Title
Identifikacija, analiza i klasifikacija kretanja zgloba kolena
Creator
Petrović-Savić, Suzana R., 1983-
Copyright date
2016
Object Links
Select license
Autorstvo-Nekomercijalno-Bez prerade 3.0 Srbija (CC BY-NC-ND 3.0)
License description
Dozvoljavate samo preuzimanje i distribuciju dela, ako/dok se pravilno naznačava ime autora, bez ikakvih promena dela i bez prava komercijalnog korišćenja dela. Ova licenca je najstroža CC licenca. Osnovni opis Licence: http://creativecommons.org/licenses/by-nc-nd/3.0/rs/deed.sr_LATN. Sadržaj ugovora u celini: http://creativecommons.org/licenses/by-nc-nd/3.0/rs/legalcode.sr-Latn
Language
Serbian
Cobiss-ID
Inventory ID
D-2973
Theses Type
Doktorska disertacija
description
Datum odbrane: 26.09.2016.
Other responsibilities
mentor
Devedžić, Goran, 1962-
predsednik komisije
Manić, Miodrag, 1957-
član komisije
Ristić, Branko, 1962-
član komisije
Filipović, Nenad, 1970-
član komisije
Adamović, Dragan, 1960-
Academic Expertise
Tehničko-tehnološke nauke
University
Univerzitet u Kragujevcu
Faculty
Fakultet inženjerskih nauka
Publisher
[S. R. Petrović Savić]
Format
VI, 183 lista
Abstract (en)
Gait is a fundamental human activity. One of the main joints that participate
in walking process is knee joint. This joint is considered to be the largest and most complex joint in human body. This complexity comes from possibility of translation
and rotation along and around all axes. All of these movements have
corresponding pattern.
Main purpose of this doctoral thesis is to identify and analyze standard
values and patterns of basic movement parameters of healthy individuals.
Experimental research was done in Clinical Centre Kragujevac on healthy
individuals and on patients with deficient/diseased soft tissue and/or cartilaginous knee structures. Three systems were used for acquiring data – OptiTrack, Kinetic
XBOX camera and simple web camera. Mathematical model of a knee was
created for calculating identified gait parameters.
It is concluded, with a help of statistical methods, that there is a significant difference in gait pattern between healthy individuals and patients with
deficient/diseased knee joint structures.
For the purpose of getting objective results, models for
predicting/classification (based on logistic regression and neural network models)
possible damage/illness of knee joint based on walk parameters values and gait
curves were created. Models for predicting/classification are valued by diagnostic
tests.
Results showed that this approach can help in better understanding of
processes in knee joint that occur during walking, can help to achieve objectivity in
walking process evaluation, improve rehabilitation process depending on level of
recovery of the patient, etc.
Authors Key words
mechanics, MoCap systems, parameters of knee joint, logistic
regression, neural networks
Authors Key words
mehanika, sistem za snimanje kretanja, parametri kretanja zgloba kolena, logistička regresija, neuronske mreže
Classification
004.942.32:531.14/.15;
004.942.32:519.248
Subject
Zglob kolena - Kretanje - Računarska simulacija
Subject
Biomehanika
Type
Tekst
Abstract (en)
Gait is a fundamental human activity. One of the main joints that participate
in walking process is knee joint. This joint is considered to be the largest and most complex joint in human body. This complexity comes from possibility of translation
and rotation along and around all axes. All of these movements have
corresponding pattern.
Main purpose of this doctoral thesis is to identify and analyze standard
values and patterns of basic movement parameters of healthy individuals.
Experimental research was done in Clinical Centre Kragujevac on healthy
individuals and on patients with deficient/diseased soft tissue and/or cartilaginous knee structures. Three systems were used for acquiring data – OptiTrack, Kinetic
XBOX camera and simple web camera. Mathematical model of a knee was
created for calculating identified gait parameters.
It is concluded, with a help of statistical methods, that there is a significant difference in gait pattern between healthy individuals and patients with
deficient/diseased knee joint structures.
For the purpose of getting objective results, models for
predicting/classification (based on logistic regression and neural network models)
possible damage/illness of knee joint based on walk parameters values and gait
curves were created. Models for predicting/classification are valued by diagnostic
tests.
Results showed that this approach can help in better understanding of
processes in knee joint that occur during walking, can help to achieve objectivity in
walking process evaluation, improve rehabilitation process depending on level of
recovery of the patient, etc.
“Data exchange” service offers individual users metadata transfer in several different formats. Citation formats are offered for transfers in texts as for the transfer into internet pages. Citation formats include permanent links that guarantee access to cited sources. For use are commonly structured metadata schemes : Dublin Core xml and ETUB-MS xml, local adaptation of international ETD-MS scheme intended for use in academic documents.