ST-NILM: A Wavelet Scattering-Based Architecture for Feature Extraction and Multilabel Classification in NILM Signals

Nonintrusive load monitoring (NILM) is a relevant tool for improving energy consumption habits, contributing to energy conservation and distribution system planning. In recent years, high-frequency strategies using deep learning have been presented in the literature, achieving the state-of-the-art r...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE sensors journal 2024-04, Vol.24 (7), p.10540-10550
Hauptverfasser:	de Aguiar, Everton Luiz, da Silva Nolasco, Lucas, Lazzaretti, André Eugenio, Pipa, Daniel Rodrigues, Lopes, Heitor Silvério
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Classification Computer architecture Data augmentation Deep learning Electrical loads Energy consumption Energy distribution Feature extraction Machine learning Scattering Signal classification Signal monitoring Wavelet analysis
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!