Title :
A New Algorithm for Outlier Detection Based on Offset
Author :
Zhang, Yue ; Liu, Jie ; Song, Bo
Author_Institution :
Software Coll., Shenyang Normal Univ., Shenyang, China
Abstract :
Outlier detection is a hot topic of data mining. After studying the existing classical algorithm of detecting outliers, this paper proposes a new algorithm for outlier detection based on offset, and makes a new definition for outlier. This detection algorithm is a method based on clustering analysis. It includes cluster modeling and data detection. Also, the clustering result obtained together with detecting outliers. The experiment results on IRIS show that this algorithm can detect outliers effectively.
Keywords :
data mining; pattern clustering; statistical analysis; clustering analysis; data detection; data mining; outlier detection algorithm; standard deviation; Algorithm design and analysis; Clustering algorithms; Data mining; Detection algorithms; Iris; Clustering; Mathematical expectation; Offset; Outlier; Standard deviation;
Conference_Titel :
Information Assurance and Security, 2009. IAS '09. Fifth International Conference on
Conference_Location :
Xian
Print_ISBN :
978-0-7695-3744-3
DOI :
10.1109/IAS.2009.142
