Current Issue Cover


摘 要
目的 平行坐标是经典的多维数据可视化方法,在其用于地理空间多维数据分析过程中,往往存在空间位置信息缺失,空间关联分析不确定等问题。因此,本文拟设计一种有效关联平行坐标和地图的地理空间多维数据可视分析方法。方法 根据多维属性信息对地理空间位置进行聚类分析,引入Voronoi图和颜色映射对地理空间各类区域进行显著标识。利用平行坐标呈现地理空间多维属性信息,引入互信息度量地理空间聚类与属性类别的相关性,动态地确定平行坐标轴排列顺序。进一步计算属性轴与地图之间数据线的绑定位置,对数据线的布局进行优化处理,降低地图与平行坐标系间数据线分布的紊乱程度。结果 有效集成上述可视化设计及数据分析方法,设计与实现一种基于平行坐标轴动态排列的地理空间多维数据可视化分析系统,提供便捷的用户交互模式,通过2组具有明显地理空间多维属性特征的数据进行测试,验证了本文可视分析方法的有效性和实用性。结论 所提出的可视分析方法和工具可以帮助用户快速地分析地理空间多维属性存在的空间分布特征及其关联模式,为地理空间多维数据的探索提供了有效手段。
Visual analysis of geospatial multi-dimensional data via dynamically arrangement of parallel coordinates

Zhou ZhiGuang,Yu JiaJun,Guo ZhiYong,Liu YuHua(School of Information,Zhejiang University of Finance and Economics)

Geospatial multi-dimensional data is mainly composed of spatial location and attribute information, which can effectively record and describe events and phenomena such as social and economic development, natural environment changes, and human social activities. As a commonly-used method for multi-dimensional data visualization, parallel coordinates do not work well for the visual exploration of geospatial multi-dimensional data, because of the lack of spatial information and uncertainty of spatial correlation. Therefore, it is of great significance for the analysis and understanding of geospatial multidimensional data to establish an effective association between spatial locations and multiple attributes. In this paper, we propose a novel geospatial multi-dimensional data visualization method, which uses geographical map to display spatial locations, visualizes multi-dimensional attributes by means of parallel coordinates, and associates map and parallel coordinates through data lines. We design a corresponding visual analysis system, allowing users to interactively explore and analyze the spatial distribution of geospatial multi-dimensional data and its associated feature patterns, based on the initial geospatial multi-dimensional data, including different spatial locations and their corresponding multi-dimensional attribute information. Spatial areas are classified into different clusters according to multi-dimensional attributes and spatial distance, and the Voronoi diagrams and color mappings are designed to visually represent different clusters. The attribute information of the geospatial multi-dimensional data is represented by parallel coordinates, and the data on different attribute axes is clustered and analyzed. The mutual information is used to dynamically calculate the correlation between the geospatial clustering and the attribute categories, and the ordering of the parallel coordinate plot is adaptively determined. Then, the map is embedded into the parallel coordinates based on the above axis alignment results, and the map view and parallel coordinate systems are effectively correlated through data lines. Furthermore, the binding position of the data line between the attribute axis and the map is dynamically calculated according to the geospatial clustering, and the layout of the data line is optimized to reduce the disorder of the data line distribution between the map and the parallel coordinate system. We design and implement a geospatial multi-dimensional data visualization analysis system with the above visual designs and data analysis methods integrated. A convenient user interaction mode is provided, and two case studies are conducted based on the datasets with multi-dimensional geospatial attributes, to demonstrate the validity and practicability of the proposed visual analysis system. The GDP data containing 11 attributes and 32 spatial locations is visualized based on our visual analysis system. Comparing the geospatial clustering and the actual urban development in the map view, it is proved that the geospatial clustering algorithm which comprehensively considers the data attribute information and spatial locations information proposed in this paper is useful. By observing the arrangement of parallel axes, it is verified that there is certain rationality in the dynamic arrangement of parallel axes based on mutual information. In the second case based on geospatial multi-dimensional data, we mainly explore the spatial distribution of the attribute information in a certain spatial cluster. When the user clicks on a geospatial clustering of interest, the system will rearrange the parallel coordinate axes. By comparing the distribution of attributes of the same geospatial clustering on different times, we find that the proposed method is more sensitive to data. When the data changes slightly, the order of parallel axis will change, making the map embedded parallel coordinates better match the spatial distribution of multi-dimensional attribute information. We further invite experts from different fields such as geography and economy to use and evaluate the system. The validity and practicability of the geospatial multidimensional data visual analysis system is further verified by one-on-one interviews. Through a set of case studies and expert feedbacks, it is shown that the visual analysis methods and tools proposed in this paper can help users to quickly analyze the spatial distribution characteristics and associated patterns of geospatial multi-dimensional attributes, and provide domain experts with an effective means for the exploration of geospatial multi-dimensional data.