Dynamic Context Modeling for Cyber-Physical Systems Applied to a Pill Dispenser

Sahlab, Nada; Jazdi, Nasser; Weyrich, Michael

doi:10.1109/etfa46521.2020.9211876

Cited by 6 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, to understand the CI on CPS, it is crucial to access the context data. To this end, several projects [17,22] use semantic technologies to model and scope the context of a CPS.…”

Section: Related Workmentioning

confidence: 99%

“…However, in recent years many automated techniques have been proposed to enrich a KG with new knowledge [4]. A recent work [22] uses KG to model context, and its relationship with the CPS highlights that such relationships are uncertain due to its dynamicity. Thus, supporting methods for discovering relationships should be considered.…”

Section: Context Modelingmentioning

confidence: 99%

“…To investigate CIs of a CPS, it is essential to first define the context of this CPS. Following different definitions of context coined over the past decades, such as Dey's popular definition [7] and a recent CPS-oriented one [22], we define the system-oriented context of a CPS as the observable entities in the physical or virtual vicinity of a CPS that could influence the functioning of such a CPS. We provide further details on context and its modeling for the proposed system in Section 3.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Poster: Towards Explaining the Effects of Contextual Influences on Cyber-Physical Systems

Jha

Mayer

García

2021

Proceedings of the 11th International Conference on the Internet of Things

View full text Add to dashboard Cite

The increasing complexity of Cyber-Physical Systems (CPS) increases the difficulty for users to understand their behavior. Using existing Explainable Artificial Intelligence (XAI) methods, CPS can explain their behavior to the users. However, the input-output correlations used in XAI methods are not capable of explaining certain anomalies on CPS behavior caused by contextual influences (CIs) since they do not consider the context of the CPS. Some well-known techniques used for understanding such CIs on CPS are test chambers and the analysis of logged CPS data. However, test chambers are typically only available to the manufacturer of a CPS, thus not useful for understanding CIs on the shop floors. Data analysis methods focus on data correlations, which are insufficient to explain causal relationships without using expert (human) knowledge. Hence, we propose a context-aware log-based explanation system to explain the causal relationship between CIs and the behavior of a CPS. The proposed solution employs semantic technologies to access the context of the CPS. It demonstrates the causal relationship between the CPS and CIs through counterfactual explanation and abductive reasoning methods. The contextual explanations offered by the proposed system will assist users in visualizing diverse scenarios in order to improve the CPS' behavior accordingly. CCS CONCEPTS• Computing methodologies → Causal reasoning and diagnostics; Machine learning; • Human-centered computing → Text input.

show abstract

“…Moreover, to understand the CI on CPS, it is crucial to access the context data. To this end, several projects [17,22] use semantic technologies to model and scope the context of a CPS.…”

Section: Related Workmentioning

confidence: 99%

Section: Context Modelingmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation