Robust hypothesis testing for structured uncertainty models

Sundeep Rangan, Poolla Kameshwar

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

Abstract

Developing uncertainty models suitable for modern Tobust design methods involves numerous modeling decisions regarding uncertainty structure, noise models and uncertainty bounds. In this paper, we consider the problem of selecting between one of two candidate uncertainty models based on input-output data. Each uncertainty model consists of a nominal linear plant with a standard linear fractional transformation (LFT) uncertainty structure and Gaussian output noise. A classical statistical hypothesis testing performance measure is used to evaluate decision procedures. We derive a D-scaled upper bound on this performance measure, and show that this upper bound can be minimized by convex programming and H filtering techniques. In addition, a general robust hypothesis testing result is derived.

Original languageEnglish (US)
Title of host publicationProceedings of the 1998 American Control Conference, ACC 1998
Pages1434-1438
Number of pages5
Volume3
DOIs
StatePublished - 1998
Event1998 American Control Conference, ACC 1998 - Philadelphia, PA, United States
Duration: Jun 24 1998Jun 26 1998

Other

Other1998 American Control Conference, ACC 1998
CountryUnited States
CityPhiladelphia, PA
Period6/24/986/26/98

Fingerprint

Testing
Convex optimization
Uncertainty

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Rangan, S., & Kameshwar, P. (1998). Robust hypothesis testing for structured uncertainty models. In Proceedings of the 1998 American Control Conference, ACC 1998 (Vol. 3, pp. 1434-1438). [707062] https://doi.org/10.1109/ACC.1998.707062

Robust hypothesis testing for structured uncertainty models. / Rangan, Sundeep; Kameshwar, Poolla.

Proceedings of the 1998 American Control Conference, ACC 1998. Vol. 3 1998. p. 1434-1438 707062.

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

Rangan, S & Kameshwar, P 1998, Robust hypothesis testing for structured uncertainty models. in Proceedings of the 1998 American Control Conference, ACC 1998. vol. 3, 707062, pp. 1434-1438, 1998 American Control Conference, ACC 1998, Philadelphia, PA, United States, 6/24/98. https://doi.org/10.1109/ACC.1998.707062
Rangan S, Kameshwar P. Robust hypothesis testing for structured uncertainty models. In Proceedings of the 1998 American Control Conference, ACC 1998. Vol. 3. 1998. p. 1434-1438. 707062 https://doi.org/10.1109/ACC.1998.707062
Rangan, Sundeep ; Kameshwar, Poolla. / Robust hypothesis testing for structured uncertainty models. Proceedings of the 1998 American Control Conference, ACC 1998. Vol. 3 1998. pp. 1434-1438
@inproceedings{3cd45f2f0d7b4edba090f2f09e4df7ff,
title = "Robust hypothesis testing for structured uncertainty models",
abstract = "Developing uncertainty models suitable for modern Tobust design methods involves numerous modeling decisions regarding uncertainty structure, noise models and uncertainty bounds. In this paper, we consider the problem of selecting between one of two candidate uncertainty models based on input-output data. Each uncertainty model consists of a nominal linear plant with a standard linear fractional transformation (LFT) uncertainty structure and Gaussian output noise. A classical statistical hypothesis testing performance measure is used to evaluate decision procedures. We derive a D-scaled upper bound on this performance measure, and show that this upper bound can be minimized by convex programming and H∞ filtering techniques. In addition, a general robust hypothesis testing result is derived.",
author = "Sundeep Rangan and Poolla Kameshwar",
year = "1998",
doi = "10.1109/ACC.1998.707062",
language = "English (US)",
isbn = "0780345304",
volume = "3",
pages = "1434--1438",
booktitle = "Proceedings of the 1998 American Control Conference, ACC 1998",

}

TY - GEN

T1 - Robust hypothesis testing for structured uncertainty models

AU - Rangan, Sundeep

AU - Kameshwar, Poolla

PY - 1998

Y1 - 1998

N2 - Developing uncertainty models suitable for modern Tobust design methods involves numerous modeling decisions regarding uncertainty structure, noise models and uncertainty bounds. In this paper, we consider the problem of selecting between one of two candidate uncertainty models based on input-output data. Each uncertainty model consists of a nominal linear plant with a standard linear fractional transformation (LFT) uncertainty structure and Gaussian output noise. A classical statistical hypothesis testing performance measure is used to evaluate decision procedures. We derive a D-scaled upper bound on this performance measure, and show that this upper bound can be minimized by convex programming and H∞ filtering techniques. In addition, a general robust hypothesis testing result is derived.

AB - Developing uncertainty models suitable for modern Tobust design methods involves numerous modeling decisions regarding uncertainty structure, noise models and uncertainty bounds. In this paper, we consider the problem of selecting between one of two candidate uncertainty models based on input-output data. Each uncertainty model consists of a nominal linear plant with a standard linear fractional transformation (LFT) uncertainty structure and Gaussian output noise. A classical statistical hypothesis testing performance measure is used to evaluate decision procedures. We derive a D-scaled upper bound on this performance measure, and show that this upper bound can be minimized by convex programming and H∞ filtering techniques. In addition, a general robust hypothesis testing result is derived.

UR - http://www.scopus.com/inward/record.url?scp=84881365536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881365536&partnerID=8YFLogxK

U2 - 10.1109/ACC.1998.707062

DO - 10.1109/ACC.1998.707062

M3 - Conference contribution

SN - 0780345304

SN - 9780780345300

VL - 3

SP - 1434

EP - 1438

BT - Proceedings of the 1998 American Control Conference, ACC 1998

ER -