NUMERICAL COMPUTING TO SOLVE THE NONLINEAR CORNEAL SYSTEM OF EYE SURGERY USING THE CAPABILITY OF MORLET WAVELET ARTIFICIAL NEURAL NETWORKS DOI Creative Commons
Bo Wang, J.F. Gómez‐Aguilar, Zulqurnain Sabir

et al.

Fractals, Journal Year: 2022, Volume and Issue: 30(05)

Published: Jan. 25, 2022

In this study, a novel heuristic computing technique is presented to solve bioinformatics problem for the corneal shape model of eye surgery using Morlet wavelet artificial neural network optimized by global search schemes, i.e. genetic algorithm (GA), local technique, sequential quadratic programming (SQP) and hybrid GA-SQP. To measure performance design configuration, different cases based on nonlinear second-order differential equations governing have been solved effectively. The numerical procedure Adams method implemented comparison purpose outcomes stochastic solver, which shows worth present scheme accuracy convergence with negligible values absolute error in range 10[Formula: see text] text]. Furthermore, statistical measures are “mean error”, “root mean square error” “coefficient Theil’s inequality” additionally endorsed consistently accurate integrated intelligent framework solving model.

Language: Английский

Chat-GPT; validating Technology Acceptance Model (TAM) in education sector via ubiquitous learning mechanism DOI
Naveed Saif, Sajid Ullah Khan, Imrab Shaheen

et al.

Computers in Human Behavior, Journal Year: 2023, Volume and Issue: 154, P. 108097 - 108097

Published: Dec. 27, 2023

Language: Английский

Citations

108
Hybrid deep CNN-SVR algorithm for solar radiation prediction problems in Queensland, Australia DOI Creative Commons
Sujan Ghimire, Binayak Bhandari, David Casillas-Pérez

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2022, Volume and Issue: 112, P. 104860 - 104860

Published: April 13, 2022

This study proposes a new hybrid deep learning (DL) model, the called CSVR, for Global Solar Radiation (GSR) predictions by integrating Convolutional Neural Network (CNN) with Support Vector Regression (SVR) approach. First, CNN algorithm is used to extract local patterns as well common features that occur recurrently in time series data at different intervals. Then, SVR subsequently adopted replace fully connected layers predict daily GSR six solar farms Queensland, Australia. To develop CSVR we adopt most pertinent meteorological variables from Climate Model and Scientific Information Landowners database. From pool of Models ground-based observations, optimal are selected through metaheuristic Feature Selection algorithm, an Atom Search Optimization method. The hyperparameters proposed optimized mean HyperOpt method, overall performance objective benchmarked against eight alternative DL methods, some other Machine Learning approaches (LSTM, DBN, RBF, BRF, MARS, WKNNR, GPML M5TREE) methods. results obtained shows model can offer several predictive advantages over models, conventional ML models. Specifically, note recorded root square error/mean absolute error ranging between ≈ 2.172–3.305 MJ m2/1.624–2.370 m2 tested compared 2.514–3.879 m2/1.939–2.866 algorithms. Consistent this predicted error, correlation measured GSR, including Willmott's, Nash-Sutcliffe's coefficient Legates & McCabe's Index was relatively higher methods all sites. Accordingly, advocates merits provide viable accurately renewable energy exploitation, demand or forecasting-based applications.

Language: Английский

Citations

70
Output power prediction of stratospheric airship solar array based on surrogate model under global wind field DOI Creative Commons
Kangwen Sun, Siyu Liu,

Yixiang GAO

et al.

Chinese Journal of Aeronautics, Journal Year: 2024, Volume and Issue: 38(4), P. 103244 - 103244

Published: Sept. 18, 2024

Language: Английский

Citations

33
Implementation of high step-up power converter for fuel cell application with hybrid MPPT controller DOI Creative Commons

V. Prashanth,

Shaik Rafikiran,

CH Hussaian Basha

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Feb. 9, 2024

Abstract As of now, there are multiple types renewable energy sources available in nature which hydro, wind, tidal, and solar. Among all that the solar source is used many applications because its features low maitainence cost, less human power for handling, a clean source, more availability nature, reduced carbon emissions. However, disadvantages networks continuously depending on weather conditions, high complexity storage, lots installation place required. So, this work, Proton Exchange Membrane Fuel Stack (PEMFS) utilized supplying to local consumers. The merits fuel stack density, ability work at very temperature values, efficient heat maintenance, water management. Also, gives quick startup response. only demerit PEMFS excessive current production, plus output voltage. To optimize supply stack, Wide Input Operation Single Switch Boost Converter (WIOSSBC) circuit placed across improve load voltage profile. advantages WIOSSBC ripples, uniform supply, good conversion ratio. Another issue nonlinear production. linearize Grey Wolf Algorithm Dependent Fuzzy Logic Methodology (GWADFLM) introduced article maintaining operating point cell near Maximum Power Point (MPP) place. entire system investigated by utilizing MATLAB software.

Language: Английский

Citations

21
Study on Integrated Neural Networks and Fuzzy Logic Control for Autonomous Electric Vehicles DOI
J. Vimala Devi, Rajesh V. Argiddi,

P. Renuka

et al.

Advances in web technologies and engineering book series, Journal Year: 2024, Volume and Issue: unknown, P. 104 - 127

Published: May 16, 2024

This chapter presents a comprehensive study on the integration of neural networks and fuzzy logic control techniques for enhancing autonomy electric vehicles (EVs). The these two paradigms aims to overcome limitations traditional approaches by leveraging complementary strengths in learning complex patterns handling uncertainty imprecision. discusses design, implementation, evaluation an autonomous EV system that utilizes vehicle dynamics decision-making various driving scenarios. Through extensive simulations experiments, effectiveness robustness proposed integrated approach are demonstrated, showcasing its potential improving safety, efficiency, adaptability EVs real-world environments.

Language: Английский

Citations

19
Identification of a different design of a photovoltaic thermal collector based on fuzzy logic control and the ARMAX model DOI

Alaa Hamada,

Mohamed Emam, H.A. Refaey

et al.

Thermal Science and Engineering Progress, Journal Year: 2024, Volume and Issue: 48, P. 102395 - 102395

Published: Jan. 11, 2024

Language: Английский

Citations

18
Binary firefly algorithm based reconfiguration for maximum power extraction under partial shading and machine learning approach for fault detection in solar PV arrays DOI

S. Saravanan,

R. Senthil Kumar,

P. Balakumar

et al.

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 154, P. 111318 - 111318

Published: Feb. 2, 2024

Language: Английский

Citations

17
Solar irradiance forecasting based on direct explainable neural network DOI
Huaizhi Wang, Cai Ren, Bin Zhou

et al.

Energy Conversion and Management, Journal Year: 2020, Volume and Issue: 226, P. 113487 - 113487

Published: Oct. 12, 2020

Language: Английский

Citations

88
Evaluating neural network and linear regression photovoltaic power forecasting models based on different input methods DOI Creative Commons
Mutaz AlShafeey, Csaba Csáki

Energy Reports, Journal Year: 2021, Volume and Issue: 7, P. 7601 - 7614

Published: Nov. 1, 2021

As Photovoltaic (PV) energy is impacted by various weather variables such as solar radiation and temperature, one of the key challenges facing forecasting choosing right inputs to achieve most accurate prediction.Weather datasets, past power data sets, or both sets can be utilized build different models.However, operators grid-connected PV farms do not always have full available them especially over an extended period time required techniques multiple regression (MR) artificial neural network (ANN).Therefore, research reported here considered these two main approaches building prediction models compared their performance when utilizing structural, time-series, hybrid methods for input.Three years generation (of actual farm) well historical same location) with several were collected test six models.Models built designed forecast a 24-hour ahead horizon 15 min resolutions.Results comparative analysis show that accuracy depending on input method used model: ANN perform better than MR regardless used.The results in techniques, while using time-series least models.Furthermore, sensitivity shows poor quality does impact negatively structural approach.

Language: Английский

Citations

76
Hybrid Deep Learning Model for Fault Detection and Classification of Grid-Connected Photovoltaic System DOI Creative Commons
Moath Alrifaey, Wei Hong Lim, Chun Kit Ang

et al.

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 13852 - 13869

Published: Jan. 1, 2022

Effective fault detection and classification play essential roles in reducing the hazards such as electric shocks fire photovoltaic (PV) systems. However, issues of interest for PV systems remain an open-ended challenge due to manual time-consuming processes that require relevant domain knowledge experience diagnoses. This paper proposes a hybrid deep-learning (DL) model-based combined architectures novel DL approaches achieve real-time automatic system. research employed wavelet packet transform (WPT) data preprocessing technique handle voltage signal collected feeding them inputs consist equilibrium optimizer algorithm (EOA) long short-term memory (LSTM-SAE) approaches. The are able extract features automatically from preprocessed without requiring any previous knowledge, therefore can override traditional shortages feature extraction selection optimal extracted features. These desirable anticipated speed up capability proposed model with higher accuracy. In order determine performance model, we carried out comprehensive evaluation study on 250-kW grid-connected this paper, symmetrical asymmetrical faults have been studied involving all phases ground single phase ground, phase, three-phase ground. simulation results validate efficacy terms computation time, accuracy detection, noise robustness. Comprehensive comparisons between studies demonstrate multidisciplinary applications present study.

Language: Английский

Citations

52