Extraction of outliers from imbalanced sets

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68081766%3A_____%2F17%3A00477864" target="_blank" >RIV/68081766:_____/17:00477864 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/00216224:14110/17:00098161 RIV/00216275:25530/17:39910984

Výsledek na webu

<a href="http://dx.doi.org/10.1007/978-3-319-59650-1_34" target="_blank" >http://dx.doi.org/10.1007/978-3-319-59650-1_34</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-319-59650-1_34" target="_blank" >10.1007/978-3-319-59650-1_34</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Extraction of outliers from imbalanced sets

Popis výsledku v původním jazyce

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 alternative.

Název v anglickém jazyce

Extraction of outliers from imbalanced sets

Popis výsledku anglicky

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 alternative.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

<a href="/cs/project/GA17-20286S" target="_blank" >GA17-20286S: Fyziologie hibernace netopýrů s ohledem na dopad mnohočetných stresorů</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Hybrid Artificial Intelligent Systems: 12th International Conference, HAIS 2017, La Rioja, Spain, June 21-23, 2017, Proceedings

ISBN

978-3-319-59649-5

ISSN

0302-9743

e-ISSN

—

Počet stran výsledku

11

Strana od-do

402-412

Název nakladatele

Springer

Místo vydání

Cham

Místo konání akce

La Rioja

Datum konání akce

21. 6. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—