Similarity measurement and truncation method in chameleon algorithm

Abstract

The invention discloses a similarity measurement and truncation method in a chameleon algorithm, belonging to the technical field of agglomeration type hierarchical clustering algorithms. A chameleonruns on a sparse graph, and nodes represent data items and weighted edges represent similarities between the data items. The chameleon finds out clusters in a dataset through a two-stage algorithm, wherein in the first stage, a k-nearest neighbor graph Gk is constructed according to the dataset, and the data items are divided into several relatively small sub-clusters through a graph partitioningalgorithm; in the second stage, through an algorithm, real clusters are found by repeatedly combining the sub-clusters. The improved algorithm improves a conventional chameleon clustering algorithm byintroducing recursive dichotomy, flood fill and first hop truncation. The invention also provides a method that can automatically select the best clustering result from a modified chameleon tree diagram.

Description

technical field [0001] The invention belongs to the technical field of agglomerative hierarchical clustering algorithms, in particular to similarity measurement and truncation methods in chameleon algorithms. Background technique [0002] Among the clustering algorithms, the ROCK hierarchical clustering algorithm mainly emphasizes the relative interconnectivity between the clusters, so the algorithm ignores the relative proximity between the clusters. Compared with the ROCK algorithm, the CURE hierarchical clustering algorithm emphasizes the clustering The relative proximity between clusters, but ignores the relative interconnectivity between clusters. By comparing the shortcomings of the CURE and ROCK algorithms, relevant personnel have developed a dynamic modeling hierarchical clustering algorithm - Chameleon algorithm, which not only considers The relative interconnectivity and relative proximity between clusters also take into account the internal characteristics of the ...

AI Technical Summary

Problems solved by technology

In the stage of merging and partitioning clusters, the parameter selection of the threshold method is more difficult, and different parameter values ​​have a greater impact on the results; the function method does not completely evaluate the similarity between clusters through the density, and in each iteration it is Least Bisector Between Two Equal Parts of Dependent Hypergraph

Images