prikaz prve stranice dokumenta Otkrivanje anomalija i stršećih vrijednosti u podatcima
No public access
undergraduate thesis
Otkrivanje anomalija i stršećih vrijednosti u podatcima
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. urn:nbn:hr:168:407076
Lisica, David
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Lisica, D. (2021). Otkrivanje anomalija i stršećih vrijednosti u podatcima (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:407076

Lisica, David. "Otkrivanje anomalija i stršećih vrijednosti u podatcima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:407076

Lisica, David. "Otkrivanje anomalija i stršećih vrijednosti u podatcima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2021. https://urn.nsk.hr/urn:nbn:hr:168:407076

Lisica, D. (2021). 'Otkrivanje anomalija i stršećih vrijednosti u podatcima', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 14 January 2025, https://urn.nsk.hr/urn:nbn:hr:168:407076

Lisica D. Otkrivanje anomalija i stršećih vrijednosti u podatcima [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2021 [cited 2025 January 14] Available at: https://urn.nsk.hr/urn:nbn:hr:168:407076

D. Lisica, "Otkrivanje anomalija i stršećih vrijednosti u podatcima", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:168:407076

Metadata
TitleOtkrivanje anomalija i stršećih vrijednosti u podatcima
Title (english)Detecting Anomalies and Outliers in Data
AuthorDavid Lisica
MentorVladimir Čeperić (mentor)
Committee memberVladimir Čeperić (predsjednik povjerenstva)
Committee memberEugen Vušak (član povjerenstva)
Committee memberMarko Barišić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2021-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Rad uvodi pojmove anomalije i stršeće vrijednosti. Predstavljena je motivacija za otkrivanje takvih vrijednosti, kao i podjela problema prema dimenzionalnosti podataka na univarijatne i multivarijatne. Objašnjeni su postupci otkrivanja anomalija u skupu univarijatnih podataka korištenjem pravila 3-sigma i međukvartilnog raspona. Za multivarijatne podatke predstavljen je programski alat PyOD i objašnjeni neki njegovi algoritmi poput kNN, ABOD, CBLOF i IForest. Za skup podataka uzeti su zapisi o prodanim nekretninama u SAD-u. Provedena je analiza podataka s naglaskom na značajkama „cijena nekretnine“ i „prosječni godišnji dohodak kućanstva“. Pristupljeno je implementaciji rješenja nad skupom tih dviju značajki koristeći nekoliko klasifikatora. Rješenja su grafički prikazana i uspoređena.
Abstract (english)
This paper introduces the concepts of anomaly and outlier. It presents the motivation for discovering such values, as well as the division of problems by the dimensionality into univariate and multivariate data. The paper explains procedures for detecting anomalies in a set of univariate data using the rule of 3-sigma and interquartile range and also for multivariate data using the software tool PyOD and some of its algorithms such as kNN, ABOD, CBLOF and IForest. Records of real estate sold in the United States were used as dataset. Data analysis was performed with an emphasis on the characteristics “real estate price” and “average annual household income”. The implementation of a solution on a set of these two features is made using several classifiers. The solutions are graphically presented and compared.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:407076
Study programmeTitle: 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 resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-14 20:59:16