Research on semi supervised K-means clustering algorithm in data mining

K-means clustering has become an important tool for the analysis of gene expression data, which can also look for the expression of cluster with the same fluctuation from two directions of genes and conditions. But the K-means clustering is a multi-objective local search algorithm, which is easy to fall into local optimum when dealing with complex data of the gene. In order to improve the global search capability of the algorithm, this paper presents a semi supervised K clustering algorithm. Firstly, the K—means clustering algorithm is used to deal with gene data. Then the improved semi supervised K mean clustering is used for the greedy iteration to find the K mean clustering, so as to achieve better results. Through the simulation experiment, the results prove the global semi supervised K clustering algorithm has better optimization ability and better cluster effect compared with MDO algorithm.