3 February 2014 Visualizing trends and clusters in ranked time-series data
Author Affiliations +
Abstract
There are many systems that provide visualizations for time-oriented data. Of those, few provide the means of finding patterns in time-series data in which rankings are also important. Fewer still have the fine granularity necessary to visually follow individual data points through time. We propose the Ranking Timeline, a novel visualization method for modestly-sized multivariate data sets that include the top ten rankings over time. The system includes two main visualization components: a ranking over time and a cluster analysis. The ranking visualization, loosely based on line plots, allows the user to track individual data points so as to facilitate comparisons within a given time frame. Glyphs represent additional attributes within the framework of the overall system. The user has control over many aspects of the visualization, including viewing a subset of the data and/or focusing on a desired time frame. The cluster analysis tool shows the relative importance of individual items in conjunction with a visualization showing the connection(s) to other, similar items, while maintaining the aforementioned glyphs and user interaction. The user controls the clustering according to a similarity threshold. The system has been implemented as a Web application, and has been tested with data showing the top ten actors/actresses from 1929-2010. The experiments have revealed patterns in the data heretofore not explored.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Michael B. Gousie, Michael B. Gousie, John Grady, John Grady, Melissa Branagan, Melissa Branagan, "Visualizing trends and clusters in ranked time-series data", Proc. SPIE 9017, Visualization and Data Analysis 2014, 90170F (3 February 2014); doi: 10.1117/12.2037038; https://doi.org/10.1117/12.2037038
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT


Back to Top