Sequence clustering algorithm based on weighted vector identification

Di Wu

doi:10.1007/s13042-015-0381-2

2015-06-03

PRE

DOI：10.1007/s13042-015-0381-2

原文链接

原文求助

摘要

En 中文

Sequence clustering has become an important topic that experts in data mining are currently investigating. However, clustering quality is typically significantly affected by both the selection of initial centers and the mean sequences. In this study, the sequence clustering algorithm based on weighted vector identification (SCAWVI) algorithm is developed based on sequence element composite similarity and the weight of a sequence in its corresponding cluster. Based on the weighted sequence element, all sequences in the sequence database are preprocessed into M-dimensional weighted vector identifications. Then, using Huffman-based initial clustering centers optimization algorithm, the initial clustering centers are optimized. In addition, the weighted vector identification and the weight of a sequence in its corresponding cluster are used to update the clustering centers. The theoretical experimental results and the analysis results in this study show that the SCAWVI algorithm has a higher rate of accurate results in its clustering results and higher execution efficiency.

Keyword:

Sequence clustering

Huffman

Weighted vector

Similarity