Abstract
The combination of the Internet of Things and Machine Learning has promoted the development of new technological approaches such as Edge Computing and Tiny Machine Learning. The contribution of this paper is the implementation of the Hypersphere Neural Network using the NodeMCU board and the Esp8266 microcontroller for energy consumption monitoring. The energy consumption monitoring consists of recognising the device operating with an IoT device. We use our IoT device for evaluating the performance of the embedded implementation of the Hypersphere Neural Network. The implementation of the Hypersphere Neural Network is carried out from the geometric algebra and conformal geometric algebra viewpoints. The idea behind the design and implementation of the Hypersphere Neural Network is to estimate hyperspheres which produce non-linear decision boundaries and separate the pattern classes. Our approach achieves 99.7\(\%\) and 99.4\(\%\) of classification success rate for training and validation stages respectively using a simple Hypersphere Neural Network topology.
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
Bertha Mazon-Olivo, A.P.: Internet of things: state-of-the-art, computing paradigms and reference architectures. IEEE Lat. Am. Trans. 20, 49–63 (2022)
López-Alfaro, G.A., et al.: Mobile robot for object detection using an iot system. In: 2020 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC), vol. 4, pp. 1–6 (2020)
López-Alfaro, G.A., et al.: Smart iot device for energy consumption monitoring in real time. In: 2021 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC), vol. 5, pp. 1–6 (2021)
Mohamed, K.S.: The era of internet of things: towards a smart world. In: The Era of Internet of Things, pp. 1–19. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-18133-8_1
Pan, J., McElhannon, J.: Future edge cloud and edge computing for internet of things applications. IEEE Internet Things J. 5, 439–449 (2018)
Cao, J., Zhang, Q., Shi, W.: Edge Computing: A Primer. Springer Briefs in Computer Science. Springer International Publishing (2018)
Zhang, C.: Intelligent internet of things service based on artificial intelligence technology. In: 2021 IEEE 2nd International Conference on Big Data, Artificial Intelligence and Internet of Things Engineering (ICBAIE), pp. 731–734 (2021)
Su, W., Li, L., Liu, F., He, M., Liang, X.: Ai on the edge: a comprehensive review. Artificial Intelligence Review, 1–59 (2022)
Mendoza, C.M.H., Rubio, J.P.S., Carillo, A.O.M., Vidal, L.M.R., Guzmán, R.H.: Sistema iot para el cuidado de plantas ornamentales. Revista de Investigación en Tecnologías de la Información 10, 15–30 (2022)
Melnyk, P., Felsberg, M., Wadenbäck, M.: Embed me if you can: a geometric perceptron. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 1276–1284 (2021)
Dorst, L., Fontijne, D., Mann, S.: Geometric algebra for computer science: an object-oriented approach to geometry. Elsevier (2010)
Serrano-Rubio, J.P., Hernández-Aguirre, A., Herrera-Guzmán, R.: Hyperconic multilayer perceptron. Neural Process. Lett. 45, 29–58 (2017)
Murrieta-Dueñas, R., Serrano-Rubio, J., López-Ramírez, V., Segovia-Dominguez, I., Cortez-González, J.: Prediction of microbial growth via the hyperconic neural network approach. Chemical Engineering Research and Design (2022)
Serrano-Rubio, J.P., Herrera-Guzmán, R., Hernández-Aguirre, A.: Hyperconic multilayer perceptron for function approximation. In: IECON 2015–41st Annual Conference of the IEEE Industrial Electronics Society, pp. 004702–004707 (2015)
Team, N.: Nodemcu-an opensource firmware based on esp8266 wifi-soc (2014). https://www.nodemcu.com
Systems, E.: Esp8266 overview (2022). https://www.espressif.com/en/products
Serrano-Rubio, J., García-Limón, J.A.: Edcube: Energy consumption dataset. https://sites.google.com/cimat.mx/jpsr/projects/machine-learning-for-edge-computing/edcube (2022) [Web (accessed August 26, 2022)]
García-Limón, J.A., Serrano-Rubio, J.: Edcube: energy consumption dataset (2022). https://sites.google.com/view/limon-alfredo/projects/hnn. Accessed 26 Aug 2022
Serrano-Rubio, J.P., Hernandez-Aguirre, A., Herrera-Guzman, R.: An evolutionary algorithm using spherical inversions. Soft. Comput. 22, 1993–2014 (2018)
Acknowledgments
The authors would like to thank the Science and Technology Council of Mexico, CONACyT, for its financial support during this research through the project CB-2015/256126 and the SNI Research Assistant Grant 156381. The second author would like to thank the Tecnológico Nacional de México/ITS de Irapuato for its support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
García-Limón, J.A., Serrano Rubio, J.P., Herrera-Guzmán, R., Rodriguez-Vidal, L.M., Hernández-Mendoza, C.M. (2022). Embedded Implementation of the Hypersphere Neural Network for Energy Consumption Monitoring. In: Pichardo Lagunas, O., Martínez-Miranda, J., Martínez Seis, B. (eds) Advances in Computational Intelligence. MICAI 2022. Lecture Notes in Computer Science(), vol 13612. Springer, Cham. https://doi.org/10.1007/978-3-031-19493-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-19493-1_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19492-4
Online ISBN: 978-3-031-19493-1
eBook Packages: Computer ScienceComputer Science (R0)