Abstract
This paper presents the general concept and the prototypical implementation for generating data for testing self-learning functions. The concept offers the possibility to create a data set consisting of several different data providers. For this purpose, a mediation pattern adapted to the data generation was developed. The concept was applied to test a self-learning comfort function by classifying the context data into three subgroups: real-, sensor-, and user data. This separation allows a more realistic simulation using the data to test a self-learning comfort function and detect possible malfunctions. The CAGEN concept was implemented as a prototype by simulating GPS and temperature data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Kalmbach, R., et al.: Automotive Landscape 2025 [electronic Resource]: Opportunities and Challenges Ahead. Roland Berger Strategy Consultants (2011)
Guissouma, H., Klare, H., Sax, E., Burger, E.: An empirical study on the current and future challenges of automotive software release and configuration management. In: Euromicro Conference on Software Engineering and Advanced Applications (SEAA), pp. 298–305. IEEE (2018)
Teslamag.de. https://teslamag.de/news/neuronales-netz-soll-in-teslas-regen-und-schnee-erkennen-25496
Edvardsson, J.: A survey on automatic test data generation. In: Proceedings of the 2nd Conference on Computer Science and Engineering (1999)
Obermeyer, Z., Emanuel, E.: Predicting the future—big data, machine learning, and clinical medicine. New Engl. J. Med. 375(13), 1216–1219 (2016)
Shorten, C., Khoshgoftaar, T.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1–48 (2019)
Matalonga, S., Rodrigues, F., Travassos, G.: Characterizing testing methods for context-aware software systems: results from a quasi -systematic literature review. J. Syst. Softw. 131, 1–21 (2017)
Zhang, J.M., Harman, M., Ma, L., Liu, Y.: Machine learning testing: survey, landscapes and horizons. IEEE Trans. Softw. Eng. (2020)
Dietterich, T.G., Kong, E.B.: Machine learning bias, statistical bias, and statistical variance of decision tree algorithms. Technical report, Department of Computer Science, Oregon State University (1995)
Riccio, V., Jahangirova, G., Stocco, A., et al.: Testing machine learning based systems: a systematic mapping. Empirical Softw. Eng. 25(6), 5193–5254 (2020)
Lauber, A., Sommer, M., Fuchs, M., Sax, E.: Evolutionary algorithms to generate test cases for safety and IT-security in automotive systems. In: Syscon 2020–14th Annual IEEE International Systems Conference (2020)
Baumann, D., Pfeffer, R., Sax, E.: Automatic generation of critical test cases for the development of highly automated driving functions. In: 93rd IEEE Vehicular Technology Conference – Spring (2021)
Acknowledgement
I want to thank the student assistants Vinzenz Rau, Matthias Zipp and Felix Schorle for their work and commitment to this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Stang, M., Marquez, M.G., Sax, E. (2021). CAGEN - Context-Action Generation for Testing Self-learning Functions. In: Ahram, T., Taiar, R., Groff, F. (eds) Human Interaction, Emerging Technologies and Future Applications IV. IHIET-AI 2021. Advances in Intelligent Systems and Computing, vol 1378. Springer, Cham. https://doi.org/10.1007/978-3-030-74009-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-74009-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73270-7
Online ISBN: 978-3-030-74009-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)Springer Nature Proceedings excluding Computer Science