Load Classification: A Case Study for Applying Neural Networks in Hyper-Constrained Embedded Devices


Andrea Agiollo, Andrea Omicini

Applied Sciences 11(24), article 11957, December 2021
MDPI
Special Issue “Artificial Intelligence and Data Engineering in Engineering Applications”

The application of Artificial Intelligence to the industrial world and its appliances has recently grown in popularity. Indeed, AI techniques are now becoming the de-facto technology for the resolution of complex tasks concerning computer vision, natural language processing and many other areas. In the last years, most of the the research community efforts have focused on increasing the performance of most common AI techniques—e.g., Neural Networks, etc.—at the expenses of their complexity. Indeed, many works in the AI field identify and propose hyper-efficient techniques, targeting high-end devices. However, the application of such AI techniques to devices and appliances which are characterised by limited computational capabilities, remains an open research issue. In the industrial world, this problem heavily targets low-end appliances, which are developed focusing on saving costs and relying on—computationally—constrained components. While some efforts have been made in this area through the proposal of AI-simplification and AI-compression techniques, it is still relevant to study which available AI techniques can be used in modern constrained devices. Therefore, in this paper we propose a load classification task as a case study to analyse which state-of-the-art NN solutions can be embedded successfully into constrained industrial devices. The presented case study is tested on a simple microcontroller, characterised by very poor computational performances—i.e., FLOPS –, to mirror faithfully the design process of low-end appliances. A handful of NN models are tested, showing positive outcomes and possible limitations, and highlighting the complexity of AI embedding.

(keywords) Load Classification; Neural Networks; Embedding; Hyper-constrained Devices
 @article{nnconstrained-applsci11,
articleno = 11957,
author = {Agiollo, Andrea and Omicini, Andrea},
doi = {10.3390/app112411957},
irisid = {11585/842440},
issn = {2076-3417},
journal = {Applied Sciences},
keywords = {Load Classification; Neural Networks; Embedding; Hyper-constrained Devices},
month = dec,
note = {Special Issue ``Artificial Intelligence and Data Engineering in Engineering Applications''},
number = 24,
publisher = {MDPI},
title = {Load Classification: A Case Study for Applying Neural Networks in Hyper-Constrained Embedded Devices},
url = {https://www.mdpi.com/2076-3417/11/24/11957},
url-openaccess = {https://www.mdpi.com/2076-3417/11/24/11957/pdf},
url-pdf = {https://www.mdpi.com/2076-3417/11/24/11957/pdf},
volume = 11,
year = 2021

Journals & Series

Publication

— authors

Andrea Agiollo, Andrea Omicini

— status

published

— sort

article in journal

Venue

— journal

Applied Sciences

— volume

11

— issue

24

— article no.

11957

— publication date

December 2021

URLs

original page  |  original PDF  |  open access PDF

Identifiers

— DOI

10.3390/app112411957

— IRIS

11585/842440

— WoS / ISI

000735509300001

— print ISSN

2076-3417

BibTeX

— BibTeX ID
nnconstrained-applsci11
— BibTeX category
article

Partita IVA: 01131710376 - Copyright © 2008-2022 APICe@DISI Research Group - PRIVACY