Login for students

Login for employees

Publication detail

Extraction of Outliers from Imbalanced Sets
Authors: Škrabánek Pavel | Martínková Natália
Year: 2017
Type of publication: článek ve sborníku
Name of source: Hybrid Artificial Intelligent Systems : 12th International Conference, HAIS 2017, proceedings
Publisher name: Springer
Place: Heidelberg
Page from-to: 402-412
Titles:
Language Name Abstract Keywords
cze Extrakce odlehlých hodnot z nevyvážených datových sad Článek přináší popis metody určené k detekci odlehlých hodnot v datových sadách s malým počtem pozorování, kde správná pozorování tvoří jeden klastr. Pro správnou funkčnost je potřeba, aby počet správných pozorování byl výrazně vyšší než počet odlehlých pozorování. Metoda je založena na Mahalanobis vzdálenosti.
eng Extraction of Outliers from Imbalanced Sets In this paper, we presented an outlier detection method, designed for small datasets, such as datasets in animal group behaviour research. The method was aimed at detection of global outliers in unlabelled datasets where inliers form one predominant cluster and the outliers are at distances from the centre of the cluster. Simultaneously, the number of inliers was much higher than the number of outliers. The extraction of exceptional observations (EEO) method was based on the Mahalanobis distance with one tuning parameter. We proposed a visualization method, which allows expert estimation of the tuning parameter value. The method was tested and evaluated on 44 datasets. Excellent results, fully comparable with other methods, were obtained on datasets satisfying the method requirements. For large datasets, the higher computational requirement of this method might be prohibitive. This drawback can be partially suppressed with an alternative distance measure. We proposed to use Euclidean distance in combination with standard deviation normalization as a reliable outlier analysis; distance based method; global outlier; single cluster; Mahalanobis distance; biology

Department

Map

en.mapy.cz

Services

Popular Links

© 2023 University of Pardubice, Studentská 95, 532 10 Pardubice 2
Phone: +420 466 036 111, 466 036 112, 466 036 113
Webmaster, RSS
Data box ID: f5vj9hu
Accessibility Statement
CC BY-NC-ND 4.0Creative CommonsAttributionNonCommercialNoDerivatives