基于蚁群和模拟退火算法的聚类新方法  

Clustering Algorithm Based on Hybrid Intelligent Algorithm

作　　者：陶红[1] 史小伍[1] 李莎[1] 高尚[1] 

机构地区：[1]江苏科技大学计算机科学与工程学院,江苏镇江212003

出　　处：《微电子学与计算机》2011年第12期96-98,共3页Microelectronics & Computer

基　　金：人工智能四川省重点实验室开放基金(2009RY001);"青蓝工程"

摘　　要：模拟退火算法具有良好的全局搜索能力,而蚁群算法具有良好的分布式并行性和正反馈能力.针对样本维数大、数目多时聚类效果不满意的问题,提出了混合的蚁群模拟退火算法,思路是利用K-均值算法的结果作为初值,再使用蚁群算法和模拟退火算法对初值进行调整聚类,结果表明这种算法比较有效.Simulated annealing algorithm has the ability of doing a global stochastically,and ant colony algorithm has the ability of distributed parallel processing and good feedback.Due to the problem that when the dimension and the number of the sample are large,the cluster result will be unsatisfied,a hybrid intelligent algorithm is proposed.The algorithm is extend to use K-Means clustering to seed the initial solution and the ant colony algorithm and simulated annealing algorithm to adjust the initial cluster.Through the result,the more effectiveness of this algorithm is illustrated.

关 键 词：聚类分析 K-均值算法 蚁群算法 模拟退火算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]