一种改进的人工免疫文本聚类算法  

Document Clustering Algorithm Based on Improved Artificial Immune System

作　　者：童健华[1] 谭洪舟[1] 郭雷勇[1] 

机构地区：[1]中山大学电子系,广州510275

出　　处：《系统仿真学报》2010年第1期29-32,共4页Journal of System Simulation

基　　金：国家自然科学基金(60575006)

摘　　要：构造了一种能准确描述文本之间相似性(亲和力)的新方法,并在此基础上提出了一种改进的人工免疫文本聚类算法。仿真结果表明,与传统的文本聚类算法相比,新算法不仅能自动发现新类,而且具有聚类精度更高、数据压缩比更大、与输入初始配置无关、可增量处理的优势。A new method which could accurately compute the affinity between documents was proposed. By using the method, a document clustering algorithm based on improved artificial immune system was proposed. Simulation results show that new algorithm can not only locate new clusters automatically, but has the advantage of being independent of the input initialization and the incremental clustering ability as well, where it has better clustering quality and higher data compression rate rather than some current document clustering algorithms.

关 键 词：抗体 亲和力计算 人工免疫网络 文本聚类 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]