Label-efficient time series representation learning: A review

E Eldele, M Ragab, Z Chen, M Wu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Label-efficient time series representation learning, which aims to learn effective
representations with limited labeled data, is crucial for deploying deep learning models in …

Cloud-edge test-time adaptation for cross-domain online machinery fault diagnosis via customized contrastive learning

M Zhu, J Liu, Z Hu, J Liu, X Jiang, T Shi - Advanced Engineering Informatics, 2024 - Elsevier
Nowadays offline transfer learning (TL) is the mainstream research for cross-domain
machinery fault diagnosis (MFD). However, the target data is usually collected online by …

MDLR: A multi-task disentangled learning representations for unsupervised time series domain adaptation

Y Liu, D Li, J Wang, B Li, B Hang - Information Processing & Management, 2024 - Elsevier
Abstract Unsupervised Time Series Domain Adaptation (UTSDA) is a method for transferring
information from a labeled source domain to an unlabeled target domain. The majority of …

A survey of spatio-temporal eeg data analysis: from models to applications

P Wang, H Zheng, S Dai, Y Wang, X Gu, Y Wu… - ar** for Time Series Test Time Adaptation
P Gong, M Ragab, M Wu, Z Chen, Y Su, X Li… - arxiv preprint arxiv …, 2025 - arxiv.org
Test-time adaptation aims to adapt pre-trained deep neural networks using solely online
unlabelled test data during inference. Although TTA has shown promise in visual …

[HTML][HTML] CLEAR: Multimodal Human Activity Recognition via Contrastive Learning Based Feature Extraction Refinement

M Cao, J Wan, X Gu - Sensors, 2025 - mdpi.com
Human activity recognition (HAR) has become a crucial research area for many
applications, such as Healthcare, surveillance, etc. With the development of artificial …

[HTML][HTML] A relation-enhanced mean-teacher framework for source-free domain adaptation of object detection

D Tian, C Xu, S Cao - Alexandria Engineering Journal, 2025 - Elsevier
Abstract Source-Free Domain Adaptation Object Detection (SF-DAOD) is a challenging task
in the field of computer vision. This task is used when the source-domain dataset is not …

Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement

G Patel, C Sandino, B Mahasseni, EL Zippi… - arxiv preprint arxiv …, 2024 - arxiv.org
In this paper, we propose a framework for efficient Source-Free Domain Adaptation (SFDA)
in the context of time-series, focusing on enhancing both parameter efficiency and data …

Fast Online Fault Diagnosis for PMSM Based on Adaptation Model

H Hu, J Gao, X Zhang, X Zhang, Y Qu… - IEEE Sensors …, 2024 - ieeexplore.ieee.org
Permanent magnet synchronous motors (PMSMs) are widely used as the key equipment in
devices due to their superior performance, and their health status is closely related to the …