Preferred Language
Articles
/
EkKM0JsBMeyNPGM3e-Hl
Update Quasi-Newton Algorithm for Training ANN
...Show More Authors

The proposed design of neural network in this article is based on new accurate approach for training by unconstrained optimization, especially update quasi-Newton methods are perhaps the most popular general-purpose algorithms. A limited memory BFGS algorithm is presented for solving large-scale symmetric nonlinear equations, where a line search technique without derivative information is used. On each iteration, the updated approximations of Hessian matrix satisfy the quasi-Newton form, which traditionally served as the basis for quasi-Newton methods. On the basis of the quadratic model used in this article, we add a new update of quasi-Newton form. One innovative features of this form's is its ability to estimate the energy function's or performance function with high order precision with second-order curvature while employ the given function value data and gradient. The global convergence of the proposed algorithm is established under some suitable conditions. Under some hypothesis the approach is established to be globally convergent. The updated approaches can be numerical and more efficient than the existing comparable traditional methods, as illustrated by numerical trials. Numerical results show that the given method is competitive to those of the normal BFGS methods. We show that solving a partial differential equation can be formulated as a multi-objective optimization problem, and use this formulation to propose several modifications to existing methods. Also the proposed algorithm is used to approximate the optimal scaling parameter, which can be used to eliminate the need to optimize this parameter. Our proposed update is tested on a variety of partial differential equations and compared to existing methods. These partial differential equations include the fourth order three dimensions nonlinear equation, which we solve in up to four dimensions, the convection-diffusion equation, all of which show that our proposed update lead to enhanced accuracy.

Crossref
View Publication Preview PDF
Quick Preview PDF
Publication Date
Thu Feb 01 2024
Journal Name
Infrastructures
Strength and Deformation of Concrete-Encased Grouting-Filled Steel Tubes Columns Exposed to Monotonic Quasi-Static Loading Conditions
...Show More Authors

This study aimed to evaluate the effectiveness of a novel concrete-encased column (CE) using small circular steel tubes filled with cementitious grouting material (GFST) as the primary reinforcement instead of traditional steel bars. The research involved three different types of reinforcement: conventional steel bars, concrete-filled steel tubes with 30% of the reinforcement ratio of steel bars, and concrete-filled steel tubes with the same reinforcement ratio as steel bars. Twenty-four circular concrete columns were tested and categorized into six groups based on the type of reinforcement employed. Each group comprised four columns, with one subjected to concentric axial load, two subjected to eccentric axial load (with eccentrici

... Show More
View Publication
Scopus (9)
Crossref (9)
Scopus Clarivate Crossref
Publication Date
Sun Mar 01 2009
Journal Name
Al-khwarizmi Engineering Journal
A Proposed Artificial Intelligence Algorithm for Assessing of Risk Priority for Medical Equipment in Iraqi Hospital
...Show More Authors

This paper presents a robust algorithm for the assessment of risk priority for medical equipment based on the calculation of static and dynamic risk factors and Kohnen Self Organization Maps (SOM). Four risk parameters have been calculated for 345 medical devices in two general hospitals in Baghdad. Static risk factor components (equipment function and physical risk) and dynamics risk components (maintenance requirements and risk points) have been calculated. These risk components are used as an input to the unsupervised Kohonen self organization maps. The accuracy of the network was found to be equal to 98% for the proposed system. We conclude that the proposed model gives fast and accurate assessment for risk priority and it works as p

... Show More
View Publication Preview PDF
Publication Date
Fri Dec 30 2022
Journal Name
Iraqi Journal Of Chemical And Petroleum Engineering
Permeability Prediction in One of Iraqi Carbonate Reservoir Using Statistical, Hydraulic Flow Units, and ANN Methods
...Show More Authors

   Permeability is an essential parameter in reservoir characterization because it is determined hydrocarbon flow patterns and volume, for this reason, the need for accurate and inexpensive methods for predicting permeability is important. Predictive models of permeability become more attractive as a result.

   A Mishrif reservoir in Iraq's southeast has been chosen, and the study is based on data from four wells that penetrate the Mishrif formation. This study discusses some methods for predicting permeability. The conventional method of developing a link between permeability and porosity is one of the strategies. The second technique uses flow units and a flow zone indicator (FZI) to predict the permeability of a rock mass u

... Show More
View Publication Preview PDF
Crossref (2)
Crossref
Publication Date
Tue Mar 01 2016
Journal Name
International Journal Of Engineering Research And Advanced Technology (ijerat)
Speeding Up Back-Propagation Learning (SUBPL) Algorithm: A New Modified Back_Propagation Algorithm
...Show More Authors

The convergence speed is the most important feature of Back-Propagation (BP) algorithm. A lot of improvements were proposed to this algorithm since its presentation, in order to speed up the convergence phase. In this paper, a new modified BP algorithm called Speeding up Back-Propagation Learning (SUBPL) algorithm is proposed and compared to the standard BP. Different data sets were implemented and experimented to verify the improvement in SUBPL.

View Publication
Publication Date
Thu Feb 01 2024
Journal Name
Structures
Accelerating reliability analysis of deteriorated simply supported concrete beam with a newly developed approach: MCS, FORM and ANN
...Show More Authors

Reliability analysis methods are used to evaluate the safety of reinforced concrete structures by evaluating the limit state function 𝑔(𝑋𝑖). For implicit limit state function and nonlinear analysis , an advanced reliability analysis methods are needed. Monte Carlo simulation (MCS) can be used in this case however, as the number of input variables increases, the time required for MCS also increases, making it a time consuming method especially for complex problems with implicit performance functions. In such cases, MCS-based FORM (First Order Reliability Method) and Artificial Neural Network-based FORM (ANN FORM) have been proposed as alternatives. However, it is important to note that both MCS-FORM and ANN-FORM can also be time-con

... Show More
View Publication
Scopus (10)
Crossref (9)
Scopus Clarivate Crossref
Publication Date
Wed Jan 30 2019
Journal Name
Modern Sport
Evaluation of training programs according to some physical abilities, functional indicators and achievement for men's 200m runners
...Show More Authors

The effectiveness of (200 m) of the events of extreme intensity and this is characterized by training in the anaerobic energy system prevailing in the result of this privacy as these are based on the physical abilities and functional indicators identified in this direction and hence the importance of research in the evaluation of training programs on the basis of physical abilities and some indicators of the functionality of the hostile 200 m . The study aimed to: 1. Evaluation of training programs according to physical abilities and some functional indicators of hostile men.The researchers used the descriptive analytical method to suit the nature of the research. The researchers selected them research sample by the deliberate method of the

... Show More
Publication Date
Mon Jan 01 2024
Journal Name
Aip Conference Proceedings
Modeling and analysis of thermal contrast based on LST algorithm for Baghdad city
...Show More Authors

View Publication
Scopus (2)
Crossref (2)
Scopus Crossref
Publication Date
Sun Apr 30 2023
Journal Name
Iraqi Journal Of Science
An Evolutionary Algorithm with Gene Ontology-Aware Crossover Operator for Protein Complex Detection
...Show More Authors

     Evolutionary algorithms (EAs), as global search methods, are proved to be more robust than their counterpart local heuristics for detecting protein complexes in protein-protein interaction (PPI) networks. Typically, the source of robustness of these EAs comes from their components and parameters. These components are solution representation, selection, crossover, and mutation. Unfortunately, almost all EA based complex detection methods suggested in the literature were designed with only canonical or traditional components. Further, topological structure of the protein network is the main information that is used in the design of almost all such components. The main contribution of this paper is to formulate a more robust E

... Show More
Scopus (3)
Scopus Crossref
Publication Date
Sun Sep 07 2014
Journal Name
Baghdad Science Journal
An Algorithm for nth Order Intgro-Differential Equations by Using Hermite Wavelets Functions
...Show More Authors

In this paper, the construction of Hermite wavelets functions and their operational matrix of integration is presented. The Hermite wavelets method is applied to solve nth order Volterra integro diferential equations (VIDE) by expanding the unknown functions, as series in terms of Hermite wavelets with unknown coefficients. Finally, two examples are given

View Publication Preview PDF
Crossref (1)
Crossref
Publication Date
Sun Mar 01 2015
Journal Name
Journal Of Engineering
Multi-Sites Multi-Variables Forecasting Model for Hydrological Data using Genetic Algorithm Modeling
...Show More Authors

A two time step stochastic multi-variables multi-sites hydrological data forecasting model was developed and verified using a case study. The philosophy of this model is to use the cross-variables correlations, cross-sites correlations and the two steps time lag correlations simultaneously, for estimating the parameters of the model which then are modified using the mutation process of the genetic algorithm optimization model. The objective function that to be minimized is the Akiake test value. The case study is of four variables and three sites. The variables are the monthly air temperature, humidity, precipitation, and evaporation; the sites are Sulaimania, Chwarta, and Penjwin, which are located north Iraq. The model performance was

... Show More
View Publication Preview PDF