.png){kind=icon}
Return
Data-Driven Sparsification and Multi-Resolution Analysis-Based Framework for Load Identification
.png){kind=icon}
PRE
AI
DOI：10.1109/TSG.2023.3343127.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The present work focuses on certain pivotal aspects regarding load identification for non-intrusive load monitoring (NILM) using convolutional neural networks (CNN). Primarily, image sets of load signatures are generated via multi-resolution analysis leading to improved image sets compared to the recent relevant works. Secondly, to avoid manual settings for deep learning optimization algorithm hyper-parameters, Bayesian optimization is performed. Lastly, a data-driven strategy based on Taylor's score is considered to significantly compress the CNN architecture. The proposed overall strategy leads to high classification performance and reduced memory footprint.
Keywords:
Bayesian optimization
hyper-parameters
multi-resolution analysis
non-intrusive load monitoring
Journal
IF:
9.8
Papers:
5.7K
Citations:
4.3W
Organization
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSave no more
no more