The Diagnostic Competitions

Feldman, Alexander; Kleer, Johan de; Kurtoglu, Tolga; Narasimhan, Sriram; Poll, Scott; García, David; Kuhn, Lukas; Gemund, Arjan J. C. van

doi:10.1609/aimag.v35i2.2532

Cited by 2 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, some approaches exploit a truth maintenance system [15], others exploit fault probabilities to guide the process [16] (in the case of recommendation, this approach would exploit probability estimates for the items to be recommended); others are based on the pre-compilation of guiding heuristics [12], and still others exploit OBDD [49]. All of them show that diagnoses can be effectively computed and indeed the community established a competition for the design of efficient diagnosers (see [19]).…”

Section: Complexity and Efficient Algorithmsmentioning

confidence: 99%

Logical foundations of knowledge-based recommender systems: A unifying spectrum of alternatives

Cena

Console

Vernero

2021

Information Sciences

View full text Add to dashboard Cite

The aim of this paper is to provide logical foundations for knowledge-based recommender systems, for which, unlike other problem solving tasks, a comprehensive formalization is not yet available. This goal is justified by the need to compare recommenders based on the way they use knowledge to generate recommendations and, consequently, on the underlying semantics of the recommendation process itself. Moreover, since the here adopted logical formalization has been borrowed from other tasks such as diagnosis, many interesting results and opportunities can be transposed from such tasks to recommendation. While we do not aim at proposing a new recommendation generation technique, we believe that our formalization will be the basis for unifying different approaches to knowledge-based recommendation, revealing their semantics and offering a conceptual framework to compare them. In fact, the framework covers different variations of knowledge-based recommendation, such as context-aware, constraints-based, package and group recommendation, as well as recommendation based on negative preferences.

show abstract

Section: Complexity and Efficient Algorithmsmentioning

confidence: 99%

Logical foundations of knowledge-based recommender systems: A unifying spectrum of alternatives

Cena

Console

Vernero

2021

Information Sciences

View full text Add to dashboard Cite

show abstract

“…The term predictive accuracy is dependent on the respective PHM task and is evaluated by different metrics, some of which are subject-specific. Typical examples of these metrics are for fault detection fault detection rate, for diagnosis isolation classification rate, for health assessment root mean squared error, and for prognosis prognostic horizon (Saxena et al, 2010;Feldman et al, 2010;Gao et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

On the Integration of Fundamental Knowledge about Degradation Processes into Data-Driven Diagnostics and Prognostics Using Theory-Guided Data Science

Hagmeyer

Zeiler²,

Huber³

2022

PHME_CONF

View full text Add to dashboard Cite

In Prognostics and Health Management, there are three main approaches for implementing diagnostic and prognostic applications. These approaches are data-driven methods, physical model-based methods, and combinations of them, in the form of hybrid methods. Each of them has specific advantages but also limitations for their purposeful implementation. In the case of data-driven methods, one of the main limitations is the availability of sufficient training data that adequately cover the relevant state space. For model-based methods, on the other hand, it is often the case that the degradation process of the considered technical system is of significant complexity. In such a scenario physics-based modeling requires great effort or is not possible at all. Combinations of data-driven and model-based approaches in form of hybrid approaches offer the possibility to partially mitigate the shortcomings of the other two approaches, however, require a sufficiently detailed data-driven and physics-based model. This paper addresses the transitional field between data-driven and hybrid approaches. Despite the issues of formulating a physics-based model that provides a representation of the degradation process, basic knowledge of the considered system and of the laws governing its degradation process is usually available. Integration of such knowledge into a machine learning process is part of a research field that is either called theory-guided data science, (physics) informed machine learning, physics-based learning or physics guided machine learning. First, the state of research in Prognostics and Health Management on methods of this field is presented and existing research gaps are outlined. Then, a concept is introduced for incorporating fundamental knowledge, such as monotonicity constraints, into data-driven diagnostic and prognostic applications using approaches from theory-guided data science. A special aspect of this concept is its cross-application usability through the consideration of knowledge that repeatedly occurs in diagnostics and prognostics. This is, for example, knowledge about physically justified boundaries whose compliance makes a prediction of the data-driven model plausible in the first place.

show abstract

The Diagnostic Competitions

Abstract: The diagnostic competition (DX) provides a set of diagnostic benchmarks to evaluate diagnostic algorithms. This paper describes a common diagnostic framework used to evaluate diagnostic algorithms. This competition, started in 2009, has significantly helped shape diagnostic algorithms.

Cited by 2 publications

References 6 publications

Logical foundations of knowledge-based recommender systems: A unifying spectrum of alternatives

Logical foundations of knowledge-based recommender systems: A unifying spectrum of alternatives

On the Integration of Fundamental Knowledge about Degradation Processes into Data-Driven Diagnostics and Prognostics Using Theory-Guided Data Science

Contact Info

Product

Resources

About