A novel ant colony optimization algorithm for clustering

Clustering Analysis is one kind of pattern recognition that not to be supervised. The Clustering algorithm based on object function resolves the clustering problem into optimization problem, thereby it becomes to the main investigatory stream nowadays. But it has some shortcomings such as its sensitivity to initial condition, and it is easy to fall in local peak To overcome these deficiencies, ant colony optimization algorithm is applied to clustering analysis and a novel clustering based on an improved ant colony optimization algorithm is proposed. Theoretical analysis and experiments show this method is faster and more efficient to convergence upon the optimal value in the whole field.