Comparing Probabilistic Graphical Model Based and Gaussian Process Based Selections for Predicting the Temporal Observations


In wireless sensor networks, the limited power source makes sensing expensive. It is thus a big optimization problem that obtaining more and useful information but making less observations. In this paper, we compare two model based approaches. One is to apply the improved VoIDP algorithm on a chain graphical model for selecting a subset of observations that minimizes the overall uncertainty; The other is to find a selection of observations on a Gaussian process model that maximizes the entropy and the mutual information criteria respectively. We compare the selections based on their prediction accuracies for the temporal observations on a sensor. Further more, we analyze the strength and weakness of the two approaches through the experimental results.

  • Abstract
  • I. Introduction
  • II. Probabilistic Graphical Model Based Selection
  • III. Gaussian Process Based Selection
  • IV. Experiments
  • V. Conclusions
  • References

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In