prikaz prve stranice dokumenta PROCJENA KVALITETE VINA
  Download
PDF 1.52 MB
undergraduate thesis
PROCJENA KVALITETE VINA
2021. urn:nbn:hr:200:306353
Orić, Mihaela
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

Orić, M. (2021). PROCJENA KVALITETE VINA (Undergraduate thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:306353

Orić, Mihaela. "PROCJENA KVALITETE VINA." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:306353

Orić, Mihaela. "PROCJENA KVALITETE VINA." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:306353

Orić, M. (2021). 'PROCJENA KVALITETE VINA', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 19 March 2023, https://urn.nsk.hr/urn:nbn:hr:200:306353

Orić M. PROCJENA KVALITETE VINA [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2021 [cited 2023 March 19] Available at: https://urn.nsk.hr/urn:nbn:hr:200:306353

M. Orić, "PROCJENA KVALITETE VINA", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:200:306353

Please login to the repository to save this object to your list.
Metadata
TitlePROCJENA KVALITETE VINA
Title (english)Machine Learning based estimation of wine quality
AuthorMihaela Orić
MentorEmmanuel Karlo Nyarko (mentor)
Committee memberIvana Hartman-Tolić (predsjednik 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 country2021-09-28, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Kvaliteta vina određena je mnogim kemijsko-fizikalnim svojstvima. Ali i ta svojstva uvjetovana su cijelim procesom nastajanja vina. Kvaliteta plodova vinove loze ovisi o okruženju vinograda i o klimatskim uvjetima kojima je on izložen, poput izloženosti suncu, karakteristike tla i načina berbe. Konkurencija kod proizvodnje vina je velika i potrebno je osigurati konstantno visoku kvalitetu. Ona se provjerava testom kušanja, međutim to nije najefikasnija metoda. U ovom radu napravit će se nova metoda koja bi bila jeftinija, brža, točnija i efikasnija od testa kušanja. Koristit će se klasifikacija pomoću strojnog učenja (algoritam slučajnih šuma, stroj s potpornim vektorima) kojom će se odrediti kvaliteta vina na temelju jedanaest svojstava. Napravljeni model klasifikatora bi za svako novo proizvedeno vino mogao odrediti njegovu kvalitetu, što znači da bi osiguravao da svako vino koje se stavlja na tržište bude provjereno odlične kvalitete. Također će se zaključiti koja svojstva najviše utječu na kvalitetu te bi se tako svako vino kontroliranjem tih svojstava moglo dodatno poboljšati.
Abstract (english)
The quality of wine is determined by many chemical and physical properties, which are conditioned by the entire process of wine production. The quality of the grapevine fruit depends on the environment of the vineyard and the climatic conditions to which it is exposed, such as sun insolation, soil characteristics and harvesting methods. Competition in wine production is high and it is necessary to ensure consistently high quality of produced wine. Wine quality is traditionally checked by tasting, which is not the most effective method. This paper presents a method that is cheaper, faster, and more efficient than the tasting test. Machine learning (Random Forest Classifier, SVM) is used to determine wine quality based on eleven characteristics. The presented classifier model can determine the quality of each newly produced wine, what ensures high quality of each wine placed on the market. Finally, the most important properties that have impact on quality are emphasized, so that each wine could be further improved by controlling these properties.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:306353
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 on2021-11-05 16:01:53