Discovering Interpretable Semantics from Radio Signals for Contactless Cardiac Monitoring
This study presents a semantic representation framework for clinically interpretable cardiac monitoring from contactless radio signals. It formulates radio semantic learning as an information‐bottleneck problem and approximates the objective via intra‐modal compression and cross‐modal alignment, structuring radio measurements into meaningful semantic ...
Jinbo Chen +10 more
wiley +1 more source
CRCFound: A Colorectal Cancer CT Image Foundation Model Based on Self-Supervised Learning. [PDF]
Yang J +13 more
europepmc +1 more source
Annealing‐Induced Plasticity and Strengthening in Metallic Glasses
This work challenges the dogma that annealing inevitably embrittles metallic glasses. We demonstrate that sub‐Tg annealing, guided by positive mixing enthalpy and constrained kinetics, can drive a self‐organized compositional fluctuation that creates an interface‐free heterogeneous structure.
Yingjie Zhang +17 more
wiley +1 more source
Anomaly detection in encrypted network traffic using self-supervised learning. [PDF]
Sattar S +7 more
europepmc +1 more source
Masked autoencoder-based self-supervised learning for forest plant classification
Luu Van Huy +3 more
openalex +2 more sources
Biomass‐ and solid waste‐derived sustainable single‐atom catalysts (Sus‐SACs) provide a cost‐effective and renewable approach to catalyst design. This review summarizes precursor selection, including AI‐assisted screening, synthesis strategies with emphasis on ultrafast methods, and advanced characterization techniques.
Hongzhe He +8 more
wiley +1 more source
Self-Supervised Learning and Multi-Sensor Fusion for Alpine Wetland Vegetation Mapping: Bayinbuluke, China. [PDF]
Zaka MM +5 more
europepmc +1 more source
Emerging Advanced Electronic Packaging Materials for Thermal Management in Power Electronics
This review surveys emerging materials for thermal management in advanced electronic packaging, with emphasis on ceramic substrates and thermal interface materials. Multiscale simulations and mechanistic analyses are highlighted, alongside the emerging role of artificial intelligence in predicting thermal properties and guiding design, offering ...
Yongjun Huo +11 more
wiley +1 more source
Two-stage deep learning framework for laterally spreading tumors detection using self-supervised learning and few-shot classification. [PDF]
Wang M, Shi Z, Wang Y, Lu J.
europepmc +1 more source
PAIR: Reconstructing Single‐Cell Open‐Chromatin Landscapes for Transcription Factor Regulome Mapping
scATAC‐seq analysis is often constrained by limited sequencing depth, extreme sparsity, and pervasive technical missingness. PAIR is a probabilistic framework that restores scATAC‐seq accessibility profiles by directly modeling the native cell–peak bipartite structure of chromatin accessibility.
Yanchi Su +7 more
wiley +1 more source

