Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Analyzing Complex Systems with Cascades Using Continuous-Time Bayesian Networks

Bregoli, Alessandro ; Rathsman, Karin LU ; Scutari, Marco ; Stella, Fabio and Mogensen, Søren Wengel LU (2023) 30th International Symposium on Temporal Representation and Reasoning, TIME 2023
Abstract

Interacting systems of events may exhibit cascading behavior where events tend to be temporally clustered. While the cascades themselves may be obvious from the data, it is important to understand which states of the system trigger them. For this purpose, we propose a modeling framework based on continuous-time Bayesian networks (CTBNs) to analyze cascading behavior in complex systems. This framework allows us to describe how events propagate through the system and to identify likely sentry states, that is, system states that may lead to imminent cascading behavior. Moreover, CTBNs have a simple graphical representation and provide interpretable outputs, both of which are important when communicating with domain experts. We also develop... (More)

Interacting systems of events may exhibit cascading behavior where events tend to be temporally clustered. While the cascades themselves may be obvious from the data, it is important to understand which states of the system trigger them. For this purpose, we propose a modeling framework based on continuous-time Bayesian networks (CTBNs) to analyze cascading behavior in complex systems. This framework allows us to describe how events propagate through the system and to identify likely sentry states, that is, system states that may lead to imminent cascading behavior. Moreover, CTBNs have a simple graphical representation and provide interpretable outputs, both of which are important when communicating with domain experts. We also develop new methods for knowledge extraction from CTBNs and we apply the proposed methodology to a data set of alarms in a large industrial system.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
alarm network, continuous-time Bayesian network, event cascade, event model, graphical models
host publication
30th International Symposium on Temporal Representation and Reasoning, TIME 2023
editor
Artikis, Alexander ; Bruse, Florian and Hunsberger, Luke
article number
8
publisher
Schloss Dagstuhl - Leibniz-Zentrum für Informatik
conference name
30th International Symposium on Temporal Representation and Reasoning, TIME 2023
conference location
Athens, Greece
conference dates
2023-09-25 - 2023-09-26
external identifiers
  • scopus:85174165963
ISBN
9783959772983
DOI
10.4230/LIPIcs.TIME.2023.8
language
English
LU publication?
yes
id
c20a139d-4d72-4337-b585-60437551b21d
date added to LUP
2023-12-11 14:09:38
date last changed
2023-12-11 14:09:38
@inproceedings{c20a139d-4d72-4337-b585-60437551b21d,
  abstract     = {{<p>Interacting systems of events may exhibit cascading behavior where events tend to be temporally clustered. While the cascades themselves may be obvious from the data, it is important to understand which states of the system trigger them. For this purpose, we propose a modeling framework based on continuous-time Bayesian networks (CTBNs) to analyze cascading behavior in complex systems. This framework allows us to describe how events propagate through the system and to identify likely sentry states, that is, system states that may lead to imminent cascading behavior. Moreover, CTBNs have a simple graphical representation and provide interpretable outputs, both of which are important when communicating with domain experts. We also develop new methods for knowledge extraction from CTBNs and we apply the proposed methodology to a data set of alarms in a large industrial system.</p>}},
  author       = {{Bregoli, Alessandro and Rathsman, Karin and Scutari, Marco and Stella, Fabio and Mogensen, Søren Wengel}},
  booktitle    = {{30th International Symposium on Temporal Representation and Reasoning, TIME 2023}},
  editor       = {{Artikis, Alexander and Bruse, Florian and Hunsberger, Luke}},
  isbn         = {{9783959772983}},
  keywords     = {{alarm network; continuous-time Bayesian network; event cascade; event model; graphical models}},
  language     = {{eng}},
  publisher    = {{Schloss Dagstuhl - Leibniz-Zentrum für Informatik}},
  title        = {{Analyzing Complex Systems with Cascades Using Continuous-Time Bayesian Networks}},
  url          = {{http://dx.doi.org/10.4230/LIPIcs.TIME.2023.8}},
  doi          = {{10.4230/LIPIcs.TIME.2023.8}},
  year         = {{2023}},
}