Fuzzy outlier analysis a combined clustering - Outlier detection approach

Noha Yousri, Mohammed A. Ismail, Mohamed S. Kamel

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

Many outlier detection methods identify outliers ignoring any structure in data. However, it is sometimes beneficial to integrate outlierness and a method that groups data, such as clustering. This enhances both outlier and cluster analysis. In this paper, a fuzzy approach is proposed for integrating results from an outlier detection method and a clustering algorithm. A universal set of clusters is proposed which combines clusters obtained from clustering, and a virtual cluster for the outliers. The approach has two phases; the first computes patterns' initial memberships for the outlier cluster, and the second calculates memberships for the universal clusters, using an iterative membership propagation technique. The proposed approach is general and can combine any outlier detection method with any clustering algorithm. Both low and high dimensional data sets are used to illustrate the impact of the proposed approach.

Original languageEnglish
Title of host publication2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007
Pages412-418
Number of pages7
DOIs
Publication statusPublished - 1 Dec 2007
Externally publishedYes
Event2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007 - Montreal, QC, Canada
Duration: 7 Oct 200710 Oct 2007

Other

Other2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007
CountryCanada
CityMontreal, QC
Period7/10/0710/10/07

Fingerprint

Clustering algorithms
Cluster analysis

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yousri, N., Ismail, M. A., & Kamel, M. S. (2007). Fuzzy outlier analysis a combined clustering - Outlier detection approach. In 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007 (pp. 412-418). [4413873] https://doi.org/10.1109/ICSMC.2007.4413873

Fuzzy outlier analysis a combined clustering - Outlier detection approach. / Yousri, Noha; Ismail, Mohammed A.; Kamel, Mohamed S.

2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007. 2007. p. 412-418 4413873.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yousri, N, Ismail, MA & Kamel, MS 2007, Fuzzy outlier analysis a combined clustering - Outlier detection approach. in 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007., 4413873, pp. 412-418, 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007, Montreal, QC, Canada, 7/10/07. https://doi.org/10.1109/ICSMC.2007.4413873
Yousri N, Ismail MA, Kamel MS. Fuzzy outlier analysis a combined clustering - Outlier detection approach. In 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007. 2007. p. 412-418. 4413873 https://doi.org/10.1109/ICSMC.2007.4413873
Yousri, Noha ; Ismail, Mohammed A. ; Kamel, Mohamed S. / Fuzzy outlier analysis a combined clustering - Outlier detection approach. 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007. 2007. pp. 412-418
@inproceedings{56ded88fa9d544b7b2a0ad3c68c8f2e1,
title = "Fuzzy outlier analysis a combined clustering - Outlier detection approach",
abstract = "Many outlier detection methods identify outliers ignoring any structure in data. However, it is sometimes beneficial to integrate outlierness and a method that groups data, such as clustering. This enhances both outlier and cluster analysis. In this paper, a fuzzy approach is proposed for integrating results from an outlier detection method and a clustering algorithm. A universal set of clusters is proposed which combines clusters obtained from clustering, and a virtual cluster for the outliers. The approach has two phases; the first computes patterns' initial memberships for the outlier cluster, and the second calculates memberships for the universal clusters, using an iterative membership propagation technique. The proposed approach is general and can combine any outlier detection method with any clustering algorithm. Both low and high dimensional data sets are used to illustrate the impact of the proposed approach.",
author = "Noha Yousri and Ismail, {Mohammed A.} and Kamel, {Mohamed S.}",
year = "2007",
month = "12",
day = "1",
doi = "10.1109/ICSMC.2007.4413873",
language = "English",
isbn = "1424409918",
pages = "412--418",
booktitle = "2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007",

}

TY - GEN

T1 - Fuzzy outlier analysis a combined clustering - Outlier detection approach

AU - Yousri, Noha

AU - Ismail, Mohammed A.

AU - Kamel, Mohamed S.

PY - 2007/12/1

Y1 - 2007/12/1

N2 - Many outlier detection methods identify outliers ignoring any structure in data. However, it is sometimes beneficial to integrate outlierness and a method that groups data, such as clustering. This enhances both outlier and cluster analysis. In this paper, a fuzzy approach is proposed for integrating results from an outlier detection method and a clustering algorithm. A universal set of clusters is proposed which combines clusters obtained from clustering, and a virtual cluster for the outliers. The approach has two phases; the first computes patterns' initial memberships for the outlier cluster, and the second calculates memberships for the universal clusters, using an iterative membership propagation technique. The proposed approach is general and can combine any outlier detection method with any clustering algorithm. Both low and high dimensional data sets are used to illustrate the impact of the proposed approach.

AB - Many outlier detection methods identify outliers ignoring any structure in data. However, it is sometimes beneficial to integrate outlierness and a method that groups data, such as clustering. This enhances both outlier and cluster analysis. In this paper, a fuzzy approach is proposed for integrating results from an outlier detection method and a clustering algorithm. A universal set of clusters is proposed which combines clusters obtained from clustering, and a virtual cluster for the outliers. The approach has two phases; the first computes patterns' initial memberships for the outlier cluster, and the second calculates memberships for the universal clusters, using an iterative membership propagation technique. The proposed approach is general and can combine any outlier detection method with any clustering algorithm. Both low and high dimensional data sets are used to illustrate the impact of the proposed approach.

UR - http://www.scopus.com/inward/record.url?scp=40949138456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=40949138456&partnerID=8YFLogxK

U2 - 10.1109/ICSMC.2007.4413873

DO - 10.1109/ICSMC.2007.4413873

M3 - Conference contribution

SN - 1424409918

SN - 9781424409914

SP - 412

EP - 418

BT - 2007 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2007

ER -