Machine Learning in Context of IoT/Edge Devices and LoLiPoP-IoT Project

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F24%3APU151964" target="_blank" >RIV/00216305:26230/24:PU151964 - isvavai.cz</a>

Result on the web

<a href="https://ieeexplore.ieee.org/document/10716234" target="_blank" >https://ieeexplore.ieee.org/document/10716234</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/Austrochip62761.2024.10716234" target="_blank" >10.1109/Austrochip62761.2024.10716234</a>

Result language

angličtina

Original language name

Machine Learning in Context of IoT/Edge Devices and LoLiPoP-IoT Project

Original language description

Machine learning models are traditionally deployed in the cloud or on centralized servers to leverage their computing resources. However, such a deployment may reduce privacy, introduce extra latency, consume more power, etc., and subsequently negatively impact properties of an application that typically runs on a battery-operated device used to communicate via a wireless network. To minimize the negative impact, it is necessary to deploy a model directly to such a device to minimize data transfer energy and run the model closer to the data source and, application and its environment. However, this kind of deployment is a  challenging task due to the very limited resources available in such devices and applications. Many people and companies have tackled this challenging problem and proposed different ways and means to solve it. Having defined the problem and our area of interest, the paper provides an overview of representative applications, methods and means, including libraries, frameworks, datasets, devices etc. It then presents a  typical deployment process workflow in the context of resource-constrained devices. Finally, it sums representative results for popular resource-constrained devices (e.g., Arduino, ARM Cortex-M, ESP32, nRF5x, Nvidia Jetson, Raspberry Pi) to demonstrate how various phenomena (e.g., model type, setting, quantization) affect model performance (e.g., accuracy, loss), metrics (e.g., ROC AUC, F1 scores) and device performance (e.g., feature and inference processing time, memory usage).

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/9A23012" target="_blank" >9A23012: Long Life Power Platforms for Internet of Things</a><br>

Continuities

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of 32nd Austrian Workshop on Microelectronics (Austrochip 2024)

ISBN

979-8-3315-1617-8

ISSN

—

e-ISSN

—

Number of pages

4

Pages from-to

1-4

Publisher name

Institute of Electrical and Electronics Engineers, US

Place of publication

Vienna

Event location

Vienna

Event date

Sep 25, 2024

Type of event by nationality

EUR - Evropská akce

UT code for WoS article

001344861600018