摘要
采用密度敏感距离作为数据相似性度量,并基于多智能体进化的思想提出了一种密度敏感的多智能体进化聚类(density sensitive based multi-agent evolutionary clustering,简称DSMAEC)算法.算法设计了一种基于连接的编码方式,通过解码过程可直接得到最终的聚类结果,无需事先确定聚类类别数,有效地克服了对领域知识的依赖.针对聚类问题,设计了3个有效的进化算子来模拟智能体间的竞争、合作和自学习行为,共同完成智能体的进化,最终达到对数据聚类的目的.分别对人工数据集、UCI数据集以及合成纹理图像进行仿真,实验结果表明,该算法不但可以自动确定聚类类别数,而且能够应付不同结构的数据,适应不同的聚类要求,具有较强的实用价值.
By using the density sensitive distance as the similarity measurement, an algorithm of Density Sensitive based Multi-Agent Evolutionary Clustering （DSMAEC）, based on multi-agent evolution, is proposed in this paper. DSMAEC designs a new connection based encoding, and the clustering results can be obtained by the process of decoding directly. It does not require the number of clusters to be known beforehand and overcomes the dependence of the domain knowledge. Aim at solving the clustering problem, three effective evolutionary operators are designed for competition, cooperation, and self-learning of an agent. Some experiments about artificial data, UCI data, and synthetic texture images are tested. These results show that DSMAEC can confirm the number of clusters automatically, tackle the data with different structures, and satisfy the diverse clustering request.
出处
《软件学报》
EI
CSCD
北大核心
2010年第10期2420-2431,共12页
Journal of Software
基金
国家自然科学基金Nos.60703107
60703108
国家高技术研究发展计划(863)No.2006AA01Z107~~
关键词
密度敏感距离
无监督聚类
多智能体进化
k近邻变异
density sensitive distance
unsupervised clustering
multi-agent evolution
k-nearest neighbor mutation
