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
Back to Top