Preferred Language
Articles
/
ixaF44sBVTCNdQwCV-Nn
Bayesian Regularized Neural Network Model Development for Predicting Daily Rainfall from Sea Level Pressure Data: Investigation on Solving Complex Hydrology Problem
...Show More Authors

Prediction of daily rainfall is important for flood forecasting, reservoir operation, and many other hydrological applications. The artificial intelligence (AI) algorithm is generally used for stochastic forecasting rainfall which is not capable to simulate unseen extreme rainfall events which become common due to climate change. A new model is developed in this study for prediction of daily rainfall for different lead times based on sea level pressure (SLP) which is physically related to rainfall on land and thus able to predict unseen rainfall events. Daily rainfall of east coast of Peninsular Malaysia (PM) was predicted using SLP data over the climate domain. Five advanced AI algorithms such as extreme learning machine (ELM), Bayesian regularized neural networks (BRNNs), Bayesian additive regression trees (BART), extreme gradient boosting (xgBoost), and hybrid neural fuzzy inference system (HNFIS) were used considering the complex relationship of rainfall with sea level pressure. Principle components of SLP domain correlated with daily rainfall were used as predictors. The results revealed that the efficacy of AI models is predicting daily rainfall one day before. The relative performance of the models revealed the higher performance of BRNN with normalized root mean square error (NRMSE) of 0.678 compared with HNFIS (NRMSE = 0.708), BART (NRMSE = 0.784), xgBoost (NRMSE = 0.803), and ELM (NRMSE = 0.915). Visual inspection of predicted rainfall during model validation using density-scatter plot and other novel ways of visual comparison revealed the ability of BRNN to predict daily rainfall one day before reliably.

Scopus Clarivate Crossref
View Publication
Publication Date
Wed Jan 01 2020
Journal Name
International Journal Of Computational Intelligence Systems
Evolutionary Feature Optimization for Plant Leaf Disease Detection by Deep Neural Networks
...Show More Authors

View Publication
Scopus (40)
Crossref (39)
Scopus Clarivate Crossref
Publication Date
Wed May 13 2020
Journal Name
Nonlinear Engineering
Two meshless methods for solving nonlinear ordinary differential equations in engineering and applied sciences
...Show More Authors
Abstract<p>In this paper, two meshless methods have been introduced to solve some nonlinear problems arising in engineering and applied sciences. These two methods include the operational matrix Bernstein polynomials and the operational matrix with Chebyshev polynomials. They provide an approximate solution by converting the nonlinear differential equation into a system of nonlinear algebraic equations, which is solved by using <italic>Mathematica</italic>® 10. Four applications, which are the well-known nonlinear problems: the magnetohydrodynamic squeezing fluid, the Jeffery-Hamel flow, the straight fin problem and the Falkner-Skan equation are presented and solved using the proposed methods. To ill</p> ... Show More
View Publication
Crossref (10)
Crossref
Publication Date
Thu Aug 31 2023
Journal Name
Journal Of Kufa For Mathematics And Computer
Four Points Block Method with Second Derivative for Solving First Order Ordinary Differential Equations
...Show More Authors

Publication Date
Fri Mar 01 2024
Journal Name
Partial Differential Equations In Applied Mathematics
A hybrid technique for solving fractional delay variational problems by the shifted Legendre polynomials
...Show More Authors

This study presents a practical method for solving fractional order delay variational problems. The fractional derivative is given in the Caputo sense. The suggested approach is based on the Laplace transform and the shifted Legendre polynomials by approximating the candidate function by the shifted Legendre series with unknown coefficients yet to be determined. The proposed method converts the fractional order delay variational problem into a set of (n + 1) algebraic equations, where the solution to the resultant equation provides us the unknown coefficients of the terminated series that have been utilized to approximate the solution to the considered variational problem. Illustrative examples are given to show that the recommended appro

... Show More
View Publication Preview PDF
Scopus Crossref
Publication Date
Wed Aug 30 2023
Journal Name
Iraqi Journal Of Science
Computational methods for solving nonlinear ordinary differential equations arising in engineering and applied sciences
...Show More Authors

In this paper, the computational method (CM) based on the standard polynomials has been implemented to solve some nonlinear differential equations arising in engineering and applied sciences. Moreover, novel computational methods have been developed in this study by orthogonal base functions, namely Hermite, Legendre, and Bernstein polynomials. The nonlinear problem is successfully converted into a nonlinear algebraic system of equations, which are then solved by Mathematica®12. The developed computational methods (D-CMs) have been applied to solve three applications involving well-known nonlinear problems: the Darcy-Brinkman-Forchheimer equation, the Blasius equation, and the Falkner-Skan equation, and a comparison between t

... Show More
View Publication Preview PDF
Scopus (1)
Scopus Crossref
Publication Date
Wed May 13 2020
Journal Name
Nonlinear Engineering
Two meshless methods for solving nonlinear ordinary differential equations in engineering and applied sciences
...Show More Authors
Abstract<p>In this paper, two meshless methods have been introduced to solve some nonlinear problems arising in engineering and applied sciences. These two methods include the operational matrix Bernstein polynomials and the operational matrix with Chebyshev polynomials. They provide an approximate solution by converting the nonlinear differential equation into a system of nonlinear algebraic equations, which is solved by using <italic>Mathematica</italic>® 10. Four applications, which are the well-known nonlinear problems: the magnetohydrodynamic squeezing fluid, the Jeffery-Hamel flow, the straight fin problem and the Falkner-Skan equation are presented and solved using the proposed methods. To ill</p> ... Show More
Scopus (14)
Crossref (10)
Scopus Clarivate Crossref
Publication Date
Sun Dec 07 2014
Journal Name
Baghdad Science Journal
Convergence of the Generalized Homotopy Perturbation Method for Solving Fractional Order Integro-Differential Equations
...Show More Authors

In this paper,the homtopy perturbation method (HPM) was applied to obtain the approximate solutions of the fractional order integro-differential equations . The fractional order derivatives and fractional order integral are described in the Caputo and Riemann-Liouville sense respectively. We can easily obtain the solution from convergent the infinite series of HPM . A theorem for convergence and error estimates of the HPM for solving fractional order integro-differential equations was given. Moreover, numerical results show that our theoretical analysis are accurate and the HPM can be considered as a powerful method for solving fractional order integro-diffrential equations.

... Show More
View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Sep 07 2014
Journal Name
Baghdad Science Journal
Deriving the Composite Simpson Rule by Using Bernstein Polynomials for Solving Volterra Integral Equations
...Show More Authors

In this paper we use Bernstein polynomials for deriving the modified Simpson's 3/8 , and the composite modified Simpson's 3/8 to solve one dimensional linear Volterra integral equations of the second kind , and we find that the solution computed by this procedure is very close to exact solution.

View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Thu Jul 20 2023
Journal Name
Ibn Al-haitham Journal For Pure And Applied Sciences
Constructing RKM-Method for Solving Fractional Ordinary Differential Equations of Fifth-Order with Applications
...Show More Authors

This paper sheds the light on the vital role that fractional ordinary differential equations(FrODEs) play in the mathematical modeling and in real life, particularly in the physical conditions. Furthermore, if the problem is handled directly by using numerical method, it is a far more powerful and efficient numerical method in terms of computational time, number of function evaluations, and precision. In this paper, we concentrate on the derivation of the direct numerical methods for solving fifth-order FrODEs  in one, two, and three stages. Additionally, it is important to note that the RKM-numerical methods with two- and three-stages for solving fifth-order ODEs are convenient, for solving class's fifth-order FrODEs. Numerical exa

... Show More
View Publication Preview PDF
Crossref
Publication Date
Mon Jan 01 2018
Journal Name
Proceedings Of The 10th International Joint Conference On Computational Intelligence
Deep Classifier Structures with Autoencoder for Higher-level Feature Extraction
...Show More Authors

View Publication
Crossref (2)
Scopus Crossref