DocumentCode :
3424290
Title :
MLOD: Multi-granularity local outlier detection
Author :
Gao, Liang ; Yu, Shao-Yue ; Luo, Yu-Pan ; Shang, Lin
Author_Institution :
Nat. Lab. for Novel Software Technol., Nanjing Univ., Nanjing, China
fYear :
2009
fDate :
17-19 Aug. 2009
Firstpage :
171
Lastpage :
175
Abstract :
Outlier detection is an important data mining task, LOF(local outlier factor) was proposed to indicate the degree of outlierness, which is practical for finding local outliers. However, it is difficult to decide the neighborhood size. In this paper a multi-granularity local outlier detection(MLOD) method is proposed to organize the outlierness under multi-granularity. It finds local outliers in varying neighborhood granularity. This method applies approximation as well as grid-based partition to reduce time complexity. The theoretical results show that the time cost is linear to the size of data sets. Furthermore, the provided output and analysis can also assist users to choose the appropriate parameters. The performance of the algorithm is presented by experimenting on three generated data sets.
Keywords :
approximation theory; computational complexity; data mining; data mining task; grid-based partition; multi-granularity local outlier detection; Algorithm design and analysis; Costs; Data mining; Detection algorithms; Face detection; Indium phosphide; Laboratories; Object detection; Partitioning algorithms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Granular Computing, 2009, GRC '09. IEEE International Conference on
Conference_Location :
Nanchang
Print_ISBN :
978-1-4244-4830-2
Type :
conf
DOI :
10.1109/GRC.2009.5255138
Filename :
5255138
Link To Document :
بازگشت