ANN approach to evaluate the effects of supplementary cementitious materials on the compressive strength of recycled aggregate concrete

J Abellan-Garcia, J Fernández-Gómez, MI Khan… - … and Building Materials, 2023 - Elsevier
The growing awareness of environmental issues has triggered significant research into the
impacts generated on the environment during concrete production. To improve sustainability …

Modeling and process parameter optimization of laser cutting based on artificial neural network and intelligent optimization algorithm

X Ren, J Fan, R Pan, K Sun - The International Journal of Advanced …, 2023 - Springer
Laser cutting technology has proven advantageous in processing high-hardness metals,
ceramics, and composites. However, the process parameters significantly influence the kerf …

Improving predictive accuracy for punching shear strength in fiber-reinforced polymer concrete slab-column connections via robust deep learning

A Babiker, YM Abbas, MI Khan, JM Khatib - Structures, 2024 - Elsevier
Amidst the evolving landscape of structural engineering, this study addresses the pressing
need for a robust, data-driven model in the context of alternative reinforcement techniques …

Utilize the Prediction Results from the Neural Network Gate Recurrent Unit (GRU) Model to Optimize Reactive Power Usage in High-Rise Buildings.

A Rofii, B Soerowirdjo, R Irawan… - … Journal of Robotics …, 2024 - search.ebscohost.com
The growing urbanization and the construction sector, efficient use of electric energy
becomes important, especially the use of reactive power. If excessive use causes decreased …

From robust deep-learning regression to refined design formulas for punching shear strength of internal GFRP-reinforced flat slab-column connections

A Babiker, YM Abbas, MI Khan, FI Ismail - Engineering Structures, 2025 - Elsevier
Accurately modeling the punching shear strength (PSS) of glass fiber-reinforced polymer
(GFRP) flat slab-column connections is critical for ensuring structural safety and integrity …

Improving deep neural network random initialization through neuronal rewiring

L Scabini, B De Baets, OM Bruno - Neurocomputing, 2024 - Elsevier
The deep learning literature is continuously updated with new architectures and training
techniques. However, weight initialization is overlooked by most recent research, despite …

Modular Duality in Deep Learning

J Bernstein, L Newhouse - arXiv preprint arXiv:2410.21265, 2024 - arxiv.org
An old idea in optimization theory says that since the gradient is a dual vector it may not be
subtracted from the weights without first being mapped to the primal space where the …

Artificial neural network nonlinear transistor behavioral models: structure and parameter determination process based on the Cardiff model

M Tian, JJ Bell, R Quaglia, EM Azad… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
This article introduces a novel artificial neural network (ANN) structure determination
process based on the Cardiff model (CM), to determine ANN-based transistor nonlinear …

[HTML][HTML] Data driven health monitoring of Peltier modules using machine-learning-methods

BSPF Cotorogea, G Marino, S Vogl - SLAS technology, 2022 - Elsevier
Thermal cyclers are used to perform polymerase chain reaction runs (PCR runs) and Peltier
modules are the key components in these instruments. The demand for thermal cyclers has …

Artificial neural network based cost estimation of power losses in electricity distribution system

G Gören, B Dindar, Ö Gül - 2022 4th Global Power, Energy and …, 2022 - ieeexplore.ieee.org
Electrical energy demand is increasing day by day with developing technology and
increasing population. The limitation of resources reveals the importance of efficient use of …