Results 151 to 160 of about 39,047 (336)

Detecting Pteridium arachnoideum and Tithonia diversifolia in a Multiclass Land‐Cover Framework in the Cerrado: A Deep Learning Time‐Series Benchmark With Spatial Cross‐Validation

open access: yesTransactions in GIS, Volume 30, Issue 2, April 2026.
ABSTRACT This study presents the first deep‐learning time‐series benchmark for detecting two encroaching species in the Brazilian Cerrado: the native super‐dominant fern Pteridium arachnoideum and the invasive alien shrub Tithonia diversifolia. We evaluate 43 architectures across six families (CNNs, RNNs, Transformers, and three hybrid groups) on ...
Leandro de Arruda Bruno   +3 more
wiley   +1 more source

Shadows in the Spotlight: Casting Deep Learning Models to Unveil the Geometry of Printed Structures

open access: yesSolar RRL, Volume 10, Issue 6, 29 March 2026.
A modular deep learning (DL) pipeline predicts high‐resolution geometrical finger profiles from full surface optical and laser shadow images of solar cells. All DL models combined predict finger width, height, and cross‐sectional area, validated by microscopic measurements. Resulting quality maps visualize printing errors across solar cells, enabling a
Leslie Kurumundayil   +7 more
wiley   +1 more source

The CUDA implementation of the method of lines for the curvature dependent flows [PDF]

open access: green, 2011
Tomáš Oberhuber   +2 more
openalex  

Machine Learning Accelerated Global Search for Adsorption Geometries of Merocyanine Molecule on Hexagonal Boron Nitride

open access: yesJournal of Computational Chemistry, Volume 47, Issue 6, March 5, 2026.
Schematic illustration of HB238 adsorption on hBN(001) explored using Bayesian optimization and a MACE potential. The workflow accelerates potential‐energy‐surface exploration while retaining DFT‐level accuracy for molecular adsorption. ABSTRACT The adsorption of the merocyanine dye HB238 on hexagonal boron nitride (hBN) was investigated using a ...
Ritu Tomar, Thomas Bredow
wiley   +1 more source

Potent and Long‐Lasting Immunogenicity Generated by LNP‐mRNA gE Antigen Against Varicella Zoster Virus via an AI‐Assisted Pipeline

open access: yesAdvanced Science, Volume 13, Issue 14, 9 March 2026.
This study designs a novel mRNA‐LNP vaccine targeting VZV glycoprotein E (gE) for herpes zoster via an AI‐assisted pipeline. Validated in mice and rhesus macaques, the mRNA‐LNP vaccine shows strong humoral and cellular immune responses, with CD4+ T‐cell responses more effective and durable than Shingrix, offering a promising prophylactic option ...
Kai Dong   +6 more
wiley   +1 more source

SiCmiR Atlas: Single‐Cell miRNA Landscape Reveals Hub‐miRNA and Network Signatures in Human Cancers

open access: yesAdvanced Science, Volume 13, Issue 16, 18 March 2026.
SiCmiR predicts mature miRNA activity at single‐cell resolution using only 977 landmark genes, enabling scalable reconstruction of miRNA landscapes across diverse tissues and disease contexts. The SiCmiR Atlas integrates 9.36 million cells with analytical tools for hub‐miRNA discovery, biomarker prioritization, and regulatory network interrogation ...
Xiao‐Xuan Cai   +12 more
wiley   +1 more source

DNA Nanoflower LYTACs Enable Efficient VEGF Degradation and Verteporfin Loading for Combined Therapy of Wet Age‐Related Macular Degeneration

open access: yesAdvanced Science, Volume 13, Issue 16, 18 March 2026.
An integrated approach that combines a DNA nanoflower VEGF degrader with photodynamic therapy is developed for the treatment of wet age‐related macular degeneration, which reduces the risk of VEGF reactivation‐induced CNV recurrence and minimizes the systemic side effects associated with photodynamic therapy.
Mengxuan Li   +11 more
wiley   +1 more source

A Deep Representation Learning Method for Quantitative Immune Defense Function Evaluation and Its Clinical Applications

open access: yesAdvanced Science, Volume 13, Issue 17, 23 March 2026.
ImmuDef, a novel algorithm to quantitatively evaluate the anti‐infection immune defense function of an individual based on RNA‐seq data via a variational autoencoder (VAE) model. It is validated on 3200+ samples across four immune states with high accuracy. It can serve as a metric for disease severity and prognosis across pathogenic cohorts.
Zhen‐Lin Tan   +7 more
wiley   +1 more source

Home - About - Disclaimer - Privacy