Improved Conjugate Gradient Methods for Unconstrained Minimization Problems and Training Recurrent Neural Network

Engineering Reports, Journal Year: 2025, Volume and Issue: 7(2)

Published: Feb. 1, 2025

ABSTRACT This research introduces two conjugate gradient methods, BIV1 and BIV2, designed to enhance the efficiency performance of unconstrained optimization problems with only first derivative vectors. The study explores derivation new parameters investigates their practical performance. proposed BIV2 methods are compared traditional Hestenes‐Stiefel (HS) method through a series numerical experiments. These experiments evaluate on various test sourced from CUTE library other problem collections. Key metrics, including number iterations, function evaluations, CPU time, demonstrate that both offer superior effectiveness HS method. Furthermore, these is illustrated in context training artificial neural networks. Experimental results show achieve competitive terms convergence rate accuracy.

Language: Английский

---

Frequency regulation in a grid connected PV generation system using firefly algorithm

AIP conference proceedings, Journal Year: 2025, Volume and Issue: 3253, P. 020013 - 020013

Published: Jan. 1, 2025

Language: Английский

---

FPGA‐Based Realization of Intelligent Escalator Controller Using Artificial Neural Network

Journal of Electrical and Computer Engineering, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

In this work, a proposed intelligent controller has been designed and implemented for prototype of four stair‐step escalator. The required task is to manage the supplied power driving motor escalator according applied load on stair‐steps, which represented by number persons standing stair‐steps. must realize following objectives: adaptive consumption power, fast processing, high reliability, low cost, contribution work. backpropagation neural network (BPNN) was used in designing software reasons: learning, capability finding optimal solution. using MATLAB package; it involves three layers, they are input, hidden, output layers; input layer neurons, while hidden 10 neurons. After executing testing controller, observed that mean square error (MSE) value reached 8.68 × −18 , gradient 3.41 −9 there fitting 100% between desired actual outputs, indicates reliability accuracy controller. Finally, downloaded field‐programmable gate array (FPGA) ISE Design Suit software, as known, main characteristics FPGA small size, cost.

Language: Английский

---

Flood susceptibility assessment using deep neural networks and open-source spatial datasets in transboundary river basin

VIETNAM JOURNAL OF EARTH SCIENCES, Journal Year: 2025, Volume and Issue: unknown

Published: April 16, 2025

The Mekong Basin is the most critical transboundary river basin in Asia. This provides an abundant source of fresh water essential for development agriculture, domestic consumption, and industry, as well production hydroelectricity, it also contributes to ensuring food security worldwide. region often subject floods that cause significant damage human life, society, economy. However, flood risk management challenges this are increasingly substantial due conflicting objectives between several countries data sharing. study integrates deep learning with optimization algorithms, namely Grasshopper Optimisation Algorithm (GOA), Adam Stochastic Gradient Descent (SGD), open-source datasets identify probably occurring basin, covering Vietnam Cambodia. Various statistical indices, Area Under Curve (AUC), root mean square error (RMSE), absolute (MAE), coefficient determination (R²), were used evaluate susceptibility models. results show proposed models performed AUC values above 0.8, specifying DNN-Adam model achieved 0.98, outperforming DNN-GOA (AUC = 0.89), DNN-SGD 0.87), XGB 0.82. Regions very high concentrated Delta along River findings supporting decision-makers or planners proposing appropriate mitigation strategies, planning policies, particularly watershed.

Language: Английский

---

Neural Network Training Method Based on Dynamic Segmentation of the Training Dataset

2022 37th Youth Academic Annual Conference of Chinese Association of Automation (YAC), Journal Year: 2024, Volume and Issue: unknown, P. 1077 - 1082

Published: June 7, 2024

Language: Английский

---