A hybrid Reinforcement Learning–Explainable AI framework integrates SHAP and LIME explanations directly into a Deep Q‐Network inference loop for real‐time ICU decision support. Trained on 18 142 mechanically ventilated stays from the eICU database, the system attains 93.0% decision accuracy, 20% fewer errors than RL alone, and a 91% clinician trust ...
Jannatul Ferdaus Disha +2 more
wiley +1 more source
RF-SVR-based prediction methodology for metal tube-bending rebound: Handling non-uniformity and limited sample challenges. [PDF]
Fang Z, Zhang P, Li L, Zhang Q.
europepmc +1 more source
Toward Fully Soft and Multifunctional Shape Sensing via Optical Waveguide Arrays
This work develops a sheet made with arrays of soft optical fibers that can reconstruct its 3D surface shape. Synergy of the waveguides’ responses to bending and pressing force allows shape reconstruction with resilience to damage. Applied onto surfaces of robotic or living systems, our design can be implemented in virtual reality, teleoperation ...
Qifan Yu, Nina Cao, Kaitlyn Becker
wiley +1 more source
An efficient lattice-based identity-based proxy Re-encryption scheme with direct revocation for cloud storage. [PDF]
Li J, Jiang M, Guo Y.
europepmc +1 more source
Artificial Intelligence for Advanced Functional Materials: Progress and Emerging Frontiers
Artificial intelligence is transforming the discovery of functional materials by linking synthesis, characterization, simulation, and design in unified workflows. Advances in machine learning, autonomous experimentation, and foundation models are accelerating innovation across energy, electronics, and biomedicine, while revealing new frontiers for ...
Cristiano Malica +38 more
wiley +1 more source
A Vignetting Correction Method for Remote Sensing Images Based on Low-Rank Modeling and Polynomial Fitting. [PDF]
Zhao X, Hu Z, Xu Z.
europepmc +1 more source
Single‐Step Analog In‐Memory Matrix Computation in Three‐Dimensional Circuits
A wooden model illustrates a 3D memristive array designed for single‐step kernel convolutions. It shows how two‐dimensional input data are mapped into the 3D array and convolved in parallel with stored kernels. Color‐coded connection points represent programmed memory‐element values, with each color corresponding to a specific kernel weight.
Alireza Jaberi Rad +8 more
wiley +1 more source
Fully Characterizing Lossy Catalytic Computation. [PDF]
Folkertsma M +3 more
europepmc +1 more source
Comparative Analysis of Model‐Agnostic Explanation Methods in Materials Science
To address the critical lack of explainable artificial intelligence (XAI) benchmarks in materials science, we present a quantitative and qualitative analysis of six XAI methods applied to molecular fingerprints. Our results reveal significant discrepancies in feature importance rankings, demonstrating that the chosen explanation approach introduces ...
Anna Przybyłowska +7 more
wiley +1 more source
MSGSO: A Multi-Strategy Glider Snake Optimizer for Global Optimization and 3D UAV Path Planning. [PDF]
Aggul B, Seyyedabbasi A.
europepmc +1 more source

