|Table of Contents|

An Algorithm for GML Point Outlier Detection Based on Space Adjacent Relations(PDF)

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

Issue:
2009年01期
Page:
61-63
Research Field:
Publishing date:

Info

Title:
An Algorithm for GML Point Outlier Detection Based on Space Adjacent Relations
Author(s):
Chen Jiachun1; 2; Ji Genlin1; 2
1.School of Mathematics and Computer Science,Nanjing Normal University,Nanjing 210097,China;2.Key Laboratory of Virtual Geographic Environment,Ministry of Education,Nanjing Normal University,Nanjing 210097,China
Keywords:
outlier detec tion;  space ad jacent re lations;  GML da tam in ing
PACS:
TP311.13
DOI:
-
Abstract:
A t present algorithm fo rGM L outlier de tection has se ldom been researched. A lgor ithm SAOD for GML po int outlier de tection based on space ad jacent re la tions is propo sed in th is paper. In th is a lgor ithm, the space adjacen t relations be tw een spatia l po ints are considered as the sim ilar itym easurem ent and sim ilar itym atrix is computed. The expected outliers can be ob tained from the m atr ix. The resu lts o f experim ents show that a lgor ithm SAOD is effec tive and eff-i c ient.

References:

[ 1] Barnett V, Lew is T. Outliers in S tatistical Data[M ]. New Yo rk: JohnW iley& Sons, 1994: 194-223.
[ 2] Knorr EM, Ng R T. A lgo rithm s fo rm in ing distance-based outliers in larg e da tasets[ C] / /Proc of 1998 Internationa l Conference. Very Large Da ta Base ( VLDB98) . New Yo rk: VLDB Endowm ent, 1998: 392-403.
[ 3] BreunigM M, KruegerH P, Ng R, et a.l LOF: identify ing density-based local outliers[ C ] / /Proc o f ACM SIGMOD2000 Internationa l Con ference onM anagem ent of Da ta. Da llas, Texas: ACM Press, 2000: 93-104.
[ 4] Knorr EM, Ng R T. A un ified notion o f outliers: properties and computation[ C] / /Proc the 3rd Inte rnational Confe rence on Know ledg e Discovery and Da taM ining. Ca lifo rnia: IEEE Press, 1997: 219-222.

Memo

Memo:
-
Last Update: 2013-04-23