Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2020 Apr 29;20(9):2533.
doi: 10.3390/s20092533.

Edge Machine Learning for AI-Enabled IoT Devices: A Review

Massimo Merenda  1   2 , Carlo Porcaro  1   2 , Demetrio Iero  1   2
Affiliations
Review

Edge Machine Learning for AI-Enabled IoT Devices: A Review

Massimo Merenda et al. Sensors (Basel). .

Abstract

In a few years, the world will be populated by billions of connected devices that will be placed in our homes, cities, vehicles, and industries. Devices with limited resources will interact with the surrounding environment and users. Many of these devices will be based on machine learning models to decode meaning and behavior behind sensors' data, to implement accurate predictions and make decisions. The bottleneck will be the high level of connected things that could congest the network. Hence, the need to incorporate intelligence on end devices using machine learning algorithms. Deploying machine learning on such edge devices improves the network congestion by allowing computations to be performed close to the data sources. The aim of this work is to provide a review of the main techniques that guarantee the execution of machine learning models on hardware with low performances in the Internet of Things paradigm, paving the way to the Internet of Conscious Things. In this work, a detailed review on models, architecture, and requirements on solutions that implement edge machine learning on Internet of Things devices is presented, with the main goal to define the state of the art and envisioning development requirements. Furthermore, an example of edge machine learning implementation on a microcontroller will be provided, commonly regarded as the machine learning "Hello World".

Keywords: Internet of Things; artificial intelligence; deep learning; edge devices; machine learning.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Edge computing interest (Google Trends).
Figure 2
Figure 2
Deep Neural Network (DNN) example.
Figure 3
Figure 3
(a) Hyperplane that separate two classes of data, (b) kernel trick.
Figure 4
Figure 4
(a) On-device computation, (b) edge server-based architectures, and (c) joint computation.
Figure 5
Figure 5
Pruning effect on the network.
Figure 6
Figure 6
Joint computation among devices, edge, and cloud servers.
Figure 7
Figure 7
Digit “6” drawn by the user.
Figure 8
Figure 8
STMicrolectronics NUCLEO-F746ZG.
Figure 9
Figure 9
Inference result showing the recognition of the digit “6” drawn by the user (accuracy = 100.00%, root-mean-square error (rmse) = 0.0000, medium average error (mae) = 0.0000, 10 classes, 1 sample).
Figure 10
Figure 10
Inference details.
See this image and copyright information in PMC

References

    1. Atzori L., Iera A., Morabito G. The Internet of Things: A survey. Comput. Networks. 2010;54:2787–2805. doi: 10.1016/j.comnet.2010.05.010. - DOI
    1. Mahdavinejad M.S., Rezvan M., Barekatain M., Adibi P., Barnaghi P., Sheth A.P. Machine learning for internet of things data analysis: A survey. Digit. Commun. Netw. 2018;4:161–175. doi: 10.1016/j.dcan.2017.10.002. - DOI
    1. IoT: Number of Connected Devices Worldwide 2012–2025 | Statista. [(accessed on 21 February 2020)]; Available online: https://www.statista.com/statistics/471264/iot-number-of-connected-devic...
    1. Vahid Dastjerdi A., Buyya R. Fog Computing: Helping the Internet of Things Realize. IEEE Comput. Soc. 2016;49:112–116. doi: 10.1109/MC.2016.245. - DOI
    1. Liu Y., Yang C., Jiang L., Xie S., Zhang Y. Intelligent Edge Computing for IoT-Based Energy Management in Smart Cities. IEEE Netw. 2019;33:111–117. doi: 10.1109/MNET.2019.1800254. - DOI

LinkOut - more resources