Abstract
The quest for efficient Tiny Machine Learning on Microcontroller Units is increasing rapidly due to the vast application spectrum made possible with the advancement of Tiny ML. One application area that could benefit from such advancement is Electronic Skin systems, that are employed in several domains such as: wearable devices, robotics, prosthesis, etc. An e-skin system demands hard constraints including real-time processing, low energy consumption, and low memory footprint. This paper presents a tiny Convolution Neural Network (CNN) architecture suitable for the deployment on an off-the-shelf commercial microcontroller in compliance with the e-skin requirements. The training, optimization, and implementation of the proposed CNN are presented. The CNN implementation is optimized through layer fusion and buffer re-use strategies for efficient inference on edge devices. As a case study, experimental analysis of a touch modality classification task demonstrates that the proposed CNN-based system is capable of processing tactile data in real-time directly near the source while reducing the model size by up to 65% with respect to comparable existing solutions.
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
References
Sanchez-Iborra, R., Skarmeta, A.F.: TinyML-enabled frugal smart objects: challenges and opportunities. IEEE Circuits Syst. Mag. 20(3), 4–18 (2020)
Shafique, M., Theocharides, T., Reddy, V.J., Murmann, B.: TinyML: current progress, research challenges, and future roadmap. In: Proceedings - Design Automation Conference, vol. 2021-December, pp. 1303–1306, December 2021
Mukherjee, R., Dahiya, R.: Life cycle assessment of energy generating flexible electronic skin. In: 2021 IEEE International Conference on Flexible and Printable Sensors and Systems (FLEPS), Manchester, United Kingdom, pp. 1–4. IEEE, June 2021
Johansson, R.S., Flanagan, J.R.: Coding and use of tactile signals from the fingertips in object manipulation tasks. Nat. Rev. Neurosci. 10, 345–359 (2009)
Bhattacharjee, T., Rehg, J.M., Kemp, C.C.: Haptic classification and recognition of objects using a tactile sensing forearm. In: 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, (Vilamoura-Algarve, Portugal), pp. 4090–4097. IEEE, October 2012
Kaboli, M., Mittendorfer, P., Hugel, V., Cheng, G.: Humanoids learn object properties from robust tactile feature descriptors via multi-modal artificial skin. In: 2014 IEEE-RAS International Conference on Humanoid Robots, (Madrid, Spain), pp. 187–192. IEEE, November 2014
Schill, J., Laaksonen, J., Przybylski, M., Kyrki, V., Asfour, T., Dillmann, R.: Learning continuous grasp stability for a humanoid robot hand based on tactile sensing. In: 2012 4th IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob), (Rome, Italy), pp. 1901–1906. IEEE, June 2012
Gastaldo, P., Pinna, L., Seminara, L., Valle, M., Zunino, R.: Computational intelligence techniques for tactile sensing systems. Sensors 14, 10952–10976 (2014)
Younes, H., Ibrahim, A., Rizk, M., Valle, M.: Data oriented approximate K-nearest neighbor classifier for touch modality recognition. In: 2019 15th Conference on Ph.D Research in Microelectronics and Electronics (PRIME), (Lausanne, Switzerland), pp. 241–244. IEEE, July 2019
Alameh, M., Ibrahim, A., Valle, M., Moser, G.: DCNN for tactile sensory data classification based on transfer learning. In: 2019 15th Conference on Ph.D Research in Microelectronics and Electronics (PRIME), (Lausanne, Switzerland), pp. 237–240. IEEE, July 2019
Alameh, M., Abbass, Y., Ibrahim, A., Valle, M.: Smart tactile sensing systems based on embedded CNN implementations. Micromachines 11, 103 (2020)
Ibrahim, A., Valle, M.: Real-time embedded machine learning for tensorial tactile data processing. IEEE Trans. Circuits Syst. I Regul. Pap. 65, 3897–3906 (2018)
Younes, H., Ibrahim, A., Rizk, M., Valle, M.: An efficient selection-based kNN architecture for smart embedded hardware accelerators. IEEE Open J. Circuits Syst. 2, 534–545 (2021)
Gianoglio, C., Ragusa, E., Zunino, R., Valle, M.: 1-D convolutional neural networks for touch modalities classification. In: 2021 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS), (Dubai, United Arab Emirates), pp. 1–6. IEEE, November 2021
Gastaldo, P., Pinna, L., Seminara, L., Valle, M., Zunino, R.: A tensor-based pattern-recognition framework for the interpretation of touch modality in artificial skin systems. IEEE Sens. J. 14, 2216–2225 (2014)
Osta, M., et al.: An energy efficient system for touch modality classification in electronic skin applications. In: 2019 IEEE International Symposium on Circuits and Systems (ISCAS), (Sapporo, Japan), pp. 1–4. IEEE, May 2019
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 [cs], January 2017
Sakr, F., Bellotti, F., Berta, R., Gloria, A.D., Doyle, J.: Memory-efficient CMSIS-NN with replacement strategy. In: Proceedings - 2021 International Conference on Future Internet of Things and Cloud, FiCloud 2021, pp. 299–303, August 2021
Lai, L., Suda, N., Chandra, V.: CMSIS-NN: efficient neural network Kernels for arm Cortex-M CPUs, arXiv, vol. abs/1801.06601 (2018)
Alameh, M., Abbass, Y., Ibrahim, A., Moser, G., Valle, M.: Touch modality classification using recurrent neural networks. IEEE Sensors J. 21, 9983–9993 (2021)
Ibrahim, A., Younes, H., Alameh, M., Valle, M.: Near sensors computation based on embedded machine learning for electronic skin. Procedia Manufacturing 52, 295–300 (2020)
Younes, H., Ibrahim, A., Rizk, M., Valle, M.: Hybrid fixed-point/binary convolutional neural network accelerator for real-time tactile processing. In: 2021 28th IEEE International Conference on Electronics, Circuits, and Systems (ICECS), (Dubai, United Arab Emirates), pp. 1–5. IEEE, November 2021
Younes, H., Ibrahim, A., Rizk, M., Valle, M.: A shallow neural network for real-time embedded machine learning for tensorial tactile data processing. IEEE Trans. Circuits Syst. I 68, 4232–4244 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sakr, F., Younes, H., Doyle, J., Bellotti, F., De Gloria, A., Berta, R. (2023). A Tiny CNN for Embedded Electronic Skin Systems. In: Valle, M., et al. Advances in System-Integrated Intelligence. SYSINT 2022. Lecture Notes in Networks and Systems, vol 546. Springer, Cham. https://doi.org/10.1007/978-3-031-16281-7_53
Download citation
DOI: https://doi.org/10.1007/978-3-031-16281-7_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-16280-0
Online ISBN: 978-3-031-16281-7
eBook Packages: EngineeringEngineering (R0)