prikaz prve stranice dokumenta Problem klasifikacije kod autonomnih sustava
Access restricted to students and staff of home institution
undergraduate thesis
Problem klasifikacije kod autonomnih sustava
Split: University of Split, University of Split, Faculty of science, 2017. urn:nbn:hr:166:329997
Lešić, Danijel
University of Split
Faculty of Science
Department of Informatics

Institutional repository: Repository of Faculty of Science

Cite this document

Lešić, D. (2017). Problem klasifikacije kod autonomnih sustava (Undergraduate thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:329997

Lešić, Danijel. "Problem klasifikacije kod autonomnih sustava." Undergraduate thesis, University of Split, Faculty of Science, 2017. https://urn.nsk.hr/urn:nbn:hr:166:329997

Lešić, Danijel. "Problem klasifikacije kod autonomnih sustava." Undergraduate thesis, University of Split, Faculty of Science, 2017. https://urn.nsk.hr/urn:nbn:hr:166:329997

Lešić, D. (2017). 'Problem klasifikacije kod autonomnih sustava', Undergraduate thesis, University of Split, Faculty of Science, accessed 11 November 2024, https://urn.nsk.hr/urn:nbn:hr:166:329997

Lešić D. Problem klasifikacije kod autonomnih sustava [Undergraduate thesis]. Split: University of Split, Faculty of Science; 2017 [cited 2024 November 11] Available at: https://urn.nsk.hr/urn:nbn:hr:166:329997

D. Lešić, "Problem klasifikacije kod autonomnih sustava", Undergraduate thesis, University of Split, Faculty of Science, Split, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:166:329997

Metadata
TitleProblem klasifikacije kod autonomnih sustava
Title (english)Classification problem in autonomous systems
AuthorDanijel Lešić
MentorSaša Mladenović (mentor)
Committee memberSaša Mladenović (predsjednik povjerenstva)
Committee memberGoran Zaharija (član povjerenstva)
Committee memberDivna Krpan (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Informatics)
Split
Defense date and country2017-09-29, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad opisuje problem klasifikacije kod autonomnih sustava. U prvom dijelu rada opisan je pojam inteligentnog agenta, vrste agenata, te načini klasifikacije zadanog problema. U drugom dijelu rada predstavljena je aplikacija koja korisniku omogućuje klasificiranje slika. Implementirane su tri aplikacije. U prvoj je moguće napraviti test podatke za učenje i testiranje mreže za slučaj prepoznavanja slike. Druga aplikacija služi za stvaranje ili učitavanje već postojeće mreže sa 225 ulaznih čvorova, dva izlazna čvora i dva skrivena sloja. Prvi skriveni sloj ima 114 čvorova, a drugi skriveni sloj ima 58 čvorova. Nakon postavljanja čvorova, odnosno neurona, mreža pomoću podataka za učenje koje joj pružimo uči, a na kraju istreniranu mrežu moguće je spremiti za kasniju upotrebu. Za testiranje mreže odabrano je prepoznavanje slika prometnih znakova. Treća aplikacija radi klasifikaciju slika prema dobivenim podatcima iz prve dvije aplikacije.
Abstract (english)
This paper describes the problem od classification in autonomous systems. The first part of the paper describes the term intelligent agent, types of agents and the ways of classifying the default problem. In the second part of the paper, an application that allows the user to classify images is presented. Three applications were implemented. In the first one, it is possible to make test data for learning and testing the network for image recognition. Second application is to create or load an already existing network with 225 input nodes, two output nodes and two hidden layers. The first hidden layer has 114 nodes, and the second hidden layer 58 nodes. After setting nodes or neurons, the network uses the learning data for training, and in the end of the retrieved network can be saved for later use. To test the network, the recognition of the traffic sign image is selected. The third application is to classify the image accordnig to the data obtained from the first two applications.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:329997
Study programmeTitle: Computer Science
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2018-05-29 15:41:33