%0 Conference Proceedings
%T Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning
%+ Graz University of Technology [Graz] (TU Graz)
%A Aichernig, Bernhard, K.
%A Bloem, Roderick
%A Ebrahimi, Masoud
%A Horn, Martin
%A Pernkopf, Franz
%A Roth, Wolfgang
%A Rupp, Astrid
%A Tappler, Martin
%A Tranninger, Markus
%Z Part 1: Test and Artificial Intelligence
%< avec comité de lecture
%( Lecture Notes in Computer Science
%B 31th IFIP International Conference on Testing Software and Systems (ICTSS)
%C Paris, France
%Y Christophe Gaston
%Y Nikolai Kosmatov
%Y Pascale Le Gall
%I Springer International Publishing
%3 Testing Software and Systems
%V LNCS-11812
%P 3-21
%8 2019-10-15
%D 2019
%R 10.1007/978-3-030-31280-0_1
%K Hybrid systems
%K Behavior modeling
%K Automata learning
%K Model-Based Testing
%K Machine learning
%K Autonomous vehicle
%K Platooning
%Z Computer Science [cs]
%Z Computer Science [cs]/Networking and Internet Architecture [cs.NI]Conference papers
%X 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.
%G English
%Z TC 6
%Z WG 6.1
%2 https://inria.hal.science/hal-02526358/document
%2 https://inria.hal.science/hal-02526358/file/482770_1_En_1_Chapter.pdf
%L hal-02526358
%U https://inria.hal.science/hal-02526358
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-TC
%~ IFIP-WG
%~ IFIP-TC6
%~ IFIP-WG6-1
%~ IFIP-ICTSS
%~ IFIP-LNCS-11812