Discovering cluster-based local outliers

Zengyou He; Xiaofei Xu; Shengchun Deng

doi:10.1016/S0167-8655(03)00003-5

Discovering cluster-based local outliers

Zengyou He^*
, Xiaofei Xu
, Shengchun Deng

^*Corresponding author for this work

Faculty of Computing

Harbin Institute of Technology

Research output: Contribution to journal › Article › peer-review

956 Scopus citations

Abstract

In this paper, we present a new definition for outlier: Cluster-based local outlier , which is meaningful and provides importance to the local data behavior. A measure for identifying the physical significance of an outlier is designed, which is called cluster-based local outlier factor (CBLOF). We also propose the Find CBLOF algorithm for discovering outliers. The experimental results show that our approach outperformed the existing methods on identifying meaningful and interesting outliers.

Original language	English
Pages (from-to)	1641-1650
Number of pages	10
Journal	Pattern Recognition Letters
Volume	24
Issue number	9-10
DOIs	https://doi.org/10.1016/S0167-8655(03)00003-5
State	Published - Jun 2003

Keywords

Clustering
Data mining
Outlier detection

Access to Document

10.1016/S0167-8655(03)00003-5

Cite this

@article{ccaad9b9a6dc4d108b3ae7c6875ee0e6,

title = "Discovering cluster-based local outliers",

abstract = "In this paper, we present a new definition for outlier: Cluster-based local outlier , which is meaningful and provides importance to the local data behavior. A measure for identifying the physical significance of an outlier is designed, which is called cluster-based local outlier factor (CBLOF). We also propose the Find CBLOF algorithm for discovering outliers. The experimental results show that our approach outperformed the existing methods on identifying meaningful and interesting outliers.",

keywords = "Clustering, Data mining, Outlier detection",

author = "Zengyou He and Xiaofei Xu and Shengchun Deng",

year = "2003",

month = jun,

doi = "10.1016/S0167-8655(03)00003-5",

language = "英语",

volume = "24",

pages = "1641--1650",

journal = "Pattern Recognition Letters",

issn = "0167-8655",

publisher = "Elsevier B.V.",

number = "9-10",

}

TY - JOUR

T1 - Discovering cluster-based local outliers

AU - He, Zengyou

AU - Xu, Xiaofei

AU - Deng, Shengchun

PY - 2003/6

Y1 - 2003/6

N2 - In this paper, we present a new definition for outlier: Cluster-based local outlier , which is meaningful and provides importance to the local data behavior. A measure for identifying the physical significance of an outlier is designed, which is called cluster-based local outlier factor (CBLOF). We also propose the Find CBLOF algorithm for discovering outliers. The experimental results show that our approach outperformed the existing methods on identifying meaningful and interesting outliers.

AB - In this paper, we present a new definition for outlier: Cluster-based local outlier , which is meaningful and provides importance to the local data behavior. A measure for identifying the physical significance of an outlier is designed, which is called cluster-based local outlier factor (CBLOF). We also propose the Find CBLOF algorithm for discovering outliers. The experimental results show that our approach outperformed the existing methods on identifying meaningful and interesting outliers.

KW - Clustering

KW - Data mining

KW - Outlier detection

UR - https://www.scopus.com/pages/publications/0037410488

U2 - 10.1016/S0167-8655(03)00003-5

DO - 10.1016/S0167-8655(03)00003-5

M3 - 文章

AN - SCOPUS:0037410488

SN - 0167-8655

VL - 24

SP - 1641

EP - 1650

JO - Pattern Recognition Letters

JF - Pattern Recognition Letters

IS - 9-10

ER -

Discovering cluster-based local outliers

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this