DocumentCode
389671
Title
A novel clustering algorithm based on weighted support and its application
Author
Yang, Xiang-rong ; Shen, Jun-Yi ; Liu, Qiang
Author_Institution
Dept. of Comput. Sci. & Technol., Xi´´an Jiaotong Univ., China
Volume
1
fYear
2002
fDate
2002
Firstpage
95
Abstract
In this paper, we present a novel and efficient algorithm, WeiSC, for clustering categorical data, which is not only accurate but also displays good scalability. It is mainly based on weighted support, which, as defined by us, calculates the similarity between a new tuple and existing clusters. The new tuple is assigned to the cluster with largest similarity. As an example, we apply this algorithm in IDS and perform some research.
Keywords
data mining; database theory; pattern clustering; very large databases; KDD problem; categorical data clustering algorithm; computational complexity; intrusion detection; mushroom dataset; real-life datasets; scalability; tuple; very large databases; weighted support; Algorithm design and analysis; Application software; Clustering algorithms; Computer science; Intrusion detection; Machine learning; Scalability; Spatial databases;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on
Print_ISBN
0-7803-7508-4
Type
conf
DOI
10.1109/ICMLC.2002.1176717
Filename
1176717
Link To Document