Models play an essential role in the design process of cyber-physical systems. They form the basis for simulation and analysis and help in identifying design problems as early as possible. However, the construction of models that comprise physical and digital behavior is challenging. Therefore, there is considerable interest in learning such hybrid behavior by means of machine learning which requires sufficient and representative training data covering the behavior of the physical system adequately. In this work, we exploit a combination of automata learning and model-based testing to generate sufficient training data fully automatically.

Experimental results on a platooning scenario show that recurrent neural networks learned with this data achieved significantly better results compared to models learned from randomly generated data. In particular, the classification error for crash detection is reduced by a factor of five and a similar F1-score is obtained with up to three orders of magnitude fewer training samples.

TitelTesting Software and Systems
Untertitel31st IFIP WG 6.1 International Conference, ICTSS 2019, Paris, France, October 15–17, 2019, Proceedings
Redakteure/-innenChristophe Gaston, Nikolai Kosmatov, Pascale Le Gall
Herausgeber (Verlag)Springer International Publishing AG
ISBN (Print)978-3-030-31280-0
PublikationsstatusVeröffentlicht - 2019
VeranstaltungIFIP-ICTSS 2019: 31st IFIP International Conference on Testing Software and Systems - Paris, Frankreich
Dauer: 15 Okt 201917 Okt 2019


NameLecture Notes in Computer Science


KonferenzIFIP-ICTSS 2019

Fingerprint Untersuchen Sie die Forschungsthemen von „Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren