Abstract
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.
Highlights
In the last decade, deep learning has emerged as the dominant machine learning paradigm, kick-starting an exponential growth of artificial intelligence applications
We focus on human activity recognition using accelerometer data, as this application is very popular in the field, as well as requires both high accuracy and high energy efficiency if executed on wearable devices
With window size 256, the size difference is approximately 33 times with PerceptionNet and 430 times with the DeepCNN. These results demonstrate the importance of developing custom Convolutional Neural Networks (CNN) models suitable for microcontrollers
Summary
Deep learning has emerged as the dominant machine learning paradigm, kick-starting an exponential growth of artificial intelligence applications. These new 32-bit microcontrollers provide an unprecedented tradeoff between low energy consumption and high performance These new MCU often include instruction set architectures (ISA) optimized for deep learning applications. We focus on human activity recognition using accelerometer data, as this application is very popular in the field, as well as requires both high accuracy and high energy efficiency if executed on wearable devices. We rely on our previous results to solve the feature extraction and feature selection problems [9] We use these features as inputs for our RF classifiers. A brief investigation confirms that using features for training NN classifiers does not give substantially more accurate results, but it does come with an additional run-time energy cost for the feature extraction step
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
