Napredna pretraga

Pregled bibliografske jedinice broj: 1011968

Performance Analysis of SMOTE-Based Oversampling Techniques When Dealing with Data Imbalance


Bajer, Dražen; Zorić, Bruno; Dudjak, Mario; Martinović, Goran
Performance Analysis of SMOTE-Based Oversampling Techniques When Dealing with Data Imbalance // Proceedings of IWSSIP 2019 / Rimac-Drlje, Snježana ; Žagar, Drago ; Galić, Irena ; Martinović, Goran ; Vranješ, Denis ; Habijan, Marija (ur.).
Osijek: Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek, 2019. str. 265-271 doi:10.1109/IWSSIP.2019.8787306 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Performance Analysis of SMOTE-Based Oversampling Techniques When Dealing with Data Imbalance

Autori
Bajer, Dražen ; Zorić, Bruno ; Dudjak, Mario ; Martinović, Goran

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of IWSSIP 2019 / Rimac-Drlje, Snježana ; Žagar, Drago ; Galić, Irena ; Martinović, Goran ; Vranješ, Denis ; Habijan, Marija - Osijek : Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek, 2019, 265-271

ISBN
978-1-7281-3253-2

Skup
2019 International Conference on Systems, Signals and Image Processing (IWSSIP)

Mjesto i datum
Osijek, Hrvatska, 05-07.06.2019

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Classification ; data imbalance ; minority oversampling ; SMOTE

Sažetak
Building classification models on imbalanced data proves to be a challenging task despite the multitude of available classifiers. The classifier bias towards the majority class can be ameliorated through various manners and with varying degrees of success. Oversampling minority instances or undersampling majority ones are prominent amongst these due both to their simplicity and effectiveness. Probably the most popular approach to oversampling is the well-known SMOTE algorithm, based on which numerous enhancement attempts were made. This paper aims to compare the performance of these, more complex, oversampling techniques with regard to the original on a wide array of problems. Additionally, it attempts to give insight into the behaviour of different interpretations of the original algorithm apparent in the literature. In that regard, some interesting findings were made.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo



POVEZANOST RADA


Projekt / tema
KK.01.1.1.01.0009 - Napredne metode i tehnologije u znanosti o podatcima i kooperativnim sustavima (Sven Lončarić, EK)

Ustanove
Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek

Citati