平行坐标系捆绑技术的评价
Evaluation of a Bundling Technique for Parallel Coordinates
摘要:
我们描述了一种技术,捆绑曲线表示在平行坐标图,并提出了一个控制用户研究评估其有效性。用C^1连续的分段贝塞尔曲线代替传统的C^0折线,可以更容易地通过每个坐标轴直观地跟踪数据点。然后可以将得到的Bezier曲线捆绑起来,以可视化具有给定聚类结构的数据。曲线束计算效率高,提供数据集群之间的视觉分离,减少视觉混乱,并提供更清晰的数据集概览。一项有14名参与者的受控用户研究证实了曲线捆绑对于平行坐标可视化的有效性:1)与多边形线相比,它同样能够揭示相邻数据属性之间的相关性; 2)其几何线索可以有效地显示聚类信息。对于某些数据集,曲线捆绑允许将颜色感知通道应用于其他数据属性,而对于复杂的聚类模式,捆绑和颜色可以比单独使用更清楚地表示聚类。
英文摘要:
We describe a technique for bundled curve representations in parallel-coordinates plots and present a controlled user study evaluating their effectiveness. Replacing the traditional C^0 polygonal lines by C^1 continuous piecewise Bezier curves makes it easier to visually trace data points through each coordinate axis. The resulting Bezier curves can then be bundled to visualize data with given cluster structures. Curve bundles are efficient to compute, provide visual separation between data clusters, reduce visual clutter, and present a clearer overview of the dataset. A controlled user study with 14 participants confirmed the effectiveness of curve bundling for parallel-coordinates visualization: 1) compared to polygonal lines, it is equally capable of revealing correlations between neighboring data attributes; 2) its geometric cues can be effective in displaying cluster information. For some datasets curve bundling allows the color perceptual channel to be applied to other data attributes, while for complex cluster patterns, bundling and color can represent clustering far more clearly than either alone.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。