Toward Non-IID in Load Disaggregation: An Unsupervised Domain Adaptation Framework for Heterogeneous Energy Consumption Sectors
H Yin, K Zhou, Z Chen, S Yang - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
This article proposes a generalizable nonintrusive load monitoring (NILM) framework to
address nonindependent and identically distributed (Non-IID) data challenges in …
address nonindependent and identically distributed (Non-IID) data challenges in …
Load Identification Based on Attention Semi-supervised Curriculum Label Learning with AVME-HT Feature
Nonintrusive load monitoring (NILM) is a cost-effective technology for monitoring detailed
electricity energy consumption. In recent years, machine learning has emerged as the …
electricity energy consumption. In recent years, machine learning has emerged as the …
Multi-Task Learning-Based Method for Load Identification, Electrical Fault Detection and Signal Denoising
J Jiang, Z Wang, S Qiu, K Zhang, Y Su… - IEEE Sensors …, 2024 - ieeexplore.ieee.org
In recent years, the application of deep learning techniques for load identification in
nonintrusive load monitoring (NILM) has gained significant momentum. However, the …
nonintrusive load monitoring (NILM) has gained significant momentum. However, the …
Non-Intrusive Load Identification Considering Unknown Load Based on Bi-Modal Fusion and One-Class Classification
J Xiao, M Tan, R Pan, Y Su, T Li… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Nonintrusive load monitoring (NILM) enables the real-time monitoring and data analysis of
energy consumption, providing more accurate, efficient, and intelligent data support for …
energy consumption, providing more accurate, efficient, and intelligent data support for …
A Federated Learning Method for Non-intrusive Load Monitoring Based on Fed-Prox and Bi-GRU
J Xu, D Li, W Hu, X Cheng - International Conference on Neural …, 2024 - Springer
Abstract In recent studies, Non-Intrusive Load Monitoring (NILM) methods based on deep
learning have received widespread attentions and achieved promising results. Most existing …
learning have received widespread attentions and achieved promising results. Most existing …
Enhancing ADMET Property Models Performance through Combinatorial Fusion Analysis.
Accurate prediction of Absorption, Distribution, Metabolism, Excretion, and Toxicity (ADMET)
properties is crucial for drug discovery and development. However, existing computational …
properties is crucial for drug discovery and development. However, existing computational …