SLOM

A new measure for local spatial outliers

Sanjay Chawla, Pei Sun

Research output: Contribution to journalArticle

69 Citations (Scopus)

Abstract

We propose a measure, spatial local outlier measure (SLOM), which captures the local behaviour of datum in their spatial neighbourhood. With the help of SLOM, we are able to discern local spatial outliers that are usually missed by global techniques, like "three standard deviations away from the mean". Furthermore, the measure takes into account the local stability around a data point and suppresses the reporting of outliers in highly unstable areas, where data are too heterogeneous and the notion of outliers is not meaningful. We prove several properties of SLOM and report experiments on synthetic and real data sets that show that our approach is novel and scalable to large datasets.

Original languageEnglish
Pages (from-to)412-429
Number of pages18
JournalKnowledge and Information Systems
Volume9
Issue number4
DOIs
Publication statusPublished - Apr 2006
Externally publishedYes

Fingerprint

Experiments

Keywords

  • Complexity
  • Oscillating parameter
  • R-trees index
  • Spatial local outlier
  • Spatial neighbourhood

ASJC Scopus subject areas

  • Information Systems

Cite this

SLOM : A new measure for local spatial outliers. / Chawla, Sanjay; Sun, Pei.

In: Knowledge and Information Systems, Vol. 9, No. 4, 04.2006, p. 412-429.

Research output: Contribution to journalArticle

@article{1e23971d82cf483e883bf4fa3ad75f0d,
title = "SLOM: A new measure for local spatial outliers",
abstract = "We propose a measure, spatial local outlier measure (SLOM), which captures the local behaviour of datum in their spatial neighbourhood. With the help of SLOM, we are able to discern local spatial outliers that are usually missed by global techniques, like {"}three standard deviations away from the mean{"}. Furthermore, the measure takes into account the local stability around a data point and suppresses the reporting of outliers in highly unstable areas, where data are too heterogeneous and the notion of outliers is not meaningful. We prove several properties of SLOM and report experiments on synthetic and real data sets that show that our approach is novel and scalable to large datasets.",
keywords = "Complexity, Oscillating parameter, R-trees index, Spatial local outlier, Spatial neighbourhood",
author = "Sanjay Chawla and Pei Sun",
year = "2006",
month = "4",
doi = "10.1007/s10115-005-0200-2",
language = "English",
volume = "9",
pages = "412--429",
journal = "Knowledge and Information Systems",
issn = "0219-1377",
publisher = "Springer London",
number = "4",

}

TY - JOUR

T1 - SLOM

T2 - A new measure for local spatial outliers

AU - Chawla, Sanjay

AU - Sun, Pei

PY - 2006/4

Y1 - 2006/4

N2 - We propose a measure, spatial local outlier measure (SLOM), which captures the local behaviour of datum in their spatial neighbourhood. With the help of SLOM, we are able to discern local spatial outliers that are usually missed by global techniques, like "three standard deviations away from the mean". Furthermore, the measure takes into account the local stability around a data point and suppresses the reporting of outliers in highly unstable areas, where data are too heterogeneous and the notion of outliers is not meaningful. We prove several properties of SLOM and report experiments on synthetic and real data sets that show that our approach is novel and scalable to large datasets.

AB - We propose a measure, spatial local outlier measure (SLOM), which captures the local behaviour of datum in their spatial neighbourhood. With the help of SLOM, we are able to discern local spatial outliers that are usually missed by global techniques, like "three standard deviations away from the mean". Furthermore, the measure takes into account the local stability around a data point and suppresses the reporting of outliers in highly unstable areas, where data are too heterogeneous and the notion of outliers is not meaningful. We prove several properties of SLOM and report experiments on synthetic and real data sets that show that our approach is novel and scalable to large datasets.

KW - Complexity

KW - Oscillating parameter

KW - R-trees index

KW - Spatial local outlier

KW - Spatial neighbourhood

UR - http://www.scopus.com/inward/record.url?scp=33645548899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33645548899&partnerID=8YFLogxK

U2 - 10.1007/s10115-005-0200-2

DO - 10.1007/s10115-005-0200-2

M3 - Article

VL - 9

SP - 412

EP - 429

JO - Knowledge and Information Systems

JF - Knowledge and Information Systems

SN - 0219-1377

IS - 4

ER -