A generic concept to increase the robustness of embedded systems by trust management

Brockmann, Werner; Buschermöhle, Andreas; Hülsmann, Jens

doi:10.1109/icsmc.2010.5641720

Cited by 6 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work also shows how trust management can be incorporated into a continuous signal processing task [2]. Complementary to that, the work presented here is intended to show how to balance the performance and trustworthiness of classification algorithms, i.e.…”

Section: Motivation and Backgroundmentioning

confidence: 96%

“…In [2] we therefor introduced a generic framework called trust management. One main focus of trust management is to deal with (dynamic) uncertainties explicitly and to make them as comprehensible as possible.…”

Section: Motivation and Backgroundmentioning

confidence: 99%

“…In the framework of trust management [2], a trust signal is a meta-information to a normal signal, e.g. a sensor-reading, or to an internally generated signal, which depends on uncertain information.…”

Section: Uncertainty Representationmentioning

confidence: 99%

See 2 more Smart Citations

Incorporating Dynamic Uncertainties into a Fuzzy Classifier

Hülsmann

Buschermöhle

Brockmann

2011

Proceedings of the 7th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-2011)

Self Cite

View full text Add to dashboard Cite

Dealing with classification problems in practice often has to cope with uncertain information, either in the training or in the operation phase or both. Modeling these uncertainties allows to enhance the robustness or performance of the classifier. In this paper we focus on the operation phase and present a general, but simple extension to rule based fuzzy classifier to do so. Therefor uncertain features are gradually and dimension wise faded out of the classification process. An artificial two-dimensional dataset is used to visualize the effectiveness of this approach. Investigations on three benchmark datasets shows the performance and gain in robustness.

show abstract

Section: Motivation and Backgroundmentioning

confidence: 96%

Section: Motivation and Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

Incorporating Dynamic Uncertainties into a Fuzzy Classifier

Hülsmann

Buschermöhle

Brockmann

2011

Proceedings of the 7th Conference of the European Society for Fuzzy Logic and Technology (EUSFLAT-2011)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The idea of health signals has been put further by envisioning a complete framework for trust management for embedded systems [14]. There, it has been shown that the explicit uncertainty representation by trust or health signals yield results which are superior to simplified gaussian models and which come close to the theoretical optimum.…”

Section: State Of the Artmentioning

confidence: 98%

“…But for the blending scheme, only one health signal is used. To handle this, one can either use one of the health signals, e.g., the one attributing the most critical input signal, or fuse the health signals by a suitable operator [14]. This allows for greater flexibility and expressiveness, but requires some more knowledge from the engineer concerning the relation of the signals.…”

Section: F Strategy Blendingmentioning

confidence: 99%

Tackling uncertainties in self-optimizing systems by strategy blending

Rosemann

Brockmann

Hanel

2011

2011 IEEE Workshop on Evolving and Adaptive Intelligent Systems (EAIS)

Self Cite

View full text Add to dashboard Cite

Complex technical applications often show severe uncertainties, which may vary over time, e.g., situation dependent sensor inaccuracies or anomalies and faults. In order to ease the engineering process for such systems, organic computing principles, e.g., self-adaptation and self-optimization, offer a solution. Hence, machine learning paradigms are needed which work online and which can cope with such dynamically varying uncertainties, but still operate safely all the time. In this work, such a learning paradigm is developed based on the Organic Robot Control Architecture and the incremental learning scheme Directed Self-Learning. It is combined with an explicit uncertainty representation. The core idea is to use a strategy blending scheme to show a good performance and improve it by selfoptimizing learning on the one hand in case of high trust, or low uncertainty, respectively. On the other hand, a robust fallback-system is used to ensure safety in situations of high uncertainty. Of course, in such situations learned knowledge has to be protected from corruption. The feasibility of this approach is demonstrated in a simulated pick-and-place scenario with unknown, but changing load masses.

show abstract

Classification of Uncertain Data: An Application in Nondestructive Testing

Hülsmann

Brockmann

2012

Communications in Computer and Information Science

View full text Add to dashboard Cite

A generic concept to increase the robustness of embedded systems by trust management

Cited by 6 publications

References 9 publications

Incorporating Dynamic Uncertainties into a Fuzzy Classifier

Incorporating Dynamic Uncertainties into a Fuzzy Classifier

Tackling uncertainties in self-optimizing systems by strategy blending

Classification of Uncertain Data: An Application in Nondestructive Testing

Contact Info

Product

Resources

About