Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems

  • R. A. Rill Faculty of Mathematics and Computer Science, Babes-Bolyai University, Cluj-Napoca, Romania
  • A. Lorincz Faculty of Informatics, Eotvos-Lorand University, Budapest, Hungary

Abstract

In this paper, inspired by our previous works, we propose an architecture for the design and realization of cyber-physical systems (CPS) that considers the spatio-temporal context of events, promotes anomaly detection, facilitates efficient human-computer interaction and is capable of discovering novel human and/or machine knowledge. We view deep neural networks as smart sensors and sensory data from the environment represents the semantic and episodic input to a consistency seeking component of the cyber-space. Starting from a knowledge base infused with a deterministic world assumption, this module can detect anomalies and correct estimation errors by combining the outputs of multiple sensors. We also exploit an episodic description of ongoing situations by integrating temporal segmentation with kernel and low-dimensional embedding based methods. We demonstrate parts of the architecture through illustrative examples on our self-collected driving dataset. Our framework can be related to cognitive science foundations and may facilitate reliable functioning of CPS through integrating traditional AI and deep learning methods with deterministic models and reasoning tools. We expect that such knowledge base and cognition driven approaches of joining deep neural networks will be adopted in complex CPS. This looks like a scalable, and beneficial match between human knowledge and the exploding deep learning technologies.

References

[1] M. Atif, S. Latif, R. Ahmad, A. K. Kiani, J. Qadir, A. Baig, H. Ishibuchi, and W. Abbas. Soft computing techniques for dependable cyber-physical systems. CoRR, abs/1801.10472, 2018.
[2] C. Berger, A. Hees, S. Braunreuther, and G. Reinhart. Characterization of cyberphysical sensor systems. Procedia CIRP, 41:638–643, 2016. Research and Innovation in Manufacturing: Key Enabling Technologies for the Factories of the Future - Proceedings of the 48th CIRP Conference on Manufacturing Systems.
[3] M. Z. A. Bhuiyan, J. Wu, G. Wang, J. Cao, W. Jiang, and M. Atiquzzaman. Towards cyber-physical systems design for structural health monitoring: Hurdles and opportunities. ACM Trans. Cyber-Phys. Syst., 1(4):19:1–19:26, 2017.
[4] K. Bleakley and J.-P. Vert. The group fused Lasso for multiple change-point detection. working paper or preprint, 2011.
[5] A. Chattopadhyay and K.-Y. Lam. Security of autonomous vehicle as a cyber-physical system. In 2017 7th International Symposium on Embedded Computing and System Design (ISED), pages 1–6, 2017.
[6] M. Cuturi. Fast global alignment kernels. In Proceedings of the 28th International Conference on International Conference on Machine Learning, ICML’11, pages 929–936, USA, 2011. Omnipress.
[7] T. Dreossi, A. Donz´ e, and S. A. Seshia. Compositional falsification of cyber-physical systems with machine learning components. CoRR, abs/1703.00978, 2017.
[8] M. W. Eysenck. Fundamentals of Cognition. Psychology Press, 2012.
[9] E. Ilg, N. Mayer, T. Saikia, M. Keuper, A. Dosovitskiy, and T. Brox. Flownet 2.0: Evolution of optical flow estimation with deep networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1647–1655, 2017.
[10] E. A. Lee. Cyber physical systems: Design challenges. In 2008 11th IEEE International Symposium on Object and Component-Oriented Real-Time Distributed Computing (ISORC), pages 363–369, 2008.
[11] E. A. Lee. Cyber-physical systems: A rehash or a new intellectual challenge? Invited Talk in the Distinguished Speaker Series, sponsored by the IEEE Council on Electronic Design Automation (CEDA) held at the Design Automation Conference (DAC), Austin, Texas., 2013.
[12] J. Lee, B. Bagheri, and C. Jin. Introduction to cyber manufacturing. Manufacturing Letters, 8:11–15, 2016.
[13] J. Lee, B. Bagheri, and H.-A. Kao. A cyber-physical systems architecture for industry 4.0-based manufacturing systems. Manufacturing Letters, 3:18–23, 2015.
[14] J. Lin, S. Sedigh, and A. Miller. A Semantic Agent Framework for Cyber-Physical Systems, pages 189–213. Springer Berlin Heidelberg, Berlin, Heidelberg, 2011.
[15] Y. Liu, Y. Peng, B. Wang, S. Yao, and Z. Liu. Review on cyber-physical systems. IEEE/CAA Journal of Automatica Sinica, 4(1):27–40, 2017.
[16] A. Lorincz, M. Csákvári, ´ Aron. Fóthi, Z. ´A. Milacski, A. Sárkány, and Z. Toser. Towards reasoning based representations: Deep consistence seeking machine. Cognitive Systems Research, 47:92–108, 2018.
[17] Z. A. Milacski, K. B. Faragó, A. Fóthi, V. Varga, and A. Lorincz. Declarative description: The meeting point of artificial intelligence, deep neural networks, and human intelligence. In IJCAI/ECAI 2018 Workshop on Explainable Artificial Intelligence (XAI), 2018.
[18] Z. A. Milacski, M. Ludersdorfer, A. Lorincz, and P. Van Der Smagt. Robust detection of anomalies via sparse methods. In Lecture Notes in Computer Science, volume 9491, pages 419–426. Springer Verlag, 2015.
[19] S. Munir, J. A. Stankovic, C.-J. M. Liang, and S. Lin. Cyber physical system challenges for human-in-the-loop control. In Presented as part of the 8th International Workshop on Feedback Computing, San Jose, CA, 2013. USENIX.
[20] W. Nilsen, E. Ertin, E. B. Hekler, S. Kumar, I. Lee, R. Mangharam, M. Pavel, J. M. Rehg, W. Riley, D. E. Rivera, and D. Spruijt-Metz. Modeling Opportunities in mHealth Cyber-Physical Systems, pages 443–453. Springer International Publishing, Cham, 2017.
[21] W. D. Nothwang, M. J. McCourt, R. M. Robinson, S. A. Burden, and J. W. Curtis. The human should be part of the control loop? In 2016 Resilience Week (RWS), pages 214–220, 2016.
[22] N. Pedersen, T. Bojsen, and J. Madsen. Co-simulation of cyber physical systems with hmi for human in the loop investigations. In Proceedings of the Symposium on Theory of Modeling & Simulation, TMS/DEVS ’17, pages 1:1–1:12, San Diego, CA, USA, 2017. Society for Computer Simulation International.
[23] J. Redmon and A. Farhadi. Yolo9000: Better, faster, stronger. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 6517–6525, 2017.
[24] T. Simon, H. Joo, I. Matthews, and Y. Sheikh. Hand keypoint detection in single images using multiview bootstrapping. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4645–4653, 2017.
[25] D. Sonntag, S. Zillner, S. Chakraborty, A. L˝ orincz, E. Strommer, and L. Serafini. The medical cyber-physical systems activity at EIT: A look under the hood. In 2014 IEEE 27th International Symposium on Computer-Based Medical Systems, pages 351–356, 2014.
[26] L. van der Maaten and G. Hinton. Visualizing data using t-SNE. Journal of Machine Learning Research, 9:2579–2605, 2008.
Published
2019-06-17
How to Cite
RILL, R. A.; LORINCZ, A.. Cognitive Modeling Approach for Dealing with Challenges in Cyber-Physical Systems. Studia Universitatis Babeș-Bolyai Informatica, [S.l.], v. 64, n. 1, p. 51-66, june 2019. ISSN 2065-9601. Available at: <http://www.cs.ubbcluj.ro/~studia-i/journal/journal/article/view/36>. Date accessed: 29 nov. 2020. doi: https://doi.org/10.24193/subbi.2019.1.05.
Section
Articles