|
Activity Number:
|
553
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 6, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistical Computing
|
| Abstract - #305709 |
|
Title:
|
Nonparametric Density Estimation of Streaming Data Using Orthogonal Series
|
|
Author(s):
|
Kyle A. Caudle*+ and Edward J. Wegman
|
|
Companies:
|
U.S. Naval Academy and George Mason University
|
|
Address:
|
Department of Mathematics, Annapolis, MD, 21402,
|
|
Keywords:
|
recursive updating ; exponential smoothing ; block recursion ; wavelets
|
|
Abstract:
|
Streaming data represent a serious challenge because implicit in the nature of streaming data, data are not exchangeable and are not storable. This means data must be processed on the fly. Density estimation is an essential tool used to make sense of data collected by large scale systems. In this paper, we present a recursive method for constructing and updating an estimate of the nonstationary probability density function. Our approach is shown to work well with simulated data as well as with real data.
|
