Results 101 to 110 of about 6,102 (204)

Calibration‐Free Single‐Frame Super‐Resolution Fluorescence Microscopy

Laser &Photonics Reviews, EarlyView.
A deep learning framework reconstructs super‐resolved fluorescence images from a single dense camera frame, without any prior calibration or knowledge of the microscope. Trained solely on synthetic data, it generalizes across imaging setups and conditions.
Anežka Dostálová, Dominik Vašinka, Robert Stárek, Miroslav Ježek   +3 more
wiley   +1 more source

Monitoring and investigation to control the brain network disease under immunotherapy by using fractional operator. [PDF]

Sci Rep
Farman M, Talib A, Jamil K, Nisar KS, Sambas A, Bayram M, Hafez M.   +6 more
europepmc   +1 more source

Deep Learning Using Isotroping, Laplacing, Eigenvalues Interpolative Binding, and Convolved Determinants with Normed Mapping for Large-Scale Image Retrieval. [PDF]

Sensors (Basel), 2021
Kanwal K, Tehseen Ahmad K, Khan R, Alhusaini N, Jing L.   +4 more
europepmc   +1 more source

Kernel Bounds for Parabolic Operators Having First‐Order Degeneracy at the Boundary

Mathematische Nachrichten, EarlyView.
ABSTRACT We study kernel estimates for parabolic problems governed by singular elliptic operators ∑i,j=1N+1qijDij+cDyy,cγ+1>0,γ=qN+1,N+1,$$\begin{equation*} \sum _{i,j=1}^{N+1}q_{ij}D_{ij}+c\frac{D_y}{y},\qquad \frac{c}{\gamma }+1>0, \quad \gamma =q_{N+1,N+1}, \end{equation*}$$in the half‐space R+N+1={(x,y):x∈RN,y>0}$\mathbb {R}^{N+1}_+=\lbrace (x,y ...
L. Negro, C. Spina
wiley   +1 more source

Uniform Convergence of Deep Neural Networks With Lipschitz Continuous Activation Functions and Variable Widths. [PDF]

IEEE Trans Inf Theory
Xu Y, Zhang H.
europepmc   +1 more source

Evaluation of a connectivity-based imaging metric that reflects functional decline in Multiple Sclerosis. [PDF]

PLoS One, 2021
Koenig KA, Beall EB, Sakaie KE, Ontaneda D, Stone L, Rao SM, Nakamura K, Jones SE, Lowe MJ.   +8 more
europepmc   +1 more source

Designing γ‐TiAl Alloys With Refined Twin‐Lamellar Microstructures via Machine Learning‐Driven Phase‐Field Methods

Materials Genome Engineering Advances, EarlyView.
Dual‐phase γ‐TiAl alloys with refined twin‐lamellar (RTL) structures exhibit optimal strength‐ductility synergy. Here, phase‐field simulations reveal composition‐stress‐dependent refined twin‐lamellar (RTL) microstructure evolution. Machine learning (CatBoost + NSGA‐III) trained on phase‐field images predicts optimal RTL‐stress‐composition design space.
Jianwei Li, Zhenqiang Xiong, Chuanxin Liang, Tianjiao Dong, Heran Wang, Mengyuan Hao, Liqiang He, Tianlong Zhang, Dong Wang   +8 more
wiley   +1 more source

A New Efficient Explicit Deferred Correction Framework: Analysis and Applications to Hyperbolic PDEs and Adaptivity. [PDF]

Commun Appl Math Comput
Micalizzi L, Torlo D.
europepmc   +1 more source

Breaking Extrapolation Barriers: Dual Innovations for Property and Component Design of Multi‐Component Alloy

Materials Genome Engineering Advances, EarlyView.
This study breaks extrapolation barriers in alloy design by merging symbolic regression with latent space sampling. The dual‐strategy framework enables accurate prediction of high‐hardness properties and navigates uncharted compositional spaces. The approach successfully designs novel high‐entropy alloys with hardness exceeding 863.5 HV, demonstrating ...
Zhigang Yu, Boyu Zhao, Jianhua Chen, Jun Luan, Yunying Fan, Xingli Zou, Xionggang Lu   +6 more
wiley   +1 more source

Lower Bounds on the Noiseless Worst-Case Complexity of Efficient Global Optimization. [PDF]

J Optim Theory Appl
Xu W, Jiang Y, Maddalena ET, Jones CN.
europepmc   +1 more source