepotpuno znanje eksperta. Sustav LABAQM radi u dvije glavne faze: faza učenja ponašanja i faza analize ponašanja. Faza učenja i faza analize se temelje na nizovima simbola dobivenim transformacijom kvantitativnih podataka. Faza učenja uključuje postupak nadgledanog učenja, postupak nenadgledanog učenja i njihovu kombinaciju. Pokazali smo da kvalitativne modele ponašanja možemo modelirati kao skrivene Markovljev modele (SMM-e). Rezultati fuzije postupaka nadgledanog i nenadgledanog učenja su robustniji modeli karakterističnih ponašanja, koji se koriste u fazi analize ponašanja.
Abstract (english)
The paper presents the LABAQM system developed for the analysis of laboratory animal behaviours. It is based on qualitative modelling of animal motions. We are dealing with the cognitive phase of the laboratory animal behaviour analysis as a part of the pharmacological experiments. The system is based on the quantitative data from the tracking application and incomplete domain background knowledge. The LABAQM system operates in two main phases: behaviour learning and behaviour analysis. The behaviour learning and behaviour analysis phase are based on symbol sequences, obtained by the transformation of the quantitative data. Behaviour learning phase includes supervised learning procedure, unsupervised learning procedure and their combination. We have shown that the qualitative model of behaviour can be modelled by hidden Markov models. The fusion of supervised and unsupervised learning procedures produces more robust models of characteristic behaviours, which are used in the behaviour analysis phase.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:428253
Study programmeTitle: Computer Science
Study programme type: university
Study level: postgraduate
Academic / professional title: Doktor znanosti (Doktor znanosti)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Created on2019-04-30 07:27:57