基于Louvain算法的海上态势生成多目标层次化分群方法

Multi-target Hierarchical Clustering Method for Maritime Situation Generation Based on Louvain Algorithm

目标分群是海上态势生成中态势估计的核心问题之一,针对已有的海战场中目标分群算法的不足,提出了一种基于Louvain算法的多目标层次化分群方法。文中对目标分群问题进行了形式化描述,分析了在执行不同层次分群操作时所应考虑的因素,设计了适当的目标间距离度量标准,给出了层次化分群算法的理论方法及实现流程,并对群参数的更新方法进行了详细说明。最后,通过仿真实验对方法的有效性进行了验证。

Target clustering is a quite important issue in situation assessment.To deal with the shortcomings of the existing target clustering algorithms,a multi-target hierarchical clustering method based on Louvain algorithm is proposed in this paper.Specifically,the problem of target clustering is formalized,then,the factors that should be considered when performing clustering operations at different levels are analyzed,finally,an appropriate distance metric used to measure the distance between targets is designed.The thought and the calculation process of the proposed algorithm are described in detail,and the approach to update the cluster parameters is explained at length.The effectiveness of the method is verified by simulation experiments.