Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning

Bernhard K. Aichernig; Roderick Bloem; Masoud Ebrahimi; Martin Horn; Franz Pernkopf; Wolfgang Roth; Astrid Rupp; Martin Tappler; Markus Tranninger

doi:10.1007/978-3-030-31280-0_1

Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning

Bernhard K. Aichernig, Roderick Bloem, Masoud Ebrahimi, Martin Horn, Franz Pernkopf, Wolfgang Roth, Astrid Rupp, Martin Tappler, Markus Tranninger

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Abstract

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.

Originalsprache	englisch
Titel	Testing Software and Systems
Untertitel	31st IFIP WG 6.1 International Conference, ICTSS 2019, Paris, France, October 15–17, 2019, Proceedings
Redakteure/-innen	Christophe Gaston, Nikolai Kosmatov, Pascale Le Gall
Erscheinungsort	Cham
Herausgeber (Verlag)	Springer International Publishing AG
Seiten	3-21
Seitenumfang	19
ISBN (Print)	978-3-030-31280-0
DOIs	https://doi.org/10.1007/978-3-030-31280-0_1
Publikationsstatus	Veröffentlicht - 2019
Veranstaltung	31st IFIP International Conference on Testing Software and Systems: IFIP-ICTSS 2019 - Paris, Frankreich Dauer: 15 Okt. 2019 → 17 Okt. 2019

Publikationsreihe

Name	Lecture Notes in Computer Science
Band	11812

Konferenz

Konferenz	31st IFIP International Conference on Testing Software and Systems
Land/Gebiet	Frankreich
Ort	Paris
Zeitraum	15/10/19 → 17/10/19

Zugriff auf Dokument

10.1007/978-3-030-31280-0_1

Enable-S3 - Europäische Initiative zur Validierung von hochautomatisierten und sicheren Systeme
Bloem, R. (Teilnehmer (Co-Investigator)), Horn, M. (Teilnehmer (Co-Investigator)), Wotawa, F. (Teilnehmer (Co-Investigator)), Bösch, W. (Teilnehmer (Co-Investigator)) & Eichberger, A. (Teilnehmer (Co-Investigator))
1/05/16 → 30/04/19
Projekt: Forschungsprojekt
Verlaesslichkeit im Internet der Dinge
Boano, C. A. (Teilnehmer (Co-Investigator)), Kubin, G. (Teilnehmer (Co-Investigator)), Bloem, R. (Teilnehmer (Co-Investigator)), Horn, M. (Teilnehmer (Co-Investigator)), Pernkopf, F. (Teilnehmer (Co-Investigator)), Zakany, N. (Teilnehmer (Co-Investigator)), Mangard, S. (Teilnehmer (Co-Investigator)), Witrisal, K. (Teilnehmer (Co-Investigator)), Römer, K. U. (Teilnehmer (Co-Investigator)), Aichernig, B. (Teilnehmer (Co-Investigator)), Bösch, W. (Teilnehmer (Co-Investigator)), Baunach, M. C. (Teilnehmer (Co-Investigator)), Tappler, M. (Teilnehmer (Co-Investigator)), Malenko, M. (Teilnehmer (Co-Investigator)), Weiser, S. (Teilnehmer (Co-Investigator)), Eichlseder, M. (Teilnehmer (Co-Investigator)), Leitinger, E. (Teilnehmer (Co-Investigator)), Grosinger, J. (Teilnehmer (Co-Investigator)), Großwindhager, B. (Teilnehmer (Co-Investigator)), Ebrahimi, M. (Teilnehmer (Co-Investigator)), Alothman Alterkawi, A. B. (Teilnehmer (Co-Investigator)), Knoll, C. (Teilnehmer (Co-Investigator)), Teschl, R. (Teilnehmer (Co-Investigator)), Saukh, O. (Teilnehmer (Co-Investigator)), Rath, M. (Teilnehmer (Co-Investigator)), Steinberger, M. (Teilnehmer (Co-Investigator)), Steinbauer-Wagner, G. (Teilnehmer (Co-Investigator)) & Tranninger, M. (Teilnehmer (Co-Investigator))
1/01/16 → 31/03/22
Projekt: Forschungsprojekt

Best Paper Award: The 31st IFIP International Conference on Testing Software and Systems
Aichernig, B. (Empfänger/-in), Bloem, R. (Empfänger/-in), Ebrahimi, M. (Empfänger/-in), Horn, M. (Empfänger/-in), Pernkopf, F. (Empfänger/-in), Roth, W. (Empfänger/-in), Rupp, A. (Empfänger/-in), Tappler, M. (Empfänger/-in) & Tranninger, M. (Empfänger/-in), Okt. 2019
Auszeichnung: Preise / Medaillen / Ehrungen

Dieses zitieren

Aichernig, B. K., Bloem, R., Ebrahimi, M., Horn, M., Pernkopf, F., Roth, W., Rupp, A., Tappler, M., & Tranninger, M. (2019). Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning. in C. Gaston, N. Kosmatov, & P. Le Gall (Hrsg.), Testing Software and Systems: 31st IFIP WG 6.1 International Conference, ICTSS 2019, Paris, France, October 15–17, 2019, Proceedings (S. 3-21). (Lecture Notes in Computer Science; Band 11812). Springer International Publishing AG . https://doi.org/10.1007/978-3-030-31280-0_1

Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning. / Aichernig, Bernhard K.; Bloem, Roderick; Ebrahimi, Masoud et al.
Testing Software and Systems: 31st IFIP WG 6.1 International Conference, ICTSS 2019, Paris, France, October 15–17, 2019, Proceedings. Hrsg. / Christophe Gaston; Nikolai Kosmatov; Pascale Le Gall. Cham: Springer International Publishing AG , 2019. S. 3-21 (Lecture Notes in Computer Science; Band 11812).

Publikation: Beitrag in Buch/Bericht/Konferenzband › Beitrag in einem Konferenzband › Begutachtung

Aichernig, BK , Bloem, R, Ebrahimi, M, Horn, M , Pernkopf, F, Roth, W, Rupp, A, Tappler, M & Tranninger, M 2019, Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning. in C Gaston, N Kosmatov & P Le Gall (Hrsg.), Testing Software and Systems: 31st IFIP WG 6.1 International Conference, ICTSS 2019, Paris, France, October 15–17, 2019, Proceedings. Lecture Notes in Computer Science, Bd. 11812, Springer International Publishing AG , Cham, S. 3-21, 31st IFIP International Conference on Testing Software and Systems, Paris, Frankreich, 15/10/19. https://doi.org/10.1007/978-3-030-31280-0_1

Aichernig BK , Bloem R, Ebrahimi M, Horn M , Pernkopf F, Roth W et al. Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning. in Gaston C, Kosmatov N, Le Gall P, Hrsg., Testing Software and Systems: 31st IFIP WG 6.1 International Conference, ICTSS 2019, Paris, France, October 15–17, 2019, Proceedings. Cham: Springer International Publishing AG . 2019. S. 3-21. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-31280-0_1

Aichernig, Bernhard K. ; Bloem, Roderick ; Ebrahimi, Masoud et al. / Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning. Testing Software and Systems: 31st IFIP WG 6.1 International Conference, ICTSS 2019, Paris, France, October 15–17, 2019, Proceedings. Hrsg. / Christophe Gaston ; Nikolai Kosmatov ; Pascale Le Gall. Cham : Springer International Publishing AG , 2019. S. 3-21 (Lecture Notes in Computer Science).

@inproceedings{2ef9be82021242378dd1d1040e1c4065,

title = "Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning",

abstract = "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.",

keywords = "Hybrid systems, Behavior modeling, Automata learning, Model-Based Testing, Machine learning, Autonomous vehicle, Platooning",

author = "Aichernig, {Bernhard K.} and Roderick Bloem and Masoud Ebrahimi and Martin Horn and Franz Pernkopf and Wolfgang Roth and Astrid Rupp and Martin Tappler and Markus Tranninger",

year = "2019",

doi = "10.1007/978-3-030-31280-0_1",

language = "English",

isbn = "978-3-030-31280-0",

series = "Lecture Notes in Computer Science",

publisher = "Springer International Publishing AG ",

pages = "3--21",

editor = "Christophe Gaston and Nikolai Kosmatov and {Le Gall}, Pascale",

booktitle = "Testing Software and Systems",

address = "Switzerland",

note = "31st IFIP International Conference on Testing Software and Systems : IFIP-ICTSS 2019 ; Conference date: 15-10-2019 Through 17-10-2019",

}

TY - GEN

T1 - Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning

AU - Aichernig, Bernhard K.

AU - Bloem, Roderick

AU - Ebrahimi, Masoud

AU - Horn, Martin

AU - Pernkopf, Franz

AU - Roth, Wolfgang

AU - Rupp, Astrid

AU - Tappler, Martin

AU - Tranninger, Markus

PY - 2019

Y1 - 2019

N2 - 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.

AB - 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.

KW - Hybrid systems

KW - Behavior modeling

KW - Automata learning

KW - Model-Based Testing

KW - Machine learning

KW - Autonomous vehicle

KW - Platooning

U2 - 10.1007/978-3-030-31280-0_1

DO - 10.1007/978-3-030-31280-0_1

M3 - Conference paper

SN - 978-3-030-31280-0

T3 - Lecture Notes in Computer Science

SP - 3

EP - 21

BT - Testing Software and Systems

A2 - Gaston, Christophe

A2 - Kosmatov, Nikolai

A2 - Le Gall, Pascale

PB - Springer International Publishing AG

CY - Cham

T2 - 31st IFIP International Conference on Testing Software and Systems

Y2 - 15 October 2019 through 17 October 2019

ER -

Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning

Abstract

Publikationsreihe

Konferenz

Zugriff auf Dokument

Fingerprint

Projekte

Enable-S3 - Europäische Initiative zur Validierung von hochautomatisierten und sicheren Systeme

Verlaesslichkeit im Internet der Dinge

Auszeichnungen

Best Paper Award: The 31st IFIP International Conference on Testing Software and Systems

Dieses zitieren