Biblioteka za rad sa slučajnim šumama

undergraduate thesis

• Title (english): Library for Random Forest Algorithm
• Author: Jakov Ćurić
• Mentor: Marko Čupić (mentor)
• Committee member: Marko Čupić (predsjednik povjerenstva)
• Committee member: Mihael Marović (član povjerenstva)
• Committee member: Zoran Medić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-09-14, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu implementirana je biblioteka za rad sa slučajnim šumama u programskom jezku Java. Objašnjeni su temeljni pojmovi i problemi koji se javljaju pri stvaranju i evaluaciji stabala regresije i klasifikacije. Navadeni su načešće korišteni algoritmi današnjice te su analizirane njihove sličnosti i razlike te prednosti i mane. Biblioteka je testirana kroz ukupno 5 testova. Prva tri testa uključuju kreiranje i evaluaciju pojedinačnih stabala za odabrane probleme klasifikacije i regresije. Ostala dva testa provjeravaju kreiranje i evaluaciju slučajne šume za odabrane probleme klasifikacije i regresije. U testovima su prikazani programi, podaci koji se koriste te ispisi programa. Prokomentirane su sve klase od kojih se biblioteka sastoji te su objašnjene najvažnije metode.

Abstract (english)

The main goal of this thesis was to implement a random forest Java library.
The key concepts and problems of building and evaluating decision trees are explained. The most relevant modern decsion tree building algorithms are listed, mutually compared and their advantages and disadvantages are described.
The library is tested with a total of 5 tests. The first three tests include building and evaluating singular decision trees for different problems of classification and regression. The last two tests include building and evaluating a random forest for different problems of classification and regression. The tests include the main methods, the data being used and the outputs. Every class of the library is described and the most relevant methods are analyzed.

• Keywords: slučajne; šume; stablo; odluke; regresija; klasifikacija; algoritam; java; biblioteka
• Keywords (english): random; forest; tree; decision; regression; classification; algorithm; java; library
• Language: croatian
• URN:NBN: urn:nbn:hr:168:066046
• Study programme: Title: Computing; 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-14 20:15:19