空间点群目标权重的可视化表达方法

Visualization of the Target Weight of Point Group

权重是点群选取的重要依据,它反映了点要素在点群中的重要性程度.针对现有的相关算法对点群权重信息顾及不足及计算缺乏科学依据等问题,提出了一种点群目标权重的计算与可视化表达方法.该方法的基本思路:1)选取影响范围与影响人群作为点群权重的衡量指标;2)利用新浪微博数据分析并获取点群的影响范围与影响人群数据;3)利用群组目标约束Delaunay三角剖分、动态阈值"剥皮"算法及聚类算法等对点群的影响范围及影响人群进行处理与可视化表达.实验表明:算法对点群权重进行了合理的计算与可视化表达,能够解决多种类型点群的权重的计算及表达问题,且得到的点群权重具有较高的现势性.同时,算法较好地克服了传统算法中点群权重受局部密度影响较大的缺陷.

The weight of the point is a key factor that should be considered in the process of point selection as it reflects the importance of a point in point groups.Aiming at the problems of insufficient information of point group weight and lack of scientific basis in existing algorithms,a method for calculating and visualizing the target weight of point group was proposed.The basic ideas of the method are：1）First,set the factors（i.e.influenced region and affected population）as the weighting index of points＇ weight;2）Use the data obtained from Sina Weibo to analyze and achieve the influence range of point group and the data of affected population;3）Use Delaunay triangulation,dynamic threshold ＂peeling＂ algorithm and clustering algorithm to process and visualize the influence range and the affected population.Experiments show that the algorithm calculates and represents the weight of the point reasonably,it can resolve the problem of calculation and representation of the weights of different kinds of point groups,and the weights of the point groups can be updated with time going on.In addition,the algorithm overcomes the defect that the weight of the point group is greatly influenced by the local density in the traditional algorithm.