Genetic Algorithm-Based High-dimensional Data Clustering Technique
Haojun Sun, Xiong Lang-huan · 2009
A genetic algorithm-based high-dimensional data clustering technique, called GA-HDclustering, is proposed in this paper. This approach searches feature subspace by genetic algorithms to find the effective clustering feature subspaces. The candidate features and cluster centers are binary encoded, and the degree of feature subspace contributes to subspace clustering is proposed as the fitness function. The experimental results indicate the feasibility and efficiency of the GA-HD clustering algorithm.