基于动态粒度的并行人工免疫聚类算法  

Parallel Artificial Immune Clustering Algorithm Based on Dynamic Granulation

作　　者：郝晓丽[1] 谢克明[1] 

机构地区：[1]太原理工大学计算机学院,太原030024

出　　处：《计算机工程》2007年第23期194-196,共3页Computer Engineering

基　　金：国家自然科学基金资助项目(60374029);国家高等学校博士学科点专项科研基金资助项目(20060112005);山西省留学人员基金资助项目(2004-18)

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。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.

关 键 词：动态粒度 人工免疫 聚类 协调度 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]