基于遗传算法的自适应文本模糊聚类研究  

Research on Adaptive Text Fuzzy Clustering Based on Genetic Algorithm

作　　者：戴文华[1] 焦翠珍[1] 何婷婷[2] 

机构地区：[1]咸宁学院计算机系,咸宁437100 [2]华中师范大学计算机科学系,武汉430079

出　　处：《计算机科学》2008年第8期134-137,共4页Computer Science

基　　金：国家自然科学基金(No.60442005,No.60673040);国家社会科学基金(No.06BYY029);教育部重点研究项目(No.105117);湖北省教育厅科研重点项目(No.D200728002)

摘　　要：针对FCM聚类算法对初始聚类中心的选择敏感,以及聚类数C难以确定的问题,提出一种基于遗传算法的自适应文本模糊聚类方法。该方法首先将文档集合表示成向量空间模型,并采用一种新型的可变长染色体编码方案,随机选择文本向量作为初始聚类中心形成染色体,然后结合FCM算法的高效性和遗传算法的全局优化能力,通过遗传进化,有效地避免了局部最优解的出现,同时得到了优化的聚类数目和聚类结果。实验表明该算法是一种精确高效的文本聚类方法。As Fuzzy C-means Clustering Algorithm was sensitive to the choice of the initial cluster centers and it＇s difficult to determine the cluster number, we proposed an Adaptive Text Fuzzy Clustering Method Based on Genetic Algorithm. According to the principle of Vector Space Model, documents were represented as vectors. Then we adopted a new strategy of variablelength chromosome encoding and randomly chose initial clustering centers to form chromosomes among document vectors. Combining the dficiency of Fuzzy C-means Algorithm with the global optimization ability of Genetic Algorithm, the local optimal solution was avoided and the optimum number and the optimum result of cluster were obtained by means of genetic evolution. Experiments indicated that this algorithm was efficient and accurate.

关 键 词：遗传算法 FCM聚类 文本聚类 模糊聚类 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置] P618.130.8[自动化与计算机技术—控制科学与工程]