Optimal sequential test with finite horizon and constrained sensor selection

Shang Li; Xiaoou Li; Xiaodong Wang; Jingchen Liu

doi:10.1109/ISIT.2016.7541558

Optimal sequential test with finite horizon and constrained sensor selection

Shang Li
, Xiaoou Li
, Xiaodong Wang
, Jingchen Liu

Statistics (Twin Cities)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

This work considers the online sensor selection for the finite-horizon sequential hypothesis testing. In particular, at each step of the sequential test, the 'most informative' sensor is selected based on all the previous samples so that the expected sample size is minimized. In addition, certain sensors cannot be used more than their prescribed budgets on average. Under this setup, we show that the optimal sensor selection strategy is a time-variant function of the running hypothesis posterior, and the optimal test takes the form of a truncated sequential probability ratio test. Both of these operations can be obtained through a simplified version of dynamic programming. Numerical results demonstrate that the proposed online approach outperforms the existing offline approach to the order of magnitude.

Original language	English (US)
Title of host publication	Proceedings - 2016 IEEE International Symposium on Information Theory, ISIT 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1546-1550
Number of pages	5
ISBN (Electronic)	9781509018062
DOIs	https://doi.org/10.1109/ISIT.2016.7541558
State	Published - Aug 10 2016
Event	2016 IEEE International Symposium on Information Theory, ISIT 2016 - Barcelona, Spain Duration: Jul 10 2016 → Jul 15 2016

Publication series

Name	IEEE International Symposium on Information Theory - Proceedings
Volume	2016-August
ISSN (Electronic)	2157-8117

Other

Other	2016 IEEE International Symposium on Information Theory, ISIT 2016
Country/Territory	Spain
City	Barcelona
Period	7/10/16 → 7/15/16

Bibliographical note

Publisher Copyright:
© 2016 IEEE.

Keywords

Sequential hypothesis testing
dynamic programming
finite horizon
online sensor selection
sensor usages

Publisher link

10.1109/ISIT.2016.7541558

Find It

Find It at U of M Libraries

Cite this

Li, S., Li, X., Wang, X., & Liu, J. (2016). Optimal sequential test with finite horizon and constrained sensor selection. In Proceedings - 2016 IEEE International Symposium on Information Theory, ISIT 2016 (pp. 1546-1550). Article 7541558 (IEEE International Symposium on Information Theory - Proceedings; Vol. 2016-August). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISIT.2016.7541558

Optimal sequential test with finite horizon and constrained sensor selection. / Li, Shang; Li, Xiaoou; Wang, Xiaodong et al.
Proceedings - 2016 IEEE International Symposium on Information Theory, ISIT 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1546-1550 7541558 (IEEE International Symposium on Information Theory - Proceedings; Vol. 2016-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Li, S, Li, X, Wang, X & Liu, J 2016, Optimal sequential test with finite horizon and constrained sensor selection. in Proceedings - 2016 IEEE International Symposium on Information Theory, ISIT 2016., 7541558, IEEE International Symposium on Information Theory - Proceedings, vol. 2016-August, Institute of Electrical and Electronics Engineers Inc., pp. 1546-1550, 2016 IEEE International Symposium on Information Theory, ISIT 2016, Barcelona, Spain, 7/10/16. https://doi.org/10.1109/ISIT.2016.7541558

Li S, Li X, Wang X, Liu J. Optimal sequential test with finite horizon and constrained sensor selection. In Proceedings - 2016 IEEE International Symposium on Information Theory, ISIT 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1546-1550. 7541558. (IEEE International Symposium on Information Theory - Proceedings). doi: 10.1109/ISIT.2016.7541558

@inproceedings{4b8023faa1f84abd8843090bdb016caf,

title = "Optimal sequential test with finite horizon and constrained sensor selection",

abstract = "This work considers the online sensor selection for the finite-horizon sequential hypothesis testing. In particular, at each step of the sequential test, the 'most informative' sensor is selected based on all the previous samples so that the expected sample size is minimized. In addition, certain sensors cannot be used more than their prescribed budgets on average. Under this setup, we show that the optimal sensor selection strategy is a time-variant function of the running hypothesis posterior, and the optimal test takes the form of a truncated sequential probability ratio test. Both of these operations can be obtained through a simplified version of dynamic programming. Numerical results demonstrate that the proposed online approach outperforms the existing offline approach to the order of magnitude.",

keywords = "Sequential hypothesis testing, dynamic programming, finite horizon, online sensor selection, sensor usages",

author = "Shang Li and Xiaoou Li and Xiaodong Wang and Jingchen Liu",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 2016 IEEE International Symposium on Information Theory, ISIT 2016 ; Conference date: 10-07-2016 Through 15-07-2016",

year = "2016",

month = aug,

day = "10",

doi = "10.1109/ISIT.2016.7541558",

language = "English (US)",

series = "IEEE International Symposium on Information Theory - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "1546--1550",

booktitle = "Proceedings - 2016 IEEE International Symposium on Information Theory, ISIT 2016",

}

TY - GEN

T1 - Optimal sequential test with finite horizon and constrained sensor selection

AU - Li, Shang

AU - Li, Xiaoou

AU - Wang, Xiaodong

AU - Liu, Jingchen

PY - 2016/8/10

Y1 - 2016/8/10

N2 - This work considers the online sensor selection for the finite-horizon sequential hypothesis testing. In particular, at each step of the sequential test, the 'most informative' sensor is selected based on all the previous samples so that the expected sample size is minimized. In addition, certain sensors cannot be used more than their prescribed budgets on average. Under this setup, we show that the optimal sensor selection strategy is a time-variant function of the running hypothesis posterior, and the optimal test takes the form of a truncated sequential probability ratio test. Both of these operations can be obtained through a simplified version of dynamic programming. Numerical results demonstrate that the proposed online approach outperforms the existing offline approach to the order of magnitude.

AB - This work considers the online sensor selection for the finite-horizon sequential hypothesis testing. In particular, at each step of the sequential test, the 'most informative' sensor is selected based on all the previous samples so that the expected sample size is minimized. In addition, certain sensors cannot be used more than their prescribed budgets on average. Under this setup, we show that the optimal sensor selection strategy is a time-variant function of the running hypothesis posterior, and the optimal test takes the form of a truncated sequential probability ratio test. Both of these operations can be obtained through a simplified version of dynamic programming. Numerical results demonstrate that the proposed online approach outperforms the existing offline approach to the order of magnitude.

KW - Sequential hypothesis testing

KW - dynamic programming

KW - finite horizon

KW - online sensor selection

KW - sensor usages

UR - https://www.scopus.com/pages/publications/84986001169

UR - https://www.scopus.com/pages/publications/84986001169#tab=citedBy

U2 - 10.1109/ISIT.2016.7541558

DO - 10.1109/ISIT.2016.7541558

M3 - Conference contribution

AN - SCOPUS:84986001169

T3 - IEEE International Symposium on Information Theory - Proceedings

SP - 1546

EP - 1550

BT - Proceedings - 2016 IEEE International Symposium on Information Theory, ISIT 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 IEEE International Symposium on Information Theory, ISIT 2016

Y2 - 10 July 2016 through 15 July 2016

ER -

Optimal sequential test with finite horizon and constrained sensor selection

Abstract

Publication series

Other

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this