期刊
INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING
卷 4, 期 2, 页码 251-262出版社
WORLD SCIENTIFIC PUBL CO PTE LTD
DOI: 10.1142/S0219622005001507
关键词
outlier detection; clustering; complete spatial randomness; knowledge discovery
Outlier detection targets those exceptional data whose pattern is rare and lie in low density regions. In this paper, under the assumption of complete spatial randomness inside clusters, we propose an MDV (Multi-scale Deviation of the Volume) approach to identifying outliers. In addition to assigning an outlier score for each object, it directly outputs a crisp outlier set. It also offers a plot showing the data structure in every object's vicinity, which is useful in explaining why it may be outlying. Finally, the effectiveness of MDV is demonstrated with both artificial and real datasets.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据