An Improved Ant Colony Clustering Algorithm Based on Information Entropy

Cluster analysis is a very important topic in the field of data mining.This paper,on the basis of LF algorithm,uses information entropy to reduce the number of parameters.By introducing some strategies such as radius increase,short-term memory,forced drop,cluster merge,etc.,we make the performance improved.The experiment illustrates that our algorithm will obtain better clustering results and it is quite feasible for data sets with mixed attribute especially for categorical values.