In this paper, a new class of Gaussian processes is proposed for resource-constrained mobile sensor networks. Such a Gaussian process builds on a GMRF with respect to a proximity graph over a surveillance region. The main advantages of using this class of Gaussian processes over standard Gaussian processes defined by mean and covariance functions are its numerical efficiency and scalability due to its built-in GMRF and its capability of representing a wide range of non-stationary physical processes. The formulas for Bayesian posterior predictive statistics such as prediction mean and variance are derived and a sequential field prediction algorithm is provided for sequentially sampled observations. For a special case using compactly supported kernels, we propose a distributed algorithm to implement field prediction by correctly fusing all observations in Bayesian statistics. Simulation results illustrate the effectiveness of our approach.
- Dynamic Systems and Control Division
Spatial Prediction With Mobile Sensor Networks Using Gaussian Process Regression Based on Gaussian Markov Random Fields
- Views Icon Views
- Share Icon Share
- Search Site
Xu, Y, & Choi, J. "Spatial Prediction With Mobile Sensor Networks Using Gaussian Process Regression Based on Gaussian Markov Random Fields." Proceedings of the ASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control. ASME 2011 Dynamic Systems and Control Conference and Bath/ASME Symposium on Fluid Power and Motion Control, Volume 2. Arlington, Virginia, USA. October 31–November 2, 2011. pp. 173-180. ASME. https://doi.org/10.1115/DSCC2011-6092
Download citation file: