Bayesian prediction and adaptive sampling algorithms for mobile sensor networks

Yunfei Xu, Jongeun Choi, Sarat Dass, Taps Maiti

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

In this paper, we formulate a full Bayesian approach for spatio-temporal Gaussian process regression under practical conditions such as measurement noise and unknown hyperparmeters (particularly, the bandwidths). Thus, multi-factorial effects of observations, measurement noise and prior distributions of hyperparameters are all correctly incorporated in the computed predictive distribution. Using discrete prior probabilities and compactly supported kernels, we provide a way to design sequential Bayesian prediction algorithms that can be computed (without using the Gibbs sampler) in constant time as the number of observations increases. Both centralized and distributed sequential Bayesian prediction algorithms have been proposed for mobile sensor networks. An adaptive sampling strategy for mobile sensors, using the maximum a posteriori (MAP) estimation, has been proposed to minimize the prediction error variances. Simulation results illustrate the effectiveness of the proposed algorithms.

Original languageEnglish
Title of host publicationProceedings of the 2011 American Control Conference, ACC 2011
Pages4195-4200
Number of pages6
Publication statusPublished - 2011 Sep 29
Event2011 American Control Conference, ACC 2011 - San Francisco, CA, United States
Duration: 2011 Jun 292011 Jul 1

Other

Other2011 American Control Conference, ACC 2011
CountryUnited States
CitySan Francisco, CA
Period11/6/2911/7/1

Fingerprint

Sensor networks
Wireless networks
Sampling
Bandwidth
Sensors

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Xu, Y., Choi, J., Dass, S., & Maiti, T. (2011). Bayesian prediction and adaptive sampling algorithms for mobile sensor networks. In Proceedings of the 2011 American Control Conference, ACC 2011 (pp. 4195-4200). [5990887]
Xu, Yunfei ; Choi, Jongeun ; Dass, Sarat ; Maiti, Taps. / Bayesian prediction and adaptive sampling algorithms for mobile sensor networks. Proceedings of the 2011 American Control Conference, ACC 2011. 2011. pp. 4195-4200
@inproceedings{af5ef22fe4d74dbc836f0ebc1ccc225b,
title = "Bayesian prediction and adaptive sampling algorithms for mobile sensor networks",
abstract = "In this paper, we formulate a full Bayesian approach for spatio-temporal Gaussian process regression under practical conditions such as measurement noise and unknown hyperparmeters (particularly, the bandwidths). Thus, multi-factorial effects of observations, measurement noise and prior distributions of hyperparameters are all correctly incorporated in the computed predictive distribution. Using discrete prior probabilities and compactly supported kernels, we provide a way to design sequential Bayesian prediction algorithms that can be computed (without using the Gibbs sampler) in constant time as the number of observations increases. Both centralized and distributed sequential Bayesian prediction algorithms have been proposed for mobile sensor networks. An adaptive sampling strategy for mobile sensors, using the maximum a posteriori (MAP) estimation, has been proposed to minimize the prediction error variances. Simulation results illustrate the effectiveness of the proposed algorithms.",
author = "Yunfei Xu and Jongeun Choi and Sarat Dass and Taps Maiti",
year = "2011",
month = "9",
day = "29",
language = "English",
isbn = "9781457700804",
pages = "4195--4200",
booktitle = "Proceedings of the 2011 American Control Conference, ACC 2011",

}

Xu, Y, Choi, J, Dass, S & Maiti, T 2011, Bayesian prediction and adaptive sampling algorithms for mobile sensor networks. in Proceedings of the 2011 American Control Conference, ACC 2011., 5990887, pp. 4195-4200, 2011 American Control Conference, ACC 2011, San Francisco, CA, United States, 11/6/29.

Bayesian prediction and adaptive sampling algorithms for mobile sensor networks. / Xu, Yunfei; Choi, Jongeun; Dass, Sarat; Maiti, Taps.

Proceedings of the 2011 American Control Conference, ACC 2011. 2011. p. 4195-4200 5990887.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Bayesian prediction and adaptive sampling algorithms for mobile sensor networks

AU - Xu, Yunfei

AU - Choi, Jongeun

AU - Dass, Sarat

AU - Maiti, Taps

PY - 2011/9/29

Y1 - 2011/9/29

N2 - In this paper, we formulate a full Bayesian approach for spatio-temporal Gaussian process regression under practical conditions such as measurement noise and unknown hyperparmeters (particularly, the bandwidths). Thus, multi-factorial effects of observations, measurement noise and prior distributions of hyperparameters are all correctly incorporated in the computed predictive distribution. Using discrete prior probabilities and compactly supported kernels, we provide a way to design sequential Bayesian prediction algorithms that can be computed (without using the Gibbs sampler) in constant time as the number of observations increases. Both centralized and distributed sequential Bayesian prediction algorithms have been proposed for mobile sensor networks. An adaptive sampling strategy for mobile sensors, using the maximum a posteriori (MAP) estimation, has been proposed to minimize the prediction error variances. Simulation results illustrate the effectiveness of the proposed algorithms.

AB - In this paper, we formulate a full Bayesian approach for spatio-temporal Gaussian process regression under practical conditions such as measurement noise and unknown hyperparmeters (particularly, the bandwidths). Thus, multi-factorial effects of observations, measurement noise and prior distributions of hyperparameters are all correctly incorporated in the computed predictive distribution. Using discrete prior probabilities and compactly supported kernels, we provide a way to design sequential Bayesian prediction algorithms that can be computed (without using the Gibbs sampler) in constant time as the number of observations increases. Both centralized and distributed sequential Bayesian prediction algorithms have been proposed for mobile sensor networks. An adaptive sampling strategy for mobile sensors, using the maximum a posteriori (MAP) estimation, has been proposed to minimize the prediction error variances. Simulation results illustrate the effectiveness of the proposed algorithms.

UR - http://www.scopus.com/inward/record.url?scp=80053169360&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053169360&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:80053169360

SN - 9781457700804

SP - 4195

EP - 4200

BT - Proceedings of the 2011 American Control Conference, ACC 2011

ER -

Xu Y, Choi J, Dass S, Maiti T. Bayesian prediction and adaptive sampling algorithms for mobile sensor networks. In Proceedings of the 2011 American Control Conference, ACC 2011. 2011. p. 4195-4200. 5990887