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

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

4 Scopus citations

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

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

Fingerprint Dive into the research topics of 'HyMn: Mining linear hybrid automata from input output traces of cyber-physical systems'. Together they form a unique fingerprint.

  • 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