Minimax Robust Quickest Change Detection in Systems and Signals with Unknown Transients

Timothy L. Molloy; Jason J. Ford

doi:10.1109/TAC.2018.2872198

Minimax Robust Quickest Change Detection in Systems and Signals with Unknown Transients

Timothy L. Molloy^*, Jason J. Ford

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

We consider the problem of quickly detecting an unknown change in a sequence of independent random variables with unknown transient (or time-varying) prechange and postchange distributions. We pose and solve novel robust versions of the popular Lorden and Bayesian quickest change detection criteria with unknown transients that belong to known uncertainty sets. Simulations of our robust solutions detecting additive changes in linear state-space systems suggest that they can outperform more computationally expensive rules.

Original language	English
Article number	8472189
Pages (from-to)	2976-2982
Number of pages	7
Journal	IEEE Transactions on Automatic Control
Volume	64
Issue number	7
DOIs	https://doi.org/10.1109/TAC.2018.2872198
Publication status	Published - Jul 2019
Externally published	Yes

Access to Document

10.1109/TAC.2018.2872198

Cite this

@article{987049bf5f6145ed96cb123b9dfaeda6,

title = "Minimax Robust Quickest Change Detection in Systems and Signals with Unknown Transients",

abstract = "We consider the problem of quickly detecting an unknown change in a sequence of independent random variables with unknown transient (or time-varying) prechange and postchange distributions. We pose and solve novel robust versions of the popular Lorden and Bayesian quickest change detection criteria with unknown transients that belong to known uncertainty sets. Simulations of our robust solutions detecting additive changes in linear state-space systems suggest that they can outperform more computationally expensive rules.",

keywords = "Fault detection, minimax robustness, quickest change detection",

author = "Molloy, {Timothy L.} and Ford, {Jason J.}",

note = "Publisher Copyright: {\textcopyright} 1963-2012 IEEE.",

year = "2019",

month = jul,

doi = "10.1109/TAC.2018.2872198",

language = "English",

volume = "64",

pages = "2976--2982",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

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

number = "7",

}

TY - JOUR

T1 - Minimax Robust Quickest Change Detection in Systems and Signals with Unknown Transients

AU - Molloy, Timothy L.

AU - Ford, Jason J.

PY - 2019/7

Y1 - 2019/7

N2 - We consider the problem of quickly detecting an unknown change in a sequence of independent random variables with unknown transient (or time-varying) prechange and postchange distributions. We pose and solve novel robust versions of the popular Lorden and Bayesian quickest change detection criteria with unknown transients that belong to known uncertainty sets. Simulations of our robust solutions detecting additive changes in linear state-space systems suggest that they can outperform more computationally expensive rules.

AB - We consider the problem of quickly detecting an unknown change in a sequence of independent random variables with unknown transient (or time-varying) prechange and postchange distributions. We pose and solve novel robust versions of the popular Lorden and Bayesian quickest change detection criteria with unknown transients that belong to known uncertainty sets. Simulations of our robust solutions detecting additive changes in linear state-space systems suggest that they can outperform more computationally expensive rules.

KW - Fault detection

KW - minimax robustness

KW - quickest change detection

UR - http://www.scopus.com/inward/record.url?scp=85054253042&partnerID=8YFLogxK

U2 - 10.1109/TAC.2018.2872198

DO - 10.1109/TAC.2018.2872198

M3 - Article

AN - SCOPUS:85054253042

SN - 0018-9286

VL - 64

SP - 2976

EP - 2982

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 7

M1 - 8472189

ER -

Minimax Robust Quickest Change Detection in Systems and Signals with Unknown Transients

Abstract

Access to Document

Other files and links

Fingerprint

Cite this