HyMn: Mining linear hybrid automata from input output traces of cyber-physical systems

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

3 Citations (Scopus)

Abstract

Hybrid systems are versatile in modeling the interaction between the cyber and physical components of cyber-physical control systems (CPS) such as artificial pancreas (AP). They are typically used for analysis of safety of the human centric control systems which have serious consequences of failure. As such hybrid systems are parameterized and the variables often depend on the subject on which the control system is deployed. Traditionally, control systems are initially developed using average statistical estimates of the subject specific parameters. However, such excursions may lead to suboptimal designs. In this paper, we propose HyMn, a hybrid system parameter estimation tool, where the subject specific parameters in a hybrid system are automatically learned from experimental traces of the operation of a human centric CPS control system. We apply HyMn to the AP system and show that the blood glucose control is enhanced using the learned patient specific parameters.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages264-269
Number of pages6
ISBN (Electronic)9781538665312
DOIs
StatePublished - Jun 15 2018
Event1st IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2018 - Saint Petersburg, Russian Federation
Duration: May 15 2018May 18 2018

Other

Other1st IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2018
CountryRussian Federation
CitySaint Petersburg
Period5/15/185/18/18

Fingerprint

Hybrid Automata
Mining
Trace
Control System
Hybrid systems
Control systems
Hybrid Systems
Output
Excursion
Glucose
Parameter estimation
Blood
Parameter Estimation
Cyber Physical System
Safety
Interaction
Modeling
Estimate

Keywords

  • Artificial Pancreas
  • CPS
  • Cramer-Rao Bound
  • Fisher Information
  • Mining hybrid automata

ASJC Scopus subject areas

  • Artificial Intelligence
  • Hardware and Architecture
  • Control and Optimization
  • Industrial and Manufacturing Engineering

Cite this

Lamrani, I., Banerjee, A., & Gupta, S. (2018). HyMn: Mining linear hybrid automata from input output traces of cyber-physical systems. In Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018 (pp. 264-269). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICPHYS.2018.8387670

HyMn : Mining linear hybrid automata from input output traces of cyber-physical systems. / Lamrani, Imane; Banerjee, Ayan; Gupta, Sandeep.

Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 264-269.

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

Lamrani, I, Banerjee, A & Gupta, S 2018, HyMn: Mining linear hybrid automata from input output traces of cyber-physical systems. in Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018. Institute of Electrical and Electronics Engineers Inc., pp. 264-269, 1st IEEE International Conference on Industrial Cyber-Physical Systems, ICPS 2018, Saint Petersburg, Russian Federation, 5/15/18. https://doi.org/10.1109/ICPHYS.2018.8387670
Lamrani I, Banerjee A, Gupta S. HyMn: Mining linear hybrid automata from input output traces of cyber-physical systems. In Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 264-269 https://doi.org/10.1109/ICPHYS.2018.8387670
Lamrani, Imane ; Banerjee, Ayan ; Gupta, Sandeep. / HyMn : Mining linear hybrid automata from input output traces of cyber-physical systems. Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 264-269
@inproceedings{122f049f194643ea91e8c22396c0411d,
title = "HyMn: Mining linear hybrid automata from input output traces of cyber-physical systems",
abstract = "Hybrid systems are versatile in modeling the interaction between the cyber and physical components of cyber-physical control systems (CPS) such as artificial pancreas (AP). They are typically used for analysis of safety of the human centric control systems which have serious consequences of failure. As such hybrid systems are parameterized and the variables often depend on the subject on which the control system is deployed. Traditionally, control systems are initially developed using average statistical estimates of the subject specific parameters. However, such excursions may lead to suboptimal designs. In this paper, we propose HyMn, a hybrid system parameter estimation tool, where the subject specific parameters in a hybrid system are automatically learned from experimental traces of the operation of a human centric CPS control system. We apply HyMn to the AP system and show that the blood glucose control is enhanced using the learned patient specific parameters.",
keywords = "Artificial Pancreas, CPS, Cramer-Rao Bound, Fisher Information, Mining hybrid automata",
author = "Imane Lamrani and Ayan Banerjee and Sandeep Gupta",
year = "2018",
month = "6",
day = "15",
doi = "10.1109/ICPHYS.2018.8387670",
language = "English (US)",
pages = "264--269",
booktitle = "Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - HyMn

T2 - Mining linear hybrid automata from input output traces of cyber-physical systems

AU - Lamrani, Imane

AU - Banerjee, Ayan

AU - Gupta, Sandeep

PY - 2018/6/15

Y1 - 2018/6/15

N2 - Hybrid systems are versatile in modeling the interaction between the cyber and physical components of cyber-physical control systems (CPS) such as artificial pancreas (AP). They are typically used for analysis of safety of the human centric control systems which have serious consequences of failure. As such hybrid systems are parameterized and the variables often depend on the subject on which the control system is deployed. Traditionally, control systems are initially developed using average statistical estimates of the subject specific parameters. However, such excursions may lead to suboptimal designs. In this paper, we propose HyMn, a hybrid system parameter estimation tool, where the subject specific parameters in a hybrid system are automatically learned from experimental traces of the operation of a human centric CPS control system. We apply HyMn to the AP system and show that the blood glucose control is enhanced using the learned patient specific parameters.

AB - Hybrid systems are versatile in modeling the interaction between the cyber and physical components of cyber-physical control systems (CPS) such as artificial pancreas (AP). They are typically used for analysis of safety of the human centric control systems which have serious consequences of failure. As such hybrid systems are parameterized and the variables often depend on the subject on which the control system is deployed. Traditionally, control systems are initially developed using average statistical estimates of the subject specific parameters. However, such excursions may lead to suboptimal designs. In this paper, we propose HyMn, a hybrid system parameter estimation tool, where the subject specific parameters in a hybrid system are automatically learned from experimental traces of the operation of a human centric CPS control system. We apply HyMn to the AP system and show that the blood glucose control is enhanced using the learned patient specific parameters.

KW - Artificial Pancreas

KW - CPS

KW - Cramer-Rao Bound

KW - Fisher Information

KW - Mining hybrid automata

UR - http://www.scopus.com/inward/record.url?scp=85050078377&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050078377&partnerID=8YFLogxK

U2 - 10.1109/ICPHYS.2018.8387670

DO - 10.1109/ICPHYS.2018.8387670

M3 - Conference contribution

AN - SCOPUS:85050078377

SP - 264

EP - 269

BT - Proceedings - 2018 IEEE Industrial Cyber-Physical Systems, ICPS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -