Parallel coordinates are a significant way of visualizing multidimensional data. With their assistance, people can easily and intuitively observe and analyze the data. However, parallel coordinates may cause unnecessary visual clutter due to the improper arrangement of their attribute dimensions, which affecting people's perception of the data. In this paper, we propose a method by using representative lines to estimate the number of crossings between lines in parallel coordinates and take it as the basis to optimize the arrangement of attribute dimensions. The experimental results show that the proposed method can arrange the attribute dimensions fast and achieve better performance on the analysis of data.
展开▼
