Sequential hypothesis tests for streaming data via symbolic time-series analysis

Nurali Virani, Devesh K. Jha, Asok Ray, Shashi Phoha

Research output: Contribution to journalArticle

Abstract

This paper addresses sequential hypothesis testing for Markov models of time-series data by using the concepts of symbolic dynamics. These models are inferred by discretizing the measurement space of a dynamical system, where the system dynamics are approximated as a finite-memory Markov chain on the discrete state space. The study is motivated by time-critical detection problems in physical processes, where a temporal model is trained to make fast and reliable decisions with streaming data. Sequential update rules have been constructed for log-posterior ratio statistic of Markov models in the setting of binary hypothesis testing and the stochastic evolution of this statistic is analyzed. The proposed technique allows selection of a lower bound on the performance of the detector and guarantees that the test will terminate in finite time. The underlying algorithms are first illustrated through an example by numerical simulation, and are subsequently validated on time-series data of pressure oscillations from a laboratory-scale swirl-stabilized combustor apparatus to detect the onset of thermo-acoustic instability. The performance of the proposed sequential hypothesis tests for Markov models has been compared with that of a maximum-likelihood classifier with fixed sample size (i.e., sequence length). It is shown that the proposed method yields reliable detection of combustion instabilities with fewer observations in comparison to a fixed-sample-size test.

Original languageEnglish (US)
Pages (from-to)234-246
Number of pages13
JournalEngineering Applications of Artificial Intelligence
Volume81
DOIs
StatePublished - May 1 2019

Fingerprint

Time series analysis
Time series
Dynamical systems
Statistics
Testing
Combustors
Markov processes
Maximum likelihood
Classifiers
Acoustics
Detectors
Data storage equipment
Computer simulation

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Artificial Intelligence
  • Electrical and Electronic Engineering

Cite this

@article{0a3e882deecc441895460df37535c763,
title = "Sequential hypothesis tests for streaming data via symbolic time-series analysis",
abstract = "This paper addresses sequential hypothesis testing for Markov models of time-series data by using the concepts of symbolic dynamics. These models are inferred by discretizing the measurement space of a dynamical system, where the system dynamics are approximated as a finite-memory Markov chain on the discrete state space. The study is motivated by time-critical detection problems in physical processes, where a temporal model is trained to make fast and reliable decisions with streaming data. Sequential update rules have been constructed for log-posterior ratio statistic of Markov models in the setting of binary hypothesis testing and the stochastic evolution of this statistic is analyzed. The proposed technique allows selection of a lower bound on the performance of the detector and guarantees that the test will terminate in finite time. The underlying algorithms are first illustrated through an example by numerical simulation, and are subsequently validated on time-series data of pressure oscillations from a laboratory-scale swirl-stabilized combustor apparatus to detect the onset of thermo-acoustic instability. The performance of the proposed sequential hypothesis tests for Markov models has been compared with that of a maximum-likelihood classifier with fixed sample size (i.e., sequence length). It is shown that the proposed method yields reliable detection of combustion instabilities with fewer observations in comparison to a fixed-sample-size test.",
author = "Nurali Virani and Jha, {Devesh K.} and Asok Ray and Shashi Phoha",
year = "2019",
month = "5",
day = "1",
doi = "10.1016/j.engappai.2019.02.015",
language = "English (US)",
volume = "81",
pages = "234--246",
journal = "Engineering Applications of Artificial Intelligence",
issn = "0952-1976",
publisher = "Elsevier Limited",

}

Sequential hypothesis tests for streaming data via symbolic time-series analysis. / Virani, Nurali; Jha, Devesh K.; Ray, Asok; Phoha, Shashi.

In: Engineering Applications of Artificial Intelligence, Vol. 81, 01.05.2019, p. 234-246.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Sequential hypothesis tests for streaming data via symbolic time-series analysis

AU - Virani, Nurali

AU - Jha, Devesh K.

AU - Ray, Asok

AU - Phoha, Shashi

PY - 2019/5/1

Y1 - 2019/5/1

N2 - This paper addresses sequential hypothesis testing for Markov models of time-series data by using the concepts of symbolic dynamics. These models are inferred by discretizing the measurement space of a dynamical system, where the system dynamics are approximated as a finite-memory Markov chain on the discrete state space. The study is motivated by time-critical detection problems in physical processes, where a temporal model is trained to make fast and reliable decisions with streaming data. Sequential update rules have been constructed for log-posterior ratio statistic of Markov models in the setting of binary hypothesis testing and the stochastic evolution of this statistic is analyzed. The proposed technique allows selection of a lower bound on the performance of the detector and guarantees that the test will terminate in finite time. The underlying algorithms are first illustrated through an example by numerical simulation, and are subsequently validated on time-series data of pressure oscillations from a laboratory-scale swirl-stabilized combustor apparatus to detect the onset of thermo-acoustic instability. The performance of the proposed sequential hypothesis tests for Markov models has been compared with that of a maximum-likelihood classifier with fixed sample size (i.e., sequence length). It is shown that the proposed method yields reliable detection of combustion instabilities with fewer observations in comparison to a fixed-sample-size test.

AB - This paper addresses sequential hypothesis testing for Markov models of time-series data by using the concepts of symbolic dynamics. These models are inferred by discretizing the measurement space of a dynamical system, where the system dynamics are approximated as a finite-memory Markov chain on the discrete state space. The study is motivated by time-critical detection problems in physical processes, where a temporal model is trained to make fast and reliable decisions with streaming data. Sequential update rules have been constructed for log-posterior ratio statistic of Markov models in the setting of binary hypothesis testing and the stochastic evolution of this statistic is analyzed. The proposed technique allows selection of a lower bound on the performance of the detector and guarantees that the test will terminate in finite time. The underlying algorithms are first illustrated through an example by numerical simulation, and are subsequently validated on time-series data of pressure oscillations from a laboratory-scale swirl-stabilized combustor apparatus to detect the onset of thermo-acoustic instability. The performance of the proposed sequential hypothesis tests for Markov models has been compared with that of a maximum-likelihood classifier with fixed sample size (i.e., sequence length). It is shown that the proposed method yields reliable detection of combustion instabilities with fewer observations in comparison to a fixed-sample-size test.

UR - http://www.scopus.com/inward/record.url?scp=85062711042&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062711042&partnerID=8YFLogxK

U2 - 10.1016/j.engappai.2019.02.015

DO - 10.1016/j.engappai.2019.02.015

M3 - Article

VL - 81

SP - 234

EP - 246

JO - Engineering Applications of Artificial Intelligence

JF - Engineering Applications of Artificial Intelligence

SN - 0952-1976

ER -