Results 161 to 170 of about 8,544 (259)

Development and validation of a deep survival model to predict time to seizure from routine electroencephalography

Epilepsia, EarlyView.
Abstract Objective This study was undertaken to develop and validate a deep survival model (EEGSurvNet) that analyzes routine electroencephalography (EEG) to predict individual seizure risk over time, comparing its performance to traditional clinical predictors such as interictal epileptiform discharges (IEDs).
Émile Lemoine, An Qi Xu, Mezen Jemel, Frédéric Lesage, Dang K. Nguyen, Elie Bou Assi   +5 more
wiley   +1 more source

Real-time construction safety monitoring using a drone based deep hybrid attention model. [PDF]

Sci Rep
Sujit K, Indhumathi K, Mohan G, Jose NN, Ramudu K, Abdennaji TS, Cheepurupalli NR, Saidana T, Fissha Y.   +8 more
europepmc   +1 more source

Research on Deformation Prediction of Small Interval Tunnel Based on Machine Learning and Numerical Simulation

Energy Science &Engineering, EarlyView.
This study leverages machine learning algorithms—specifically artificial neural networks (ANN) and genetic programming (GP)—to forecast and analyze variations in vault settlement measurements during excavation of small interval tunnel. A settlement prediction model was developed and validated through comparative analysis with regression to evaluate the
Wenjie Zhai, Jia Xue, Yongjie Fu, Beichen Yu, Yan Zhu, Man Yuan, Mingbo Chi, Zhentao Li   +7 more
wiley   +1 more source

A hybrid analytical-optimization framework for sidelobe suppression and beamwidth control in linear antenna arrays. [PDF]

Sci Rep
Elkhawaga AM, Aboualalaa M, Abd Elnaby MM.   +2 more
europepmc   +1 more source

Feasibility of Wind‐Powered Green Hydrogen Production via a Hybrid Graph Neural Network‐Transformer Forecasting Model

Energy Science &Engineering, EarlyView.
ABSTRACT Accurate long‐term wind speed forecasting is pivotal for the strategic planning of renewable energy infrastructure, particularly for assessing the techno‐economic feasibility of wind‐powered green hydrogen facilities. However, capturing the complex spatiotemporal dependencies in climate data remains a significant challenge. This study proposes
Iman Baghaei, Mojtaba Mirhosseini, Alireza Zahedi   +2 more
wiley   +1 more source

Refined trajectory smoothing and deep learning classification of human sperm motility. [PDF]

Hum Reprod
Shahali S, Mortimer ST, McLachlan R, O'Bryan MK, Zander-Fox D, Mortimer D, Ackermann K, Neild A, Nosrati R.   +8 more
europepmc   +1 more source

Efficient Numerical Framework for Geothermal Energy Production Optimization in Fracture‐Controlled Reservoirs

International Journal for Numerical Methods in Fluids, EarlyView.
We introduce an efficient open‐source numerical framework for the automated search for the placements of injection and production wells in hot fracture‐controlled reservoirs that sustainably optimize geothermal energy production. We model the reservoirs as discrete fracture networks in 3D. The fluid flow and heat transport in the reservoirs are modeled
Ondřej Pártl, Ernesto Meneses Rioseco
wiley   +1 more source

Sparse Transform and Compressed Sensing Methods to Improve Efficiency and Quality in Magnetic Resonance Medical Imaging. [PDF]

Sensors (Basel)
Villota S, Inga E.
europepmc   +1 more source

Local Polynomial Regression and Filtering for a Versatile Mesh‐Free PDE Solver

International Journal for Numerical Methods in Fluids, EarlyView.
A high‐order, mesh‐free finite difference method for solving differential equations is presented. Both derivative approximation and scheme stabilisation is carried out by parametric or non‐parametric local polynomial regression, making the resulting numerical method accurate, simple and versatile. Numerous numerical benchmark tests are investigated for
Alberto M. Gambaruto
wiley   +1 more source

Graphical Fourier-coefficient analysis as a paper-based method for teaching structure factors. [PDF]

Acta Crystallogr E Crystallogr Commun
Weirich TE.
europepmc   +1 more source