skip to main content
10.1145/3550356.3561554acmconferencesArticle/Chapter ViewAbstractPublication PagesmodelsConference Proceedingsconference-collections
research-article

Multi-scale model-based explanations for cyber-physical systems: the urban traffic case

Published: 09 November 2022 Publication History

Abstract

Automated control in Cyber-Physical Systems (CPS) generates behaviours that may surprise non-expert users. Relevant explanations are required to maintain user trust. Large CPS (e.g., autonomous car networks and smart grids) raise additional scaleability issues for the explanatory processes and complexity issues for generated explanations. We propose a multi-scale system modelling and explanation technique to address these concerns. The idea is to increase the scale, or abstraction level, of the modelled CPS, whenever possible without loss of salient information, so as to produce smaller system representations and hence to reduce the complexity of the explanatory process and of the generated explanations. We illustrate our proposal via an urban traffic case study, modelling traffic at two different scales (i.e., modelling individual cars at a lower-scale; and traffic jams at a higher-scale). We show how a multi-scale explanatory process can use the lower- and higher-scale models to generate either longer (more detailed) explanations, or shorter (more abstract) explanations, respectively. This proof-of-concept illustration offers a basis for further research towards a comprehensive multi-scale explanatory solution for CPS.

References

[1]
2016. Explainable Artificial Intelligence. Broad Agency Anouncement DARPA-BAA-16-53. DARPA.
[2]
Moussa Amrani, Dominique Blouin, Robert Heinrich, Arend Rensink, Hans Vangheluwe, and Andreas Wortmann. 2021. Multiparadigm modelling for cyber-physical systems: a descriptive framework. Software and Systems Modeling 20, 3 (2021), 611--639.
[3]
Alejandro Barredo Arrieta and et. al. 2020. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion 58 (2020), 82--115. Publisher: Elsevier.
[4]
Jean-Louis Dessalles. 2016. A Cognitive Approach to Relevant Argument Generation. In Principles and Practice of Multi-Agent Systems. 3--15.
[5]
A. Diaconescu, L. Di Felice, and P. Mellodge. 2021. An Information-oriented View of Multi-Scale Systems. In IEEE SISSY / ACSOS. 154--159.
[6]
Ada Diaconescu, Louisa Jane Di Felice, and Patricia Mellodge. 2021. Exogenous coordination in multi-scale systems: How information flows and timing affect system properties. Future Generation Computer Systems 114 (2021), 403--426.
[7]
J.L. Dessalles E. Houze°, A. Diaconescu and D. Menga. 2022. A generic and modular architecture for self-explainable smart homes. In IEEE ACSOS.
[8]
Kanvaly Fadiga, Etienne Houzé, Ada Diaconescu, and Jean-Louis Dessalles. 2021. To do or not to do: finding causal relations in smart homes. In IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS). IEEE, Online, 110--119.
[9]
Romain Franceschini, Bentley James Oakes, Simon Van Mierlo, Moharram Challenger, and Hans Vangheluwe. 2020. Towards Adaptive Abstraction for Continuous Time Models with Dynamic Structure. Association for Computing Machinery, New York, NY, USA.
[10]
B. Goodman and S. Flaxman. 2017. EU Regulations on Algorithmic Decision-Making and a "Right to Explanation". AI Magazine 38, 3 (2017), 50--57.
[11]
Étienne Houzé, Jean-Louis Dessalles, Ada Diaconescu, David Menga, and Mathieu Schumann. 2022. A Decentralized Explanatory System for Intelligent Cyber-Physical Systems. In Intelligent Systems and Applications, Kohei Arai (Ed.). Springer International Publishing, Cham, 719--738.
[12]
Étienne Houzé, Jean-Louis Dessalles, Ada Diaconescu, and David Menga. 2022. What Should I Notice? Using Algorithmic Information Theory to Evaluate the Memorability of Events in Smart Homes. Entropy 24, 3 (2022).
[13]
S.M. Lundberg and S.I. Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Info. Processing Systems. 4765--4774.
[14]
Tim Miller, Piers Howe, and Liz Sonenberg. 2017. Explainable AI: Beware of inmates running the asylum or: How I learnt to stop worrying and love the social and behavioural sciences. arXiv preprint arXiv:1712.00547 (2017).
[15]
J. Pearl. 2018. The Book of Why: The New Science of Cause and Effect. Science 361, 6405 (2018), 855--855.
[16]
M.T. Ribeiro, S. Singh, and C. Guestrin. 2016. Why should I trust you?: Explaining the predictions of any classifier. In ACM SIGKDD ECAI. 1135--1144.

Cited By

View all
  • (2024)A Roadmap for Causality Research in Complex Adaptive Systems2024 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)10.1109/ACSOS-C63493.2024.00027(35-40)Online publication date: 16-Sep-2024

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
MODELS '22: Proceedings of the 25th International Conference on Model Driven Engineering Languages and Systems: Companion Proceedings
October 2022
1003 pages
ISBN:9781450394673
DOI:10.1145/3550356
  • Conference Chairs:
  • Thomas Kühn,
  • Vasco Sousa
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Sponsors

In-Cooperation

  • Univ. of Montreal: University of Montreal
  • IEEE CS

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 09 November 2022

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. cyber-physical system
  2. multi-scale model and explanation
  3. traffic simulation

Qualifiers

  • Research-article

Conference

MODELS '22
Sponsor:

Acceptance Rates

Overall Acceptance Rate 144 of 506 submissions, 28%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)11
  • Downloads (Last 6 weeks)1
Reflects downloads up to 14 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)A Roadmap for Causality Research in Complex Adaptive Systems2024 IEEE International Conference on Autonomic Computing and Self-Organizing Systems Companion (ACSOS-C)10.1109/ACSOS-C63493.2024.00027(35-40)Online publication date: 16-Sep-2024

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media