Confidence measure estimation in dynamical systems model input set selection

Paul B. Deignan, Galen B. King, Peter H. Meckl, Kristofer Jennings

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

1 Citation (Scopus)

Abstract

An information-theoretic input selection method for dynamical system modeling is presented that qualifies the rejection of irrelevant inputs from a candidate input set with an estimate of a measure of confidence given only finite data. To this end, we introduce a method of determining the spatial interval of dependency in the context of the modeling problem for bootstrap mutual information estimates on dependent time-series. Additionally, details are presented for determining an optimal binning interval for histogram-based mutual information estimates.

Original languageEnglish (US)
Title of host publicationProceedings of the American Control Conference
Pages2824-2829
Number of pages6
Volume3
StatePublished - 2004
Externally publishedYes
EventProceedings of the 2004 American Control Conference (AAC) - Boston, MA, United States
Duration: Jun 30 2004Jul 2 2004

Other

OtherProceedings of the 2004 American Control Conference (AAC)
CountryUnited States
CityBoston, MA
Period6/30/047/2/04

Fingerprint

Time series
Dynamical systems

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Deignan, P. B., King, G. B., Meckl, P. H., & Jennings, K. (2004). Confidence measure estimation in dynamical systems model input set selection. In Proceedings of the American Control Conference (Vol. 3, pp. 2824-2829)

Confidence measure estimation in dynamical systems model input set selection. / Deignan, Paul B.; King, Galen B.; Meckl, Peter H.; Jennings, Kristofer.

Proceedings of the American Control Conference. Vol. 3 2004. p. 2824-2829.

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

Deignan, PB, King, GB, Meckl, PH & Jennings, K 2004, Confidence measure estimation in dynamical systems model input set selection. in Proceedings of the American Control Conference. vol. 3, pp. 2824-2829, Proceedings of the 2004 American Control Conference (AAC), Boston, MA, United States, 6/30/04.
Deignan PB, King GB, Meckl PH, Jennings K. Confidence measure estimation in dynamical systems model input set selection. In Proceedings of the American Control Conference. Vol. 3. 2004. p. 2824-2829
Deignan, Paul B. ; King, Galen B. ; Meckl, Peter H. ; Jennings, Kristofer. / Confidence measure estimation in dynamical systems model input set selection. Proceedings of the American Control Conference. Vol. 3 2004. pp. 2824-2829
@inproceedings{8e2d7fc2065b4b9ebee01a92d4f00e7c,
title = "Confidence measure estimation in dynamical systems model input set selection",
abstract = "An information-theoretic input selection method for dynamical system modeling is presented that qualifies the rejection of irrelevant inputs from a candidate input set with an estimate of a measure of confidence given only finite data. To this end, we introduce a method of determining the spatial interval of dependency in the context of the modeling problem for bootstrap mutual information estimates on dependent time-series. Additionally, details are presented for determining an optimal binning interval for histogram-based mutual information estimates.",
author = "Deignan, {Paul B.} and King, {Galen B.} and Meckl, {Peter H.} and Kristofer Jennings",
year = "2004",
language = "English (US)",
volume = "3",
pages = "2824--2829",
booktitle = "Proceedings of the American Control Conference",

}

TY - GEN

T1 - Confidence measure estimation in dynamical systems model input set selection

AU - Deignan, Paul B.

AU - King, Galen B.

AU - Meckl, Peter H.

AU - Jennings, Kristofer

PY - 2004

Y1 - 2004

N2 - An information-theoretic input selection method for dynamical system modeling is presented that qualifies the rejection of irrelevant inputs from a candidate input set with an estimate of a measure of confidence given only finite data. To this end, we introduce a method of determining the spatial interval of dependency in the context of the modeling problem for bootstrap mutual information estimates on dependent time-series. Additionally, details are presented for determining an optimal binning interval for histogram-based mutual information estimates.

AB - An information-theoretic input selection method for dynamical system modeling is presented that qualifies the rejection of irrelevant inputs from a candidate input set with an estimate of a measure of confidence given only finite data. To this end, we introduce a method of determining the spatial interval of dependency in the context of the modeling problem for bootstrap mutual information estimates on dependent time-series. Additionally, details are presented for determining an optimal binning interval for histogram-based mutual information estimates.

UR - http://www.scopus.com/inward/record.url?scp=8744302819&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8744302819&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:8744302819

VL - 3

SP - 2824

EP - 2829

BT - Proceedings of the American Control Conference

ER -