Title :
Enhancements on local outlier detection
Author :
Chiu, Anny Lai-Mei ; Fu, Ada Wai-Chee
Author_Institution :
Dept. of Comput. Sci. & Eng., Chinese Univ. of Hong Kong, China
Abstract :
Outliers, commonly referred to as exceptional cases, exist in many real-world databases. Detection of such outliers is important for many applications. In this paper, we focus on the density-based notion that discovers local outliers by means of the local outlier factor (LOF) formulation. Three enhancement schemes over LOF are introduced, namely LOF\´ and LOF" and GridLOF. Thorough explanation and analysis is given to demonstrate the abilities of LOF\´ in providing simpler and more intuitive meaning of local outlier-ness; LOF" in handling cases where LOF fails to work appropriately; and GridLOF in improving the efficiency and accuracy.
Keywords :
data mining; database management systems; expert systems; inference mechanisms; GridLOF; KDD; LOF accuracy improvement; LOF efficiency improvement; LOF failure; LOF formulation; LOF"; LOF\´; density-based notion; exceptional case; intuitive local outlierness; knowledge discovery in databases; local outlier detection enhancement; local outlier discovery; local outlier factor; Application software; Clustering algorithms; Computer science; Credit cards; Data engineering; Databases; Failure analysis; Optical noise; Statistical distributions; Telecommunications;
Conference_Titel :
Database Engineering and Applications Symposium, 2003. Proceedings. Seventh International
Print_ISBN :
0-7695-1981-4
DOI :
10.1109/IDEAS.2003.1214939
