基于移动代理的层次优化挖掘模型

对于大规模分布式数据挖掘问题,提出一种基于移动代理的层次结构挖掘模型,该模型对OIKI DDM模型进行扩展,利用层次设计思想,基于移动代理和增量优化技术进行挖掘和增量集成。实验结果表明该模型对于数据站点大小具有更好的伸缩性,实现更加灵活,可根据网络特点有效降低通讯代价,特别适合于大规模分布式环境。

A New Hierarchical Optimization Model Based on Mobile Agent for Distributed Data Mining

For large-scale distributed data sets, a new hierarchical mining model based on mobile agent is proposed to perform distributed mining tasks. Based on hierarchical idea, the proposed approach integrates multiple local results using mobile agent and incremental optimization. The experimental results demonstrate that the proposed approach is scalable and particularly suited to large-scale distributed environments. In addition, the proposed model can reduce dramatically communication cost based on network characteristics.