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

Kód výsledku v 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>

Výsledek na webu

<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>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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).

Název v anglickém jazyce

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

Popis výsledku anglicky

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).

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

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

Návaznosti

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

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

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

ISBN

979-8-3315-1617-8

ISSN

—

e-ISSN

—

Počet stran výsledku

4

Strana od-do

1-4

Název nakladatele

Institute of Electrical and Electronics Engineers, US

Místo vydání

Vienna

Místo konání akce

Vienna

Datum konání akce

25. 9. 2024

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

001344861600018