Visual and analytical extensions for the table lens
Visual and analytical extensions for the table lens
复制标题
台式镜头的视觉和分析扩展
DOI：
10.1117/12.766440
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
H. Schumann
中科院分区：
文献类型：
--
作者：
Mathias John;C. Tominski;H. Schumann
许多可视化方法告诉我们，易用性是有效的可视化数据分析的关键。Table Lens是一个简单而富有表现力的视觉方法的绝佳例子，它可以帮助分析更大量的数据。在这项工作中，我们提出了原始表镜头方法的两个扩展。特别地，我们通过双色伪着色（TTPC）和混合聚类对表透镜进行了扩展。通过将TTPC集成到表透镜中，我们获得了可以在保持精度的同时传达更大量数据的视觉表示。其次，我们提出集成一个数据分析步骤，实现基于自组织映射和分层聚类的混合聚类。分析步骤有助于提取和交流关于数据的补充结构信息，还有助于推动交互式信息向下钻取。
Many visualization approaches teach us that ease of use is the key to effective visual data analysis. The Table Lens is an excellent example of a simple, yet expressive visual method that can help in analyzing even larger volumes of data. In this work, we present two extensions of the original Table Lens approach. In particular, we extend the Table Lens by Two-Tone Pseudo Coloring (TTPC) and a hybrid clustering. By integrating TTPC into the Table Lens, we obtain visual representations that can communicate larger volumes of data while still maintaining precision. Secondly, we propose to integrate a data analysis step that implements a hybrid clustering based on self-organizing maps and hierarchical clustering. The analysis step helps to extract and communicate complementary structural information about the data and also serves to drive interactive information drill-down.