An Outlier Mining Algorithm Based on Dissimilarity

被引：0

作者：

Zhou, Ming-jian ^{[1
]}

Chen, Xue-jiao ^{[2
]}

机构：

[1] Nanchang Univ, Dept Comp Sci & Technol, Nanchang 330031, Jiangxi, Peoples R China

[2] Gannan Med Univ, Lib Gannan Med Univ, Ganzhou 341000, Jiangxi, Peoples R China

来源：

2011 INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND NEURAL COMPUTING (FSNC 2011), VOL II | 2011年

关键词：

outlier; dissimilarity; data mining; algorithm;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Outlier mining is a hot topic of data mining. After studying the commonly used outlier mining methods, this paper presents an outlier mining algorithm OMABD(Outlier Mining Algorithm Base on Dissimilarity) based on dissimilarity. The algorithm first constructs dissimilarity matrix based on object dissimilarity of each object of data set, then makes the dissimilarity degree of each object according to the dissimilarity matrix, and finally outlier will be detected by comparing the dissimilarity degree with dissimilarity threshold. The experiment results show that this algorithm can detect outlier efficiently.

引用

页码：289 / 291

页数：3

共 14 条

[1] AMING A, 1996, P 2 INT C KNOWL DISC, P164
[2] [Anonymous], 1980, IDENTIFICATION OUTLI, DOI DOI 10.1007/978-94-015-3994-4
[3] BARNET V, 1994, OUTLIERS STAT DATA
[4] Bay S.D, 2003, KDD 03, P29, DOI [10.1145/956750.956758, DOI 10.1145/956750.956758]
[5] Blake C.L., UCI Machine Learning Databases
[6] Breunig M, 2000, P ACM SIGMOD C DALL, P94
[7] He ZY, 2006, LECT NOTES ARTIF INT, V3918, P567
[8] Knorr EM, 1999, PROCEEDINGS OF THE TWENTY-FIFTH INTERNATIONAL CONFERENCE ON VERY LARGE DATA BASES, P211
[9] Mao Junguo, 2007, DATA MINING PRINCIPL
[10] Romaswany S, 2000, PROC OF THE ACM SIGM, P473

← 1 2 →