prikaz prve stranice dokumenta Klasifikacija tkiva kroničnih rana metodama strojnog učenja
  Download
PDF 6.86 MB
master's thesis
Klasifikacija tkiva kroničnih rana metodama strojnog učenja
2020. urn:nbn:hr:200:895730
Mičić, Vladimir
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Automation and Robotics

Cite this document

Mičić, V. (2020). Klasifikacija tkiva kroničnih rana metodama strojnog učenja (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:895730

Mičić, Vladimir. "Klasifikacija tkiva kroničnih rana metodama strojnog učenja." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:895730

Mičić, Vladimir. "Klasifikacija tkiva kroničnih rana metodama strojnog učenja." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. https://urn.nsk.hr/urn:nbn:hr:200:895730

Mičić, V. (2020). 'Klasifikacija tkiva kroničnih rana metodama strojnog učenja', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 22 April 2021, https://urn.nsk.hr/urn:nbn:hr:200:895730

Mičić V. Klasifikacija tkiva kroničnih rana metodama strojnog učenja [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2021 April 22] Available at: https://urn.nsk.hr/urn:nbn:hr:200:895730

V. Mičić, "Klasifikacija tkiva kroničnih rana metodama strojnog učenja", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:200:895730

Islandora Bookmark - Please login to use this feature
Metadata
TitleKlasifikacija tkiva kroničnih rana metodama strojnog učenja
Title (english)Chronic wound tissue classification using machine learning methods
AuthorVladimir Mičić
MentorDamir Filko (mentor)
Committee memberDamir Filko (predsjednik povjerenstva)
Committee memberEmmanuel Karlo Nyarko (član povjerenstva)
Committee memberRobert Cupec (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Computer Engineering and Automation)
(Chair of Automation and Robotics)
Osijek
Defense date and country2020-09-22, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Razvoj umjetne inteligencije u mnogim je područjima života unaprijedio i olakšao izvršavanje zadataka koji zahtijevaju preciznost i objektivnost. Jedna od potencijalnih primjena umjetne inteligencije jest i u medicini pri određivanju svojstava kroničnih rana poput njihovih dimenzija, tipova tkiva od kojih se sastoji rana te u praćenju procesa cijeljenja u svrhu određivanja potrebne terapije itd. U ovom se radu razmatra primjena klasifikacije kao alata strojnog učenja u određivanju tipa tkiva na fotografijama kroničnih rana, primjenom različitih klasifikatora u različitim prostorima boja. Na temelju uzoraka tipova tkiva, fibrin, granulacija i nekroza te primjenom nekolicine algoritama za klasifikaciju implementirani su klasifikatori u programskom jeziku Python. Na dostupnoj bazi slika kroničnih rana provedena je klasifikacija postojećim klasifikatorima u različitim prostorima boja te je rezultat precision-recall karakteristika.
Abstract (english)
The development of artificial intelligence in many areas of life has improved and facilitated the execution of tasks that require precision and objectivity. One of the potential applications of artificial intelligence is in medicine in determining the properties of chronic wounds such as their dimensions, tissue types of the wound and in monitoring the healing process to determine the necessary therapy, etc. This thesis discusses the application of machine learning in determining tissue type in photographs of chronic wounds, by applying different classifiers in different color spaces. Based on learning samples of tissue types, fibrin, granulation and necrosis, and several classification algorithms, classifiers in the Python programming language have been implemented. On the basis of images of chronic wounds, the classification was performed by various classificators in different color spaces, and the result is the precision-recall characteristic.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:895730
Study programmeTitle: Graduate University Study Programme in Electrical Engineering; specializations in: Communications and Informatics, Power Engineering
Course: Communications and Informatics
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike (magistar/magistra inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-11-20 11:19:38