Title :
Discovering Local Outlier Based on Rough Clustering
Author_Institution :
Inf. Eng. Sch., Lanzhou Commercial Coll., Lanzhou, China
Abstract :
The density at a data point is defined based on kernel function. And we introduce weight to refine rough k-means algorithm. Then we construct the formula for calculating local outlier score based on the clusters generated by the refined rough k-means algorithm. We use a synthetic data set and a real-world data set to verify that the new technique for local outliers detection is not only accurate but also efficient.
Keywords :
data mining; pattern clustering; statistical analysis; kernel function; local outlier discovery; rough clustering; rough k-means algorithm; Algorithm design and analysis; Approximation algorithms; Approximation methods; Clustering algorithms; Data mining; Kernel; Rough sets;
Conference_Titel :
Intelligent Systems and Applications (ISA), 2011 3rd International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-9855-0
Electronic_ISBN :
978-1-4244-9857-4
DOI :
10.1109/ISA.2011.5873272
