X2BR: High-fidelity 3D bone reconstruction from a planar X-ray image with hybrid neural implicit methods. [PDF]
Guven G, Ugurdag F, Ates HF.
europepmc +1 more source
Device Stochasticity Directly Implements Bayesian Sampling in Spiking Neurons
Brain‐inspired stochastic spiking turns device noise into Bayesian uncertainty for robust, low‐power neuromorphic computing. ABSTRACT Device stochasticity is considered a non‐ideality in neuromorphic hardware, although stochastic neural activity supports probabilistic computation in biological systems.
Huannan Zheng, Jingli Liu, Kezhou Yang
wiley +1 more source
Biological domain shift and statistical nesting concerns in generative AI-based spatial tumor growth prediction for pediatric diffuse midline glioma. [PDF]
Li W, Sun X, Pei S.
europepmc +1 more source
STRIDE: A Sequencing Depth Robust Metric for Sparse Chromosome Conformation Capture Data Comparison
A mean first passage time (MFPT)‐based representation transforms sparse Hi‐C contact maps into robust topological representations, preserving biologically meaningful chromatin features and facilitating robust analysis of TADs, chromatin loops, differential chromatin contacts, and sparse single‐cell Hi‐C data.
Bingxiang Xu +4 more
wiley +1 more source
Physics-aware generative fusion via Complex-Flow Mamba enables robust 4D radar-vision perception. [PDF]
Yang X, Guo J, Zhe L.
europepmc +1 more source
Accelerating High‐Fidelity Airfoil Design via Physics‐Informed Video Diffusion Model
Physics‐informed video diffusion enables rapid inverse aerodynamic design by mapping target lift‐to‐drag response to airfoil geometries and full‐field flow distributions. Trained on 53 400 DNS samples, the model achieves over 90% fidelity with ∼30 s inference, while experimentally realized propeller designs demonstrate a practical pathway from ...
Yifeng Ai +9 more
wiley +1 more source
KEMFF: A Knowledge-Enhanced and Multidimensional Feature Fusion Model for Aspect-Based Sentiment Analysis. [PDF]
Yang S, Liu P, Zhu W.
europepmc +1 more source
ReLink: Reliable Deep Learning for Microscopic Motion Tracking
ReLink enables reliable trajectory linking in single‐particle tracking by integrating physics‐informed motion statistics with confidence‐based adaptive filtering. Across diverse simulated and experimental conditions, ReLink robustly reconstructs trajectories and preserves the fidelity of downstream analyses, enabling accurate characterization of ...
Yuan Jiang +7 more
wiley +1 more source
Dismantling ableism in health professions education: imperative in psychosocial management of pain. [PDF]
Van Der Laan KF, Spector AL.
europepmc +1 more source
Updatable Closed‐Form Evaluation of Arbitrarily Complex Multiport Network Connections
The inverse design of electrically large wave devices often uses reduced‐order multiport models with discrete optimization, requiring many evaluations of complex interconnections between subsystems that differ only in a few blocks. This paper introduces a closed‐form framework enabling efficient Woodbury low‐rank updates of related, previous ...
Hugo Prod'homme, Philipp del Hougne
wiley +1 more source

