Results 61 to 70 of about 63,026 (172)

Decentralized Federated Learning for Wind Turbine Bearing Prognostics Under Data Scarcity and Statistical Heterogeneity

Energy Science &Engineering, EarlyView.
This paper proposes a decentralized peer‐to‐peer federated learning framework for wind turbine bearing remaining useful life prediction, introducing a virtual client paradigm in which statistical health indicators serve as independent feature‐level clients—enabling privacy‐preserving collaborative prognostics from a single physical asset under ...
Jihene Sidhom, Lotfi Saidi, Eric Bechhoefer   +2 more
wiley   +1 more source

Do optimization methods in deep learning applications matter? [PDF]

, 2020
With advances in deep learning, exponential data growth and increasing model complexity, developing efficient optimization methods are attracting much research attention.
Kiran, Mariam, Ozyildirim, Buse Melis
core   +1 more source

The Illusion of Structural Order: Evaluating the Suppression of Amorphous Carbon Black Pigment Bands in SSE‐Processed Handheld Raman Spectra

Journal of Raman Spectroscopy, EarlyView.
The handheld Raman with SSE system efficiently mitigates fluorescence; however, it may also bias the Raman response towards graphitic domains in carbon‐based black pigments, thereby concealing amorphous carbon contributions that are critical for pigment type identification.
Zeynep Alp, Christoph Herm
wiley   +1 more source

Thin‐layer drying kinetics and mathematical modelling of osmotically pretreated vacuum dried green chilli

JSFA reports, EarlyView.
Abstract Background Chilli is highly perishable, often requiring drying to extend shelf life. This study assesses and compares the drying kinetics of osmotically pretreated green chilli under vacuum drying conditions while evaluating suitable mathematical models and calculating effective moisture diffusivity and activation energy. Results Sliced chilli
Md. Raihanul Haque, Md. Iftekhar Kabir, Md. Nahidul Islam, Md. Mojaffor Hosain, Md. Sazzat Hossain Sarker   +4 more
wiley   +1 more source

Stochastic computing with Levenberg–Marquardt neural networks for the study of radiative transportation phenomena in three-dimensional Carreau nanofluid model subjected to activation energy and porous medium

Chemical Engineering Journal Advances
The objective of this research is to establish the modelling and evaluation of a differential mathematical system for the radiated Carreau nanofluid model (RCNFM) by exploiting the skills of stochastic computing with Levenberg–Marquardt neural networks ...
Zahoor Shah, Muhammad Asif Zahoor Raja, Faisal Shahzad, Muhammad Waqas, Fahad Alblehai, Sameer Nooh, Sajjad Shaukat Jamal, Nurnadiah Zamri, Shaxnoza Saydaxmetova, Abdelaziz Nasr   +9 more
doaj   +1 more source

"Parallel Training Considered Harmful?": Comparing series-parallel and parallel feedforward network training

, 2018
Neural network models for dynamic systems can be trained either in parallel or in series-parallel configurations. Influenced by early arguments, several papers justify the choice of series-parallel rather than parallel configuration claiming it has a ...
Aguirre, Luis A., Ribeiro, Antônio H.
core   +1 more source

Analytical and Numerical Soliton Solutions of the Shynaray II‐A Equation Using the G′G,1G$$ \left(\frac{G^{\prime }}{G},\frac{1}{G}\right) $$‐Expansion Method and Regularization‐Based Neural Networks

Mathematical Methods in the Applied Sciences, EarlyView.
ABSTRACT Nonlinear differential equations play a fundamental role in modeling complex physical phenomena across solid‐state physics, hydrodynamics, plasma physics, nonlinear optics, and biological systems. This study focuses on the Shynaray II‐A equation, a relatively less‐explored parametric nonlinear partial differential equation that describes ...
Aamir Farooq, H. W. A. Riaz, Sadique Rehman, M. Mamun Miah, Wen Xiu Ma   +4 more
wiley   +1 more source

Application of Levenberg-Marquardt backpropagation algorithm to the Yamada-Ota model for thermal study of a TiO2-SiO2/Hexanol hybrid fluid: A heat transfer system

Case Studies in Thermal Engineering
Levenberg-Marquardt backpropagation has emerged as a powerful method in the field of heat transfer, despite its original use in the training of artificial neural networks.
Nidhi N. Pai, K. Preethi Salian, K.R. Vasanth, K. Ganesh Kumar   +3 more
doaj   +1 more source

Splitting methods with variable metric for KL functions

, 2013
We study the convergence of general abstract descent methods applied to a lower semicontinuous nonconvex function f that satisfies the Kurdyka-Lojasiewicz inequality in a Hilbert space.
Frankel, Pierre, Garrigos, Guillaume, Peypouquet, Juan   +2 more
core   +1 more source

Single‐Breathhold 3D MR Elastography in the Liver, With Simultaneous R2* and PDFF Mapping

Magnetic Resonance in Medicine, EarlyView.
Purpose To develop a sequence for the rapid acquisition of MR elastography (MRE) parameters in 3D, with simultaneous measurement of proton‐density fat fraction (PDFF) and R2* for multiparametric assessment of liver disease. Methods The proposed sequence uses an interleaved motion‐encoding scheme to acquire 3D volumes of all motion encodings and wave ...
Donovan P Tripp, Anne‐Sophie van Schelt, Omar Darwish, Karl P Kunze, Shamsa Al Harthy, Nader S Metwalli, Ahmed M Gharib, Claudia Prieto, René M Botnar, Ralph Sinkus, Radhouene Neji   +10 more
wiley   +1 more source