Class-Based Outlier Detection: Staying Zombies or Awaiting for
Resurrection?

D 2015

Class-Based Outlier Detection: Staying Zombies or Awaiting for Resurrection?

NEZVALOVÁ, Leona, Lubomír POPELÍNSKÝ, Luis TORGO and Karel VACULÍK

Basic information

Original name

Class-Based Outlier Detection: Staying Zombies or Awaiting for Resurrection?

Authors

NEZVALOVÁ, Leona (203 Czech Republic, belonging to the institution), Lubomír POPELÍNSKÝ (203 Czech Republic, guarantor, belonging to the institution), Luis TORGO (620 Portugal) and Karel VACULÍK (203 Czech Republic, belonging to the institution)

Edition

Neuveden, Advances in Intelligent Data Analysis XIV - 14th International Symposium, IDA 2015, p. 193-204, 12 pp. 2015

Publisher

Springer

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United Kingdom of Great Britain and Northern Ireland

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

Impact factor

Impact factor: 0.402 in 2005

RIV identification code

RIV/00216224:14330/15:00084902

Organization unit

Faculty of Informatics

ISBN

978-3-319-24464-8

ISSN

DOI

http://dx.doi.org/10.1007/978-3-319-24465-5_17

UT WoS

000389228500017

Keywords in English

class-based outlier detection; outlier interpretation; outlier description; anomaly detection; outlier detection

Abstract

V originále

This paper addresses the task of finding outliers within each class in the context of supervised classification problems. Class-based outliers are cases that deviate too much with respect to the cases of the same class. We introduce a novel method for outlier detection in labelled data based on Random Forests and compare it with the existing methods both on artificial and real-world data. We show that it is competitive with the existing methods and sometimes gives more intuitive results. We also provide an overview for outlier detection in labelled data. The main contribution are two methods for class-based outlier description and interpretation.

Citovat

NEZVALOVÁ, Leona, Lubomír POPELÍNSKÝ, Luis TORGO and Karel VACULÍK. Class-Based Outlier Detection: Staying Zombies or Awaiting for Resurrection?. Online. In Elisa Fromont, Tijl De Bie, Matthijs van Leeuwen. Advances in Intelligent Data Analysis XIV - 14th International Symposium, IDA 2015. Neuveden: Springer, 2015, p. 193-204. ISBN 978-3-319-24464-8. Available from: https://dx.doi.org/10.1007/978-3-319-24465-5_17.

@inproceedings{1318718,
   author = {Nezvalová, Leona and Popelínský, Lubomír and Torgo, Luis and Vaculík, Karel},
   address = {Neuveden},
   booktitle = {Advances in Intelligent Data Analysis XIV - 14th International Symposium, IDA 2015},
   doi = {http://dx.doi.org/10.1007/978-3-319-24465-5_17},
   editor = {Elisa Fromont, Tijl De Bie, Matthijs van Leeuwen},
   keywords = {class-based outlier detection; outlier interpretation; outlier description; anomaly detection; outlier detection},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Neuveden},
   isbn = {978-3-319-24464-8},
   pages = {193-204},
   publisher = {Springer},
   title = {Class-Based Outlier Detection: Staying Zombies or Awaiting for Resurrection?},
   year = {2015}
}

TY  - JOUR
ID  - 1318718
AU  - Nezvalová, Leona - Popelínský, Lubomír - Torgo, Luis - Vaculík, Karel
PY  - 2015
TI  - Class-Based Outlier Detection: Staying Zombies or Awaiting for Resurrection?
PB  - Springer
CY  - Neuveden
SN  - 9783319244648
KW  - class-based outlier detection
KW  - outlier interpretation
KW  - outlier description
KW  - anomaly detection
KW  - outlier detection
N2  - This paper addresses the task of finding outliers within each class in the context of supervised classification problems. Class-based outliers are cases that deviate too much with respect to the cases of the same class. We introduce a novel method for outlier detection in labelled data based on Random Forests and compare it with the existing methods both on artificial and real-world data. We show that it is competitive with the existing methods and sometimes gives more intuitive results. We also provide an overview for outlier detection in labelled data. The main contribution are two methods for class-based outlier description and interpretation.
ER  -

NEZVALOVÁ, Leona, Lubomír POPELÍNSKÝ, Luis TORGO and Karel VACULÍK. Class-Based Outlier Detection: Staying Zombies or Awaiting for Resurrection?. Online. In Elisa Fromont, Tijl De Bie, Matthijs van Leeuwen. \textit{Advances in Intelligent Data Analysis XIV - 14th International Symposium, IDA 2015}. Neuveden: Springer, 2015, p.~193-204. ISBN~978-3-319-24464-8. Available from: https://dx.doi.org/10.1007/978-3-319-24465-5\_{}17.

Detailed Information on Publication Record