prikaz prve stranice dokumenta Usporedba metoda za razvrstavanje oko središnje točke
  Download
PDF 1.71 MB
undergraduate thesis
Usporedba metoda za razvrstavanje oko središnje točke
2020. urn:nbn:hr:200:338445
Znaor, Filip
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Computer Engineering and Automation
Chair of Computer Engineering

Cite this document

Znaor, F. (2020). Usporedba metoda za razvrstavanje oko središnje točke (Undergraduate thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:338445

Znaor, Filip. "Usporedba metoda za razvrstavanje oko središnje točke." Undergraduate 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:200:338445

Znaor, Filip. "Usporedba metoda za razvrstavanje oko središnje točke." Undergraduate 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:200:338445

Znaor, F. (2020). 'Usporedba metoda za razvrstavanje oko središnje točke', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 14 March 2023, https://urn.nsk.hr/urn:nbn:hr:200:338445

Znaor F. Usporedba metoda za razvrstavanje oko središnje točke [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2023 March 14] Available at: https://urn.nsk.hr/urn:nbn:hr:200:338445

F. Znaor, "Usporedba metoda za razvrstavanje oko središnje točke", Undergraduate 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:200:338445

Please login to the repository to save this object to your list.
Metadata
TitleUsporedba metoda za razvrstavanje oko središnje točke
Title (english)Comparison of central point clustering methods
AuthorFilip Znaor
MentorIvica Lukić (mentor)
Committee memberIvica Lukić (predsjednik povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
Committee memberGoran Martinović (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 Computer Engineering)
Osijek
Defense date and country2020-09-11, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Abstract
U završnom radu je opisan pojam razvrstavanja objekata te vrste metoda za razvrstavanje objekata s naglaskom na razvrstavanje oko središnje točke. Opisane su neke od češće korištenih metoda razvrstavanja objekata oko središnje točke. Navedene su i objašnjene mjere udaljenosti za objekte s brojčanim obilježjima te mjere kvalitete razvrstavanja objekata. Dan je opis ostvarenog programskog rješenja koje omogućuje izvođenje i usporedbu metoda za razvrstavanje oko središnje točke. Algoritmi k-means, k-means++, k-medoids i fuzzy c-means analizirani su i uspoređeni koristeći ostvareno programsko rješenje na raznim skupovima podataka. Algoritam k-medoids pokazao se kao najbolji algoritam za razvrstavanje malih skupova podataka, algoritam k-means++ kao najbolji algoritam za razvrstavanje velikih skupova podataka zbog male vremenske složenosti, a algoritam fuzzy c-means kao najprikladniji algoritam za razvrstavanje niskodimenzionalnih skupova podataka s preklapanjem između grozdova.
Abstract (english)
The final paper describes data clustering and different types of data clustering methods with an emphasis on center-based data clustering. Descriptions of some of the most frequently used center-based data clustering methods are given. Distance metrics for numerical data and assessment metrics for data clustering are listed and explained. A description of the realized software solution that allows execution and comparison of center-based data clustering methods is given. The algorithms which were analyzed and compared using the software solution on various datasets are k-means, k-means++, k-medoids and fuzzy c-means. The k-medoids algorithm proved to be the best algorithm for clustering small datasets, the k-means++ algorithm proved to be the best algorithm for clustering large datasets due to its low time complexity, and the fuzzy c-means algorithm proved to be the most suitable algorithm for clustering low-dimensional datasets with overlap between clusters.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:338445
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-11-11 12:41:34