prikaz prve stranice dokumenta Rukovanje problemom neuravnoteženosti klasa putem preuzorkovanja
  Download
PDF 1.01 MB
undergraduate thesis
Rukovanje problemom neuravnoteženosti klasa putem preuzorkovanja
Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2020. urn:nbn:hr:200:125535
Zmeškal, Ivan
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

Institutional repository: Faculty of Electrical Engineering, Computer Science and Information Technology Osijek

Cite this document

Zmeškal, I. (2020). Rukovanje problemom neuravnoteženosti klasa putem preuzorkovanja (Undergraduate 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:200:125535

Zmeškal, Ivan. "Rukovanje problemom neuravnoteženosti klasa putem preuzorkovanja." 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:200:125535

Zmeškal, Ivan. "Rukovanje problemom neuravnoteženosti klasa putem preuzorkovanja." 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:200:125535

Zmeškal, I. (2020). 'Rukovanje problemom neuravnoteženosti klasa putem preuzorkovanja', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 05 November 2024, https://urn.nsk.hr/urn:nbn:hr:200:125535

Zmeškal I. Rukovanje problemom neuravnoteženosti klasa putem preuzorkovanja [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2020 [cited 2024 November 05] Available at: https://urn.nsk.hr/urn:nbn:hr:200:125535

I. Zmeškal, "Rukovanje problemom neuravnoteženosti klasa putem preuzorkovanja", 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:200:125535

Metadata
TitleRukovanje problemom neuravnoteženosti klasa putem preuzorkovanja
Title (english)Handling class imbalance problem with oversampling
AuthorIvan Zmeškal
MentorGoran Martinović (mentor)
MentorDražen Bajer (sumentor)
Committee memberGoran Martinović (predsjednik povjerenstva)
Committee memberZdravko Krpić (član povjerenstva)
Committee memberRobert Cupec (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 country2020-10-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
Pojam klasifikacija u strojnom učenju označava nešto što se moţe razvrstati po odreĎenim poznatim svojstvima, odnosno grupiranje stvari u kategorije. Kada odreĎeni uzorak u strojnom učenju ne pripada niti jednoj klasi, tada se koristi klasifikator, koji ga na temelju prepoznatog dodijeli odreĎenoj klasi; u ovom slučaju algoritam k-najbliţih susjeda i algoritam SMOTE uz njegove interpretacije. Problem neuravnoteţenosti klasa je primjer problema s klasifikacijom gdje je raspodjela klasa asimetrična, a moţe varirati od neznatne asimetrije do itekako značajne neravnoteţe. Nakon objašnjenja problema neuravnoteţenosti klasa i povezivanja neuravnoteţenosti s algoritmima za preuzorkovanje, odraĎen je eksperiment gdje se moţe uvidjeti učinkovitost SMOTE algoritma nad skupovima različitih omjera neuravnoteţenosti.
Abstract (english)
The term classification in machine learning means something that can be classified to certain known properties, i.e. grouping things into categories. When a particular instance does not belong to any class, classifier is used to assign it to a particular class considering recognized propotiers; in this case k-nearest neighbors classifier was used along SMOTE algorithm and his interpretations. After explaining the problem of class imbalance and linking the imbalance with the oversampling algorithms, an experiment was performed where the efficiency of the SMOTE algorithm over sets of various imbalance ratios can be seen. The results of experiment showed that SMOTE increases the accuracy of classifiers for minority classes and provides a new approach to the oversampling imbalanced classes.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:125535
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 on2020-12-07 09:59:55