Long-term prediction for T1DM model during state-feedback control

Peter Szalay, Z. Benyó, L. Kovács

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

3 Citations (Scopus)

Abstract

Avoiding low glucose concentration is critically important in type-1 diabetes treatment. Predicting the future plasma glucose levels could ensure the safety of the patient. However, such estimation is no trivial task. The current paper proposes a predictor framework which stems from Unscented Kalman filter and works during closed-loop control, that can predict hazardous glucose levels in advance. Once the blood glucose concentration starts to rise, the predictor activates and estimates future glucose levels up to 3 hours, confirming whether the controller can endanger the patient. The capabilities of the framework is presented through simulations based on the SimEdu validated in-silico simulator.

Original languageEnglish
Title of host publication12th IEEE International Conference on Control and Automation, ICCA 2016
PublisherIEEE Computer Society
Pages311-316
Number of pages6
Volume2016-July
ISBN (Electronic)9781509017386
DOIs
Publication statusPublished - Jul 5 2016
Event12th IEEE International Conference on Control and Automation, ICCA 2016 - Kathmandu, Nepal
Duration: Jun 1 2016Jun 3 2016

Other

Other12th IEEE International Conference on Control and Automation, ICCA 2016
CountryNepal
CityKathmandu
Period6/1/166/3/16

Fingerprint

State feedback
Feedback control
Glucose
Medical problems
Kalman filters
Blood
Simulators
Plasmas
Controllers

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Control and Systems Engineering
  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering

Cite this

Szalay, P., Benyó, Z., & Kovács, L. (2016). Long-term prediction for T1DM model during state-feedback control. In 12th IEEE International Conference on Control and Automation, ICCA 2016 (Vol. 2016-July, pp. 311-316). [7505295] IEEE Computer Society. https://doi.org/10.1109/ICCA.2016.7505295

Long-term prediction for T1DM model during state-feedback control. / Szalay, Peter; Benyó, Z.; Kovács, L.

12th IEEE International Conference on Control and Automation, ICCA 2016. Vol. 2016-July IEEE Computer Society, 2016. p. 311-316 7505295.

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

Szalay, P, Benyó, Z & Kovács, L 2016, Long-term prediction for T1DM model during state-feedback control. in 12th IEEE International Conference on Control and Automation, ICCA 2016. vol. 2016-July, 7505295, IEEE Computer Society, pp. 311-316, 12th IEEE International Conference on Control and Automation, ICCA 2016, Kathmandu, Nepal, 6/1/16. https://doi.org/10.1109/ICCA.2016.7505295
Szalay P, Benyó Z, Kovács L. Long-term prediction for T1DM model during state-feedback control. In 12th IEEE International Conference on Control and Automation, ICCA 2016. Vol. 2016-July. IEEE Computer Society. 2016. p. 311-316. 7505295 https://doi.org/10.1109/ICCA.2016.7505295
Szalay, Peter ; Benyó, Z. ; Kovács, L. / Long-term prediction for T1DM model during state-feedback control. 12th IEEE International Conference on Control and Automation, ICCA 2016. Vol. 2016-July IEEE Computer Society, 2016. pp. 311-316
@inproceedings{830d39a489ef4e0295bbe2c8e31ea692,
title = "Long-term prediction for T1DM model during state-feedback control",
abstract = "Avoiding low glucose concentration is critically important in type-1 diabetes treatment. Predicting the future plasma glucose levels could ensure the safety of the patient. However, such estimation is no trivial task. The current paper proposes a predictor framework which stems from Unscented Kalman filter and works during closed-loop control, that can predict hazardous glucose levels in advance. Once the blood glucose concentration starts to rise, the predictor activates and estimates future glucose levels up to 3 hours, confirming whether the controller can endanger the patient. The capabilities of the framework is presented through simulations based on the SimEdu validated in-silico simulator.",
author = "Peter Szalay and Z. Beny{\'o} and L. Kov{\'a}cs",
year = "2016",
month = "7",
day = "5",
doi = "10.1109/ICCA.2016.7505295",
language = "English",
volume = "2016-July",
pages = "311--316",
booktitle = "12th IEEE International Conference on Control and Automation, ICCA 2016",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Long-term prediction for T1DM model during state-feedback control

AU - Szalay, Peter

AU - Benyó, Z.

AU - Kovács, L.

PY - 2016/7/5

Y1 - 2016/7/5

N2 - Avoiding low glucose concentration is critically important in type-1 diabetes treatment. Predicting the future plasma glucose levels could ensure the safety of the patient. However, such estimation is no trivial task. The current paper proposes a predictor framework which stems from Unscented Kalman filter and works during closed-loop control, that can predict hazardous glucose levels in advance. Once the blood glucose concentration starts to rise, the predictor activates and estimates future glucose levels up to 3 hours, confirming whether the controller can endanger the patient. The capabilities of the framework is presented through simulations based on the SimEdu validated in-silico simulator.

AB - Avoiding low glucose concentration is critically important in type-1 diabetes treatment. Predicting the future plasma glucose levels could ensure the safety of the patient. However, such estimation is no trivial task. The current paper proposes a predictor framework which stems from Unscented Kalman filter and works during closed-loop control, that can predict hazardous glucose levels in advance. Once the blood glucose concentration starts to rise, the predictor activates and estimates future glucose levels up to 3 hours, confirming whether the controller can endanger the patient. The capabilities of the framework is presented through simulations based on the SimEdu validated in-silico simulator.

UR - http://www.scopus.com/inward/record.url?scp=84979780919&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84979780919&partnerID=8YFLogxK

U2 - 10.1109/ICCA.2016.7505295

DO - 10.1109/ICCA.2016.7505295

M3 - Conference contribution

AN - SCOPUS:84979780919

VL - 2016-July

SP - 311

EP - 316

BT - 12th IEEE International Conference on Control and Automation, ICCA 2016

PB - IEEE Computer Society

ER -