Next Article in Journal
Aspect-Based Sentiment Analysis in Hindi Language by Ensembling Pre-Trained mBERT Models
Previous Article in Journal
Design and Implementation of Programmable Data Plane Supporting Multiple Data Types
Previous Article in Special Issue
Audio Feature Engineering for Occupancy and Activity Estimation in Smart Buildings
Article

Are Microcontrollers Ready for Deep Learning-Based Human Activity Recognition?

1
Institute of Electronics and Computer Science (EDI), LV-1006 Riga, Latvia
2
Department of Engineering Mathematics, University of Bristol, Bristol BS81TW, UK
*
Author to whom correspondence should be addressed.
Academic Editor: Maria D. R-Moreno
Electronics 2021, 10(21), 2640; https://doi.org/10.3390/electronics10212640
Received: 30 September 2021 / Revised: 21 October 2021 / Accepted: 25 October 2021 / Published: 28 October 2021
(This article belongs to the Special Issue AI and ML in the Future of Wearable Devices)
The last decade has seen exponential growth in the field of deep learning with deep learning on microcontrollers a new frontier for this research area. This paper presents a case study about machine learning on microcontrollers, with a focus on human activity recognition using accelerometer data. We build machine learning classifiers suitable for execution on modern microcontrollers and evaluate their performance. Specifically, we compare Random Forests (RF), a classical machine learning technique, with Convolutional Neural Networks (CNN), in terms of classification accuracy and inference speed. The results show that RF classifiers achieve similar levels of classification accuracy while being several times faster than a small custom CNN model designed for the task. The RF and the custom CNN are also several orders of magnitude faster than state-of-the-art deep learning models. On the one hand, these findings confirm the feasibility of using deep learning on modern microcontrollers. On the other hand, they cast doubt on whether deep learning is the best approach for this application, especially if high inference speed and, thus, low energy consumption is the key objective. View Full-Text
Keywords: machine learning; deep learning; neural networks; activity recognition; accelerometers machine learning; deep learning; neural networks; activity recognition; accelerometers
Show Figures

Figure 1

MDPI and ACS Style

Elsts, A.; McConville, R. Are Microcontrollers Ready for Deep Learning-Based Human Activity Recognition? Electronics 2021, 10, 2640. https://doi.org/10.3390/electronics10212640

AMA Style

Elsts A, McConville R. Are Microcontrollers Ready for Deep Learning-Based Human Activity Recognition? Electronics. 2021; 10(21):2640. https://doi.org/10.3390/electronics10212640

Chicago/Turabian Style

Elsts, Atis, and Ryan McConville. 2021. "Are Microcontrollers Ready for Deep Learning-Based Human Activity Recognition?" Electronics 10, no. 21: 2640. https://doi.org/10.3390/electronics10212640

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop