George Mason University
AES/CCS/SCS Statistics Colloquium Series
Seminar Announcement



Evolutionary Graphics for Streaming Data

Edward J. Wegman
George Mason University


ABSTRACT

Data visualization has evolved from static images of small fixed-size data sets through computer generated dynamic graphics for large, but fixed data sets. Many situations however call for an ability to handle streaming data. One such situation of substantial importance is Internet traffic where one is interested in detecting, on the fly, attacks on a system or local network. In such a case, it is impractical to attempt to store data. Both graphical and analytic techniques must be capable of generating analysis procedures without storing the data. For analytic techniques, recursive algorithms of relatively low computational complexity can accomplish this. We review several of these and suggest several new graphical methods, which are dynamic techniques for streaming data.


Friday, August 29, 2003
George W. Johnson Center, Assembly Room C
Seminar at 10:45 a.m.
Refreshments at 10:30 a.m.
For the 2003 Fall Seminar Schedule, go to
www.science.gmu.edu/statseminars