An EM Algorithm for Lebesgue-sampled State-space Continuous-time System Identification

Rodrigo González; Angel Cedeño; María Coronel; Juan C. Agüero; Cristian R. Rojas

doi:10.1016/j.ifacol.2023.10.1771

An EM Algorithm for Lebesgue-sampled State-space Continuous-time System Identification

Rodrigo González, Angel Cedeño, María Coronel, Juan C. Agüero, Cristian R. Rojas

Group Oomen

Research output: Contribution to journal › Conference article › peer-review

1 Citation (Scopus)

78 Downloads (Pure)

Abstract

This paper concerns the identification of continuous-time systems in state-space
form that are subject to Lebesgue sampling. Contrary to equidistant (Riemann) sampling, Lebesgue sampling consists of taking measurements of a continuous-time signal whenever it crosses fixed and regularly partitioned thresholds. The knowledge of the intersample behavior of the output data is exploited in this work to derive an expectation-maximization (EM) algorithm for parameter estimation of the state-space and noise covariance matrices. For this purpose, we
use the incremental discrete-time equivalent of the system, which leads to EM iterations of the continuous-time state-space matrices that can be computed by standard filtering and smoothing procedures. The effectiveness of the identification method is tested via Monte Carlo simulations.

Original language	English
Pages (from-to)	4204-4209
Number of pages	6
Journal	IFAC-PapersOnLine
Volume	56
Issue number	2
DOIs	https://doi.org/10.1016/j.ifacol.2023.10.1771
Publication status	Published - 1 Jul 2023
Event	22nd World Congress of the International Federation of Automatic Control (IFAC 2023 World Congress) - Yokohama, Japan Duration: 9 Jul 2023 → 14 Jul 2023 Conference number: 22 https://www.ifac2023.org/

Keywords

System identification
continuous-time systems
event-based sampling
expectation-maximization

Access to Document

10.1016/j.ifacol.2023.10.1771

Lebesgue_sampling_PureFinal author version , 378 KBLicence: CC BY-NC-ND
pdfFinal published version, 553 KBLicence: CC BY-NC-ND

Cite this

@article{19c4e0aa76364fa39680b7cc2b55c7c3,

title = "An EM Algorithm for Lebesgue-sampled State-space Continuous-time System Identification",

abstract = "This paper concerns the identification of continuous-time systems in state-spaceform that are subject to Lebesgue sampling. Contrary to equidistant (Riemann) sampling, Lebesgue sampling consists of taking measurements of a continuous-time signal whenever it crosses fixed and regularly partitioned thresholds. The knowledge of the intersample behavior of the output data is exploited in this work to derive an expectation-maximization (EM) algorithm for parameter estimation of the state-space and noise covariance matrices. For this purpose, weuse the incremental discrete-time equivalent of the system, which leads to EM iterations of the continuous-time state-space matrices that can be computed by standard filtering and smoothing procedures. The effectiveness of the identification method is tested via Monte Carlo simulations.",

keywords = "System identification, continuous-time systems, event-based sampling, expectation-maximization",

author = "Rodrigo Gonz{\'a}lez and Angel Cede{\~n}o and Mar{\'i}a Coronel and Ag{\"u}ero, {Juan C.} and Rojas, {Cristian R.}",

year = "2023",

month = jul,

day = "1",

doi = "10.1016/j.ifacol.2023.10.1771",

language = "English",

volume = "56",

pages = "4204--4209",

journal = "IFAC-PapersOnLine",

issn = "2405-8963",

publisher = "Elsevier",

number = "2",

note = "22nd World Congress of the International Federation of Automatic Control (IFAC 2023 World Congress) ; Conference date: 09-07-2023 Through 14-07-2023",

url = "https://www.ifac2023.org/",

}

TY - JOUR

T1 - An EM Algorithm for Lebesgue-sampled State-space Continuous-time System Identification

AU - González, Rodrigo

AU - Cedeño, Angel

AU - Coronel, María

AU - Agüero, Juan C.

AU - Rojas, Cristian R.

N1 - Conference code: 22

PY - 2023/7/1

Y1 - 2023/7/1

N2 - This paper concerns the identification of continuous-time systems in state-spaceform that are subject to Lebesgue sampling. Contrary to equidistant (Riemann) sampling, Lebesgue sampling consists of taking measurements of a continuous-time signal whenever it crosses fixed and regularly partitioned thresholds. The knowledge of the intersample behavior of the output data is exploited in this work to derive an expectation-maximization (EM) algorithm for parameter estimation of the state-space and noise covariance matrices. For this purpose, weuse the incremental discrete-time equivalent of the system, which leads to EM iterations of the continuous-time state-space matrices that can be computed by standard filtering and smoothing procedures. The effectiveness of the identification method is tested via Monte Carlo simulations.

AB - This paper concerns the identification of continuous-time systems in state-spaceform that are subject to Lebesgue sampling. Contrary to equidistant (Riemann) sampling, Lebesgue sampling consists of taking measurements of a continuous-time signal whenever it crosses fixed and regularly partitioned thresholds. The knowledge of the intersample behavior of the output data is exploited in this work to derive an expectation-maximization (EM) algorithm for parameter estimation of the state-space and noise covariance matrices. For this purpose, weuse the incremental discrete-time equivalent of the system, which leads to EM iterations of the continuous-time state-space matrices that can be computed by standard filtering and smoothing procedures. The effectiveness of the identification method is tested via Monte Carlo simulations.

KW - System identification

KW - continuous-time systems

KW - event-based sampling

KW - expectation-maximization

UR - http://www.scopus.com/inward/record.url?scp=85184963058&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2023.10.1771

DO - 10.1016/j.ifacol.2023.10.1771

M3 - Conference article

SN - 2405-8963

VL - 56

SP - 4204

EP - 4209

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

IS - 2

T2 - 22nd World Congress of the International Federation of Automatic Control (IFAC 2023 World Congress)

Y2 - 9 July 2023 through 14 July 2023

ER -

An EM Algorithm for Lebesgue-sampled State-space Continuous-time System Identification

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this