prikaz prve stranice dokumenta Izrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa
  Download
PDF 2.24 MB
master's thesis
Izrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa
2023. urn:nbn:hr:200:846078
Ćurić, Tomislav
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Cite this document

Ćurić, T. (2023). Izrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:846078

Ćurić, Tomislav. "Izrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:846078

Ćurić, Tomislav. "Izrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2023. https://urn.nsk.hr/urn:nbn:hr:200:846078

Ćurić, T. (2023). 'Izrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 08 January 2025, https://urn.nsk.hr/urn:nbn:hr:200:846078

Ćurić T. Izrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2023 [cited 2025 January 08] Available at: https://urn.nsk.hr/urn:nbn:hr:200:846078

T. Ćurić, "Izrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:200:846078

Please login to the repository to save this object to your list.
Metadata
TitleIzrada sustava za prepoznavanje bolesti pčelinjaka prisustvom nametnika Varoa
Title (english)Development of the system for recognizing the bee disease by the presence of the parasite Varoa
AuthorTomislav Ćurić
MentorGoran Martinović (mentor)
MentorDino Kurtagić (sumentor)
Committee memberGoran Martinović (predsjednik povjerenstva)
Committee memberAlfonzo Baumgartner (član povjerenstva)
Committee memberIvan Aleksi (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2023-11-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Information Systems
Abstract
Cilj ovog diplomskog rada je izrada sustava za detekciju grinje varoa koja može poslužiti pčelarima za davanje upozorenja u ranijim fazama pojave grinje u svrhu pravovremenog i odgovarajućeg tretiranja. U teorijskom dijelu ovog rada prikazana je morfologija grinje te je kao problem navedena detekcija sitnih objekata i moguća rješenja poput povećanja prostorne razlučivosti slike i segmentacija fotografije. Nadalje, objašnjen je način rada neuronskih mreža, objašnjena načela prijenosnog učenja te definirane mjere vrednovanja modela. U praktičnom dijelu rada ostvareno je programsko rješenje za detekciju grinje varoa. Programsko rješenje implementirano je na mobilnoj i Internet platformi te se za unos podataka na Android platformi koristi kamera mobitela, vrši se detekcija i prikazuje korisniku. Za Internet aplikaciju potrebno je imati pripremljene fotografije koje se učitaju i rezultat se ispisuje. U implementaciji aplikacija koristio se YOLOv8 model koji je postigao najbolje rezultate. Rezultati ispitivanja sustava ukazuju na dodatan rad mobilne aplikacije kako bi se sustav usavršio.
Abstract (english)
The purpose of this paper is to develop a system that detects varroa mites which can be used by beekeepers as early warning in the earlier stages of appearance of the mite for the purpose of timely and appropriate treatment. In the theoretical part of this paper the morphology of the mite is presented, and as a problem, detection of small objects was stated and possible solutions such as increasing the spatial resolution of the image and image segmentation. Furthermore, the way how neural networks operate is explained, the principles of transfer learning are explained and the evaluation measures of the model are defined. In the practical part of the paper, a software solution for the detection of the varroa mite was implemented. The software solution is implemented on the mobile and internet platforms, and the mobile camera is used for data input on Android platform, afterwards detection is applied and shown to user. For the web application, it is necessary to have preprocessed images, so when images are uploaded the results can be shown. In the implementation of the application, YOLOv8 model was used, model that had achieved the best performance. The results of the system indicate that additional work of the mobile application is needed in order to improve the system
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:846078
Study programmeTitle: Graduate University Study Programme in Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: sveučilišni/a magistar/magistra inženjer/inženjerka računarstva (sveučilišni/a magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-11-16 13:18:26