Privacy-preserving federated unsupervised domain adaptation with application to age prediction from DNA methylation data. [PDF]
BioinformaticsBaykara CA +3 more
europepmc +1 more source
Unsupervised Domain Adaptation with Shape Constraint and Triple Attention for Joint Optic Disc and Cup Segmentation. [PDF]
Sensors (Basel), 2022 Zhang F, Li S, Deng J.
europepmc +1 more source
Toward Environmentally Friendly Hydrogel‐Based Flexible Intelligent Sensor Systems
Advanced Intelligent Discovery, EarlyView.This review summarizes environmentally and biologically friendly hydrogel‐based flexible sensor systems focusing on physical, chemical, and physiological sensors. Furthermore, device concepts moving forward for the practical application are discussed about wireless integration, the interface between hydrogel and dry electronics, automatic data analysis
Sudipta Kumar Sarkar, Kuniharu Takei
wiley +1 more source
A simple preprocessing approach for improving semantic segmentation in unsupervised domain adaptation. [PDF]
Sci RepEttedgui S, Abu-Hussein S, Giryes R.
europepmc +1 more source
Unsupervised Domain Adaptation for Segmentation with Black-box Source Model. [PDF]
Proc SPIE Int Soc Opt Eng, 2022 Liu X +6 more
europepmc +1 more source
Automatic Determination of Quasicrystalline Patterns from Microscopy Images
Advanced Intelligent Discovery, EarlyView.This work introduces a user‐friendly machine learning tool to automatically extract and visualize quasicrystalline tiling patterns from atomically resolved microscopy images. It uses feature clustering, nearest‐neighbor analysis, and support vector machines. The method is broadly applicable to various quasicrystalline systems and is released as part of
Tano Kim Kender +2 more
wiley +1 more source
Contrastive learning enhanced pseudo-labeling for unsupervised domain adaptation in person re-identification. [PDF]
PLoS OneBai X, Zhang Y, Zhang C, Wang Z.
europepmc +1 more source
TSTELM: Two-Stage Transfer Extreme Learning Machine for Unsupervised Domain Adaptation. [PDF]
Comput Intell Neurosci, 2022 Zang S, Li X, Ma J, Yan Y, Gao J, Wei Y.
europepmc +1 more source
Advanced Intelligent Discovery, EarlyView.A novel convolutional neural network architecture enables rapid, unsupervised analysis of IR spectroscopic data from DRIFTS and IRRAS. By combining synthetic data generation with parallel convolutional layers and advanced regularization, the model accurately resolves spectral features of adsorbed CO, offering real‐time insights into ceria surface ...
Mehrdad Jalali +5 more
wiley +1 more source
Threshold-based exploitation of noisy label in black-box unsupervised domain adaptation. [PDF]
PLoS OneXu H, Lee J, Kang U.
europepmc +1 more source