IP devices are ubiquitously spread, for both residential and industrial purposes, thanks to the low integration costs and rapid development cycle of all-IP-based 5G+ technologies. As a consequence, the engineering community now considers their automatization and energy scheduling/management as relevant research fields. These topics have a striking relevance also for the development of smart city networks. As a drawback, most ID-device applications produce a large amount of data (high-frequency complexity), requiring supervised machine learning algorithms to be properly analyzed. In this research, we focus on the performance of vehicular mobility and imaging systems, recognizing scenarios (with powered-on devices) in real-time, with the help of a simple convolutional neural network, proving the effectiveness of such an innovative low-cost approach.

An Overview of a New Statistical Non-Intrusive Load Monitoring (NILM) Analysis and Recognition Approach for Domestic Environments: DENARDO

Mannone M.;
2024

Abstract

IP devices are ubiquitously spread, for both residential and industrial purposes, thanks to the low integration costs and rapid development cycle of all-IP-based 5G+ technologies. As a consequence, the engineering community now considers their automatization and energy scheduling/management as relevant research fields. These topics have a striking relevance also for the development of smart city networks. As a drawback, most ID-device applications produce a large amount of data (high-frequency complexity), requiring supervised machine learning algorithms to be properly analyzed. In this research, we focus on the performance of vehicular mobility and imaging systems, recognizing scenarios (with powered-on devices) in real-time, with the help of a simple convolutional neural network, proving the effectiveness of such an innovative low-cost approach.
2024
Istituto di Calcolo e Reti ad Alte Prestazioni - ICAR
Appliance Classification
Convolutional Neural Networks
Data-to-Image Conversion
IoT Networks
Machine Learning
File in questo prodotto:
File Dimensione Formato  
m97253-fazio final.pdf

solo utenti autorizzati

Licenza: Altro tipo di licenza
Dimensione 4.24 MB
Formato Adobe PDF
4.24 MB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14243/521382
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact