HGHD:An Algorithm for Clustering Data in High Dimensional Space Based on Hypergraph
Yingxin Hu · Microelectronics & Computer · 2006
Most of the traditional algorithms fail to produce meaningful clusters in high dimension space data sets.Therefore, a method is proposed for clustering data in high dimensiona1 space. It maps the data and the relationship in the data into a hypergraph, cluster data by parting this hypergraph , the problem of solving the data clustering in high dimensional space is formu1ated as a hypergraph optimal partition problem. One of the major advantages of this scheme over traditional clustering schemes is that it does not require dimensionality reduction. It uses the hypergraph model to represent relations among the original data items. It can produce high quality cluster effectively.