作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (23): 194-196. doi: 10.3969/j.issn.1000-3428.2007.23.067

• 人工智能及识别技术 • 上一篇    下一篇

基于动态粒度的并行人工免疫聚类算法

郝晓丽,谢克明   

  1. (太原理工大学计算机学院,太原 030024)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-12-05 发布日期:2007-12-05

Parallel Artificial Immune Clustering Algorithm Based on Dynamic Granulation

HAO Xiao-li, XIE Ke-ming   

  1. (School of Computer, Taiyuan Technology University, Taiyuan 030024)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-12-05 Published:2007-12-05

摘要: 从粒度的角度讨论了聚类结果和先验知识的协调度问题,提出了一种基于动态粒度的并行免疫聚类算法。鉴于并行人工免疫系统模型具有并行、随机搜索、反复进化和模式多样性等特点,将其与动态粒度模型相结合,在粒度变化过程中,通过对粒度粗化和细化的调整,选择合适粒度,保证了算法的聚类效率和聚类质量。实验证明,该算法在处理多样本、多属性、多类别问题时,是一种有效的方法。

关键词: 动态粒度, 人工免疫, 聚类, 协调度

Abstract: This paper discusses measure of harmony between clustering and transcendent knowledge, and a new clustering algorithm is proposed, which is parallel artificial immune clustering algorithm based on dynamic granulation. Artificial immune system model has the characteristics, such as parallel, random search, and maintains diversity. It is unified to dynamic granulation model. In the process of granulation changing, appropriate granulation can be made by adjusting, which can ensure clustering efficiency and quality of the new algorithm. Test results show that the algorithm is reasonable when the problem is handled, which has many samples, many attributions and many classifications.

Key words: dynamic granulation, artificial immune, clustering, harmony

中图分类号: