TVBRT:一种基于Radial Tree的具有度量属性的多变元时态数据可视化方法  

TVBRT:A Time-varying Multivariate Data Visualization Method Based on Radial Tree

作　　者：孙宁伟[1] 赵瑜[1] 刘勇[1] 刘海峰[1] 肖卫东[2] 张翀[2] 

机构地区：[1]中国人民解放军91655部队 [2]国防科技大学信息系统工程重点实验室

出　　处：《计算机科学》2014年第6期5-11,17,共8页Computer Science

摘　　要：多变元时态数据大量存在于社会科学、环境监测、金融经济、医疗卫生及地理信息等领域。对多变元时态数据集进行深入分析,创新性地将经典的层次数据可视化方法Radial Tree加以改进,提出集成度量属性的Radial Tree布局算法(LAMPRT)、基于Radial Tree的具有度量属性的多变元时态数据可视化布局算法(LOVEBRT),结合相应的人机交互策略,形成可视化方法TVBRT。案例研究证明了该方法的有效性,并表明它能展示数据集中的细节内容。TVBRT方法侧重于对数据进行层次分析,适合于展示对具体度量值更为关心的数据集。The areas of social science,environmental monitoring,financial and economic,health and geographic information have generated a large amount of time-varying multivariate data.With a depth analysis of the time-varying multivariate datasets,we proposed a layout algorithm for Radial Tree integrated metric properties called LAMPRT to demonstrate metric properties.And then,we proposed another layout algorithm called LOVEBRT to exhibit the time-varying feature.These two algorithms and some human-computer interaction techniques both form the visualization method TVBRT.Case studies demonstrate the effectiveness of this method,showing that the method is more effective in exhibiting more details of the datasets.TVBRT outperforms over other methods in exhibiting data in a hierarchical and more accurate way.

关 键 词：信息可视化 时态 多变元数据 度量属性 RADIAL Tree 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]