Abstract
TinyML technology, situated at the intersection of Machine Learning, Embedded Systems, and the Internet of Things (IoT), presents a promising solution for a wide range of IoT domains. However, achieving successful deployment of this technology on embedded devices necessitates optimizing energy efficiency. To validate the feasibility of TinyML on embedded devices, extensive field research and real-world experiments were conducted. Specifically, a TinyML computer vision model for people detection was implemented on an embedded system installed in a turnstile at a Federal Institute. The device accurately counts people, monitors battery levels, and transmits real-time data to the cloud. Encouraging results were obtained from the prototype, and experiments were performed using a lithium battery configuration with three batteries in series. Hourly voltage consumption analysis was conducted, and the findings were illustrated through graphical representations. The camera sensor prototype exhibited a consumption rate of 1.25 V per hour, whereas the prototype without the camera sensor displayed a more sustainable consumption rate of 0.93 V per hour. This field research contributes to advancing TinyML applications and enriching studies regarding its integration with IoT and computer vision.
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
Notes
References
Vangie, B.: What is the Internet?—Webopedia (2021). https://www.webopedia.com/definitions/internet/. Accessed 11 Feb 2021
Zimmer, E.F., et al.: A influência da internet na saúde biopsicossocial do adolescente: revisão integrativa. Revista Brasileira de Enfermagem, SciELO Brasil 73(2) (2020)
Datare Portal. Digital 2023: Global Overview Report (2023). https://datareportal.com. Accessed 01 Jan 2023
Umar, F.M., et al.: A review on internet of things (iot). Int. J. Comput. Appl. 113(1), 1–7 (2015)
Ahmad, K.M., Khaled, S.: IoT security: review, blockchain solutions, and open challenges. Future Gener. Comput. Syst. 82, 395–411 (2018)
Felix, W., Kristina, F.: Internet of Things. Bus. Inf. Syst. Eng. 57(3), 221–224 (2015)
Sarah, M.: Lamppost shines a light on smart cities (2015). https://www.ft.com/content/53b285c8-851d-11e4-ab4e-00144feabdc0. Accessed 11 Feb 2021
Stefano, N., et al.: Iot 2.0 and the internet of transformation (2020)
Ji, L., et al.: Mcunet: tiny deep learning on IoT devices. arXiv preprint arXiv:2007.10319 (2020)
de Prado, M., et al.: Robust navigation with tinyml for autonomous mini-vehicles. arXiv preprint arXiv:2007.00302 (2020)
Vitthalrao, L.S., et al.: Alcohol sensor calibration on the edge using tiny machine learning (tiny-ml) hardware. In: ECS Meeting Abstracts, p. 1848. IOP PUBLISHING (2020)
Lachit, D., Swapna, B.: Tinyml meets IoT: a comprehensive survey. Internet Things 16, 100461 (2021)
Somayya, M., et al.: Internet of things (IoT): a literature review. J. Comput. Commun. 3(05), 164 (2015)
Stanislava, S.: TinyML for Ubiquitous Edge AI (2021)
Chandrasekar, V., et al.: Democratization of AI, albeit constrained iot devices & tiny ml, for creating a sustainable food future. In: IEEE 2020 3rd International Conference on Information and Computer Technologies (ICICT), pp. 525–530 (2020)
Hiroshi, D., Roberto, M., Jan, H.: Bringing machine learning to the deepest IoT edge with tinyml as-a-service (2020)
Kalliopi, K., Theodoros, K., An, P.: Towards an iot-enabled intelligent energy management system. In: IEEE 2017 18th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering (ISEF) Book of Abstracts, pp. 1–2 (2017)
Brad, J.: The last thing IoT device engineers think about: end of battery life behavior for IoT devices. In: IEEE 2019 IEEE 62nd International Midwest Symposium on Circuits and Systems (MWSCAS), pp. 837–840 (2019)
Colby, R.B., et al.: Benchmarking tinyml systems: challenges and direction. arXiv preprint arXiv:2003.04821 (2020)
Jaworski, B.J., Kohli, A.K.: Conducting field-based, discovery-oriented research: lessons from our market orientation research experience. AMS Rev. 7, 4–12 (2017)
Bin, Z.Y., et al.: Internet of things (IoT): operating system, applications and protocols design, and validation techniques (2018)
TensorFlow. TensorFlow Lite (2022). https://www.tensorflow.org/lite/guide?hl=pt-br. Accessed 21 Mar 2022
Espressif ESP-IDF (2022). https://docs.espressif.com/projects/esp-idf/en/latest/esp32/get-started/index.html. Accessed 22 Mar 2022
Ubuntu, U.: https://ubuntu.com/download. Accessed 21 July 2021
Chugh, S.: https://github.com/sunnychugh/tensorflow/. Accessed 01 Aug 2021
TensorFlow Blog (2021). https://blog.tensorflow.org/2020/08/announcing-tensorflow-lite-micro-esp32.html. Accessed 01 Aug 2021
EzContents blog (2021). https://ezcontents.org/esp8266-battery-level-meter. Accessed 01 Aug 2021
Abhinab, S., Diwan, R.: IoT based load automation with remote access surveillance using esp 32 camand esp 8266 module. Ann. Romanian Soc. Cell Biol., 6904–6914 (2021)
Espressif ESP-IDF. Disponível em (2022). https://docs.espressif.com/projects/esp-idf/en/latest/esp32/get-started/index.html. Acesso em 22 Mar 2022
Firebase (2022). https://firebase.google.com/docs/database?hl=pt. Accessed 25 Mar 2022
Ministério da Educação (2022). https://www.ifes.edu.br/. Accessed 13 May 2022
Welcome to Python (2022). https://www.python.org/ Accessed 13 May 2022
Google Colab. (2022). https://colab.research.google.com/. Accessed 13 May 2022
Xian-Da, Z.: Machine learning. In: A Matrix Algebra Approach to Artificial Intelligence, pp. 223–440. Springer, Heidelberg (2020)
Korablyov, D.: https://medium.com/@dmytro.korablyov/first-steps-with-esp32-and-tensorflow-lite-for-microcontrollers-c2d8e238accf. Accessed 02 May 2022
Acknowledgments
I would like to express my sincere gratitude for the incredible teaching I received during my academic journey. I know that everything I have learned would not have been possible without the commitment, dedication, and passion that you put into your classes every day. The knowledge I have gained thanks to you is something I will carry with me forever. Additionally, I would like to thank FAPES for granting me the scholarship that made it possible for me to pursue my master’s degree at IFES. Without this opportunity, I would not have had access to all the learning and academic community I have encountered. Finally, I would like to thank IFIP-IOT for giving me the chance to publish my research work. It is an honor to be able to contribute to the academic community and I hope that my work can be useful to those who read it.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 IFIP International Federation for Information Processing
About this paper
Cite this paper
De Nardi, A.M., Monteiro, M.E. (2024). Evaluation of the Energy Viability of Smart IoT Sensors Using TinyML for Computer Vision Applications: A Case Study. In: Puthal, D., Mohanty, S., Choi, BY. (eds) Internet of Things. Advances in Information and Communication Technology. IFIPIoT 2023. IFIP Advances in Information and Communication Technology, vol 683. Springer, Cham. https://doi.org/10.1007/978-3-031-45878-1_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-45878-1_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45877-4
Online ISBN: 978-3-031-45878-1
eBook Packages: Computer ScienceComputer Science (R0)
