Advances in Artificial Intelligence by unknow

Author:unknow
Language: eng
Format: epub
Publisher: Springer International Publishing, Cham

2 Omnigram Explorer

OE was designed as a tool for interactive exploration of relations between variables in an agent-based simulation [10]. It draws upon ideas for visualization in the Attribute Explorer [9], where data is presented in a set of histograms, one per variable. For more detail information about the data requirements see the link: http://​www.​tim-taylor.​com/​omnigram/​.

To begin, a data file and model definition are necessary. The data file containing a joint data sample are loaded and presented by OE in a graphical form (Fig. 1(a)). Each variable is represented by a histogram, showing its sample distribution, with a maximum of 20 bins. If a bin is empty (e.g., bin 0 in Rainfall node in Fig. 1(a)), a thin horizontal line is drawn at the base. A small circle represents the mean (or, if the user chooses, the median). The range of values is indicated by the horizontal bar under the histogram. The initial histogram represents all the values read from the data file in a plain form, but a subset of them can be highlighted in a linking and brushing process (in dark red color).

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.