Results 111 to 120 of about 1,533 (240)
Homogenization With Guaranteed Bounds via Primal‐Dual Physically Informed Neural Networks
International Journal for Numerical Methods in Engineering, Volume 127, Issue 6, 30 March 2026.ABSTRACT Physics‐informed neural networks (PINNs) have shown promise in solving partial differential equations (PDEs) relevant to multiscale modeling, but they often fail when applied to materials with discontinuous coefficients, such as media with piecewise constant properties. This paper introduces a dual formulation for the PINN framework to improve
Liya Gaynutdinova +3 more
wiley +1 more source
Abrupt Disappearance of Plasmaspheric Hiss Inside the Magnetic Dip
Geophysical Research Letters, Volume 53, Issue 5, 16 March 2026.Abstract Plasmaspheric hiss plays an important role in radiation belt electron dynamics, and its excitation and propagation have long attracted attention. During a substorm, Van Allen Probe B observed the disappearance of plasmaspheric hiss at the magnetic dip, which was driven by the injection of energetic protons.
Yan Zhuang +6 more
wiley +1 more source
International Journal of Adaptive Control and Signal Processing, Volume 40, Issue 3, Page 544-564, March 2026.This paper proposes two projector‐based Hopfield neural network (HNN) estimators for online, constrained parameter estimation under time‐varying data, additive disturbances, and slowly drifting physical parameters. The first is a constraint‐aware HNN that enforces linear equalities and inequalities (via slack neurons) and continuously tracks the ...
Miguel Pedro Silva
wiley +1 more source
Advanced Photonics Research, Volume 7, Issue 3, March 2026.This work demonstrates thin‐film lithium niobate Mach–Zehnder modulators. One of these modulators achieves a voltage‐length product of 0.1 V cm, a driving voltage of 1 V, a device length of 1 mm, and a bandwidth exceeding 200 GHz. A high‐permittivity cladded Bragg grating waveguide is utilized to enhance modulation efficiency, enabling low‐voltage and ...
Zobeyde Dadkhah +2 more
wiley +1 more source
Advanced Photonics Research, Volume 7, Issue 3, March 2026.This article proposes a deep learning (DL) approach for modeling and optimizing frequency‐doubled radio‐over‐fiber links. By collectively replacing traditional components with DL model, accurate system evaluation is achieved. Moreover, through an end‐to‐end architecture, performance optimization is accomplished.
Difei Shi +3 more
wiley +1 more source
Multi‐View Biomedical Foundation Models for Molecule‐Target and Property Prediction
Advanced Science, Volume 13, Issue 14, 9 March 2026.Molecular foundation models can provide accurate predictions for a large set of downstream tasks. We develop MMELON, an approach that integrates pre‐trained graph, image, and text foundation models and validate our multi‐view model on over 120 tasks, including GPCR binding.
Parthasarathy Suryanarayanan +17 more
wiley +1 more source
Advanced Intelligent Systems, Volume 8, Issue 3, March 2026.Poly(vinylidene fluoride) (PVDF)‐based ferroelectric materials exhibit high strains, energy densities and coupling efficiencies, appealing for diverse applications requiring smart material actuators. This work reviews electromechanical transduction in PVDF‐based polymers and their modifications, implementation in actuators, and functional devices ...
Giulio Gallucci, Andres Hunt
wiley +1 more source
Bio‐to‐Robot Transfer of Fish Sensorimotor Dynamics via Interpretable Model
Advanced Intelligent Systems, Volume 8, Issue 3, March 2026.This study demonstrates how a biologically interpretable model trained on real‐fish muscle activity can accurately predict the motion of a robotic fish. By linking real‐fish sensorimotor dynamics with robotic fish, the work offers a transparent, data‐efficient framework for transferring biological intelligence to bioinspired robotic systems.
Waqar Hussain Afridi +6 more
wiley +1 more source
The Canadian Journal of Chemical Engineering, Volume 104, Issue 3, Page 1283-1297, March 2026.Combination of ANN modelling and process optimization to achieve the maximum % dye removal. Abstract The present work reports on the use of artificial neural networks to predict the adsorption of 5G blue reactive dye (5GBRD) on yellow passion fruit pomace in a fixed‐bed process and the % dye removal optimization.
Maraísa Lopes de Menezes +2 more
wiley +1 more source
The Canadian Journal of Chemical Engineering, Volume 104, Issue 3, Page 1372-1386, March 2026.This work demonstrates the application of neural ordinary differential equations (neural ODEs) for learning hydrocracking reaction kinetics directly from data, achieving robust predictions under noise and sparsity while preserving mechanistic interpretability through gradient‐based analysis of temperature‐ and concentration‐dependent reaction rates ...
Souvik Ta +2 more
wiley +1 more source