|
Activity Number:
|
321
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, July 31, 2007 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #308295 |
|
Title:
|
Getting What We Need from Wireless Sensor Networks: A Role for Inferential Ecosystem Models
|
|
Author(s):
|
James Clark*+ and Pankaj Agarwal and David Bell and Carla Ellis and Paul Flikkema and Alan E. Gelfand and Gabriel Katul and Kamesh Munagala and Gavino Puggioni and Adam Silberstein and Jun Yang
|
|
Companies:
|
Duke University and Duke University and Duke University and Duke University and Northern Arizona University and Duke University and Duke University and Duke University and Duke University and Duke University and Duke University
|
|
Address:
|
Nicholas School of the Environment, Durham, NC, 27708,
|
|
Keywords:
|
environmental change ; prediction ; hierarchical Bayes ; wireless networks ; forests
|
|
Abstract:
|
Efficient wireless sensor networks require inferential ecosystem models that can weigh the value of an observation against cost of transmission. Transmission costs make observations 'expensive'; networks are deployed in remote locations without access to power. The capacity to sample intensively makes sensor networks powerful, but high frequency data have value only at specific times and locations. Given that intensive sampling is sometimes critical, but more often wasteful, how do we control transmission? The value of an observation can be evaluated in terms of its contribution to estimates of state variables and parameters. Network control must be dynamic and driven by models capable of learning about both the environment and the network. Inference is needed to weigh the contributions against transmission cost. We discuss Bayesian inference to control network transmission.
|
