Hybrid model predictive control for sequential decision policies in adaptive behavioral interventions

Yuwen Dong, Sunil Deshpande, Daniel E. Rivera, Danielle Symons Downs, Jennifer Savage Williams

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

7 Citations (Scopus)

Abstract

Control engineering offers a systematic and efficient method to optimize the effectiveness of individually tailored treatment and prevention policies known as adaptive or 'just-in-time' behavioral interventions. The nature of these interventions requires assigning dosages at categorical levels, which has been addressed in prior work using Mixed Logical Dynamical (MLD)-based hybrid model predictive control (HMPC) schemes. However, certain requirements of adaptive behavioral interventions that involve sequential decision making have not been comprehensively explored in the literature. This paper presents an extension of the traditional MLD framework for HMPC by representing the requirements of sequential decision policies as mixed-integer linear constraints. This is accomplished with user-specified dosage sequence tables, manipulation of one input at a time, and a switching time strategy for assigning dosages at time intervals less frequent than the measurement sampling interval. A model developed for a gestational weight gain (GWG) intervention is used to illustrate the generation of these sequential decision policies and their effectiveness for implementing adaptive behavioral interventions involving multiple components.

Original languageEnglish (US)
Title of host publication2014 American Control Conference, ACC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4198-4203
Number of pages6
ISBN (Print)9781479932726
DOIs
StatePublished - Jan 1 2014
Event2014 American Control Conference, ACC 2014 - Portland, OR, United States
Duration: Jun 4 2014Jun 6 2014

Publication series

NameProceedings of the American Control Conference
ISSN (Print)0743-1619

Other

Other2014 American Control Conference, ACC 2014
CountryUnited States
CityPortland, OR
Period6/4/146/6/14

Fingerprint

Model predictive control
Decision making
Sampling

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering

Cite this

Dong, Y., Deshpande, S., Rivera, D. E., Downs, D. S., & Williams, J. S. (2014). Hybrid model predictive control for sequential decision policies in adaptive behavioral interventions. In 2014 American Control Conference, ACC 2014 (pp. 4198-4203). [6859462] (Proceedings of the American Control Conference). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACC.2014.6859462
Dong, Yuwen ; Deshpande, Sunil ; Rivera, Daniel E. ; Downs, Danielle Symons ; Williams, Jennifer Savage. / Hybrid model predictive control for sequential decision policies in adaptive behavioral interventions. 2014 American Control Conference, ACC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 4198-4203 (Proceedings of the American Control Conference).
@inproceedings{18fd10424b4c4239aebf90fe8e48d649,
title = "Hybrid model predictive control for sequential decision policies in adaptive behavioral interventions",
abstract = "Control engineering offers a systematic and efficient method to optimize the effectiveness of individually tailored treatment and prevention policies known as adaptive or 'just-in-time' behavioral interventions. The nature of these interventions requires assigning dosages at categorical levels, which has been addressed in prior work using Mixed Logical Dynamical (MLD)-based hybrid model predictive control (HMPC) schemes. However, certain requirements of adaptive behavioral interventions that involve sequential decision making have not been comprehensively explored in the literature. This paper presents an extension of the traditional MLD framework for HMPC by representing the requirements of sequential decision policies as mixed-integer linear constraints. This is accomplished with user-specified dosage sequence tables, manipulation of one input at a time, and a switching time strategy for assigning dosages at time intervals less frequent than the measurement sampling interval. A model developed for a gestational weight gain (GWG) intervention is used to illustrate the generation of these sequential decision policies and their effectiveness for implementing adaptive behavioral interventions involving multiple components.",
author = "Yuwen Dong and Sunil Deshpande and Rivera, {Daniel E.} and Downs, {Danielle Symons} and Williams, {Jennifer Savage}",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/ACC.2014.6859462",
language = "English (US)",
isbn = "9781479932726",
series = "Proceedings of the American Control Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4198--4203",
booktitle = "2014 American Control Conference, ACC 2014",
address = "United States",

}

Dong, Y, Deshpande, S, Rivera, DE, Downs, DS & Williams, JS 2014, Hybrid model predictive control for sequential decision policies in adaptive behavioral interventions. in 2014 American Control Conference, ACC 2014., 6859462, Proceedings of the American Control Conference, Institute of Electrical and Electronics Engineers Inc., pp. 4198-4203, 2014 American Control Conference, ACC 2014, Portland, OR, United States, 6/4/14. https://doi.org/10.1109/ACC.2014.6859462

Hybrid model predictive control for sequential decision policies in adaptive behavioral interventions. / Dong, Yuwen; Deshpande, Sunil; Rivera, Daniel E.; Downs, Danielle Symons; Williams, Jennifer Savage.

2014 American Control Conference, ACC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 4198-4203 6859462 (Proceedings of the American Control Conference).

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

TY - GEN

T1 - Hybrid model predictive control for sequential decision policies in adaptive behavioral interventions

AU - Dong, Yuwen

AU - Deshpande, Sunil

AU - Rivera, Daniel E.

AU - Downs, Danielle Symons

AU - Williams, Jennifer Savage

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Control engineering offers a systematic and efficient method to optimize the effectiveness of individually tailored treatment and prevention policies known as adaptive or 'just-in-time' behavioral interventions. The nature of these interventions requires assigning dosages at categorical levels, which has been addressed in prior work using Mixed Logical Dynamical (MLD)-based hybrid model predictive control (HMPC) schemes. However, certain requirements of adaptive behavioral interventions that involve sequential decision making have not been comprehensively explored in the literature. This paper presents an extension of the traditional MLD framework for HMPC by representing the requirements of sequential decision policies as mixed-integer linear constraints. This is accomplished with user-specified dosage sequence tables, manipulation of one input at a time, and a switching time strategy for assigning dosages at time intervals less frequent than the measurement sampling interval. A model developed for a gestational weight gain (GWG) intervention is used to illustrate the generation of these sequential decision policies and their effectiveness for implementing adaptive behavioral interventions involving multiple components.

AB - Control engineering offers a systematic and efficient method to optimize the effectiveness of individually tailored treatment and prevention policies known as adaptive or 'just-in-time' behavioral interventions. The nature of these interventions requires assigning dosages at categorical levels, which has been addressed in prior work using Mixed Logical Dynamical (MLD)-based hybrid model predictive control (HMPC) schemes. However, certain requirements of adaptive behavioral interventions that involve sequential decision making have not been comprehensively explored in the literature. This paper presents an extension of the traditional MLD framework for HMPC by representing the requirements of sequential decision policies as mixed-integer linear constraints. This is accomplished with user-specified dosage sequence tables, manipulation of one input at a time, and a switching time strategy for assigning dosages at time intervals less frequent than the measurement sampling interval. A model developed for a gestational weight gain (GWG) intervention is used to illustrate the generation of these sequential decision policies and their effectiveness for implementing adaptive behavioral interventions involving multiple components.

UR - http://www.scopus.com/inward/record.url?scp=84905715507&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905715507&partnerID=8YFLogxK

U2 - 10.1109/ACC.2014.6859462

DO - 10.1109/ACC.2014.6859462

M3 - Conference contribution

SN - 9781479932726

T3 - Proceedings of the American Control Conference

SP - 4198

EP - 4203

BT - 2014 American Control Conference, ACC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Dong Y, Deshpande S, Rivera DE, Downs DS, Williams JS. Hybrid model predictive control for sequential decision policies in adaptive behavioral interventions. In 2014 American Control Conference, ACC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 4198-4203. 6859462. (Proceedings of the American Control Conference). https://doi.org/10.1109/ACC.2014.6859462