Results 271 to 280 of about 188,667 (380)

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

Solar 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, Doga Can Öner, Theresa Trötschler, Jonas Schönauer, Stefan J. Rupitsch, Ralf Preu, Stefan Rein, Matthias Demant   +7 more
wiley   +1 more source

The history of cardiopulmonary bypass and the evolution of <i>pneuma</i> in cardiopulmonary medicine. [PDF]

Arch Med Sci Atheroscler Dis
Leivaditis V, Mavroudes G, Braun Lambur H, Baikoussis N, Liolis E, Tasios K, Tchabashvili L, Theofanis G, Antzoulas A, Litsas D, Papadopoulos PD, Nikolakopoulos K, Dahm M, Papadoulas S, Mulita F.   +14 more
europepmc   +1 more source

Comparison of different loss functions (%). Verify the optimal combination weight of Dice Loss and BCE Loss.

Kerang Cao (21602045), Miao Zhao (527763), Minghui Geng (21602048), Shuai Zheng (482786), Hoekyung Jung (21602051)   +4 more
openalex   +1 more source

Distributed Lower‐Crustal Flow Beneath the Central Xianshuihe–Xiaojiang Fault System: Reconciling Geodesy and Geology

Geophysical Research Letters, Volume 53, Issue 5, 16 March 2026.
Abstract We use recently compiled GNSS velocities across the Zemuhe‐Daliangshan fault zone, part of the central Xianshuihe‐Xiaojiang fault system, to reconcile a long‐standing mismatch between geodetic and geologic slip‐rate estimates. We show that conventional elastic dislocation models yield slip rates and locking depths that conflict with seismic ...
X. Rui, E. O. Lindsey
wiley   +1 more source

Year-round hourly temperature and humidity sensor readings from arid caves, Judean Desert, Israel. [PDF]

Sci Data
Ullman M, Kletzerman M, Oron A, Porat R, Langford B, Frumkin A, Jaffe Y, Davidovich U, Marom N.   +8 more
europepmc   +1 more source

Segmentation performance results of DEFIF-Net using different weights of the Dice loss () and BCE loss () in the combined loss function used.

Zhanlin Ji (12581332), Shengnan Hao (12582709), Quanming Zhao (7297451), Zidong Yu (12297101), Hongjiu Liu (21446866), Lei Li (29537), Ivan Ganchev (12581329)   +6 more
openalex   +1 more source

Identification report coins Harelbeke [PDF]

, 2015
Verboven, Koenraad
core  

Machine Learning Prediction of Laccase‐Catalyzed Oxidation of Aromatic Compounds Using Curated Enzyme‐Specific Datasets

Journal of Computational Chemistry, Volume 47, Issue 7, March 15, 2026.
We curate laccase‐substrate datasets and train five classifiers, from regularized logistic regression to tree‐based models and ChemBERTa, to predict whether a substrate will be oxidized. Feature importance and attention maps projected onto molecular substructures make the predictions interpretable and useful for pre‐screening before the bench ...
Yulia Kulagina, Christian Goldhahn, Ramon Weishaupt, Mark Schubert   +3 more
wiley   +1 more source