Description: K-means clustering algorithm based on the association discovery
To define a network node correlation, and build the node correlation matrix in this basis, given a K-means clustering algorithm based on a complex network of associations that way.
The principle of the minimum correlation to select a new cluster center to the principle of maximum correlation pattern classification until all the nodes are divided until the end, the last under the module to determine the degree of the ideal number of community
To Search:
- [newman] - Daniudi Newman s thesis analyzed the str
- [LFM_2] - Overlapping structure of the complex net
- [A0517] - Complex network of knowledge based netwo
- [OverlappingLinkCommunities] - community detection in complex networks.
File list (Check if you may need any files):
data.txt
k_means.exe
head.h
k_means.cpp