The aim of this paper is to design fast neural networks to approximate periodic functions, that is, design a fully connected networks contains links between all nodes in adjacent layers which can speed up the approximation times, reduce approximation failures, and increase possibility of obtaining the globally optimal approximation. We training suggested network by Levenberg-Marquardt training algorithm then speeding suggested networks by choosing most activation function (transfer function) which having a very fast convergence rate for reasonable size networks. In all algorithms, the gradient of the performance function (energy function) is used to determine how to adjust the weights such that the performance function is minimized, where the back propagation algorithm has been used to increase the speed of training.
In this paper, an algorithm is suggested to train a single layer feedforward neural network to function as a heteroassociative memory. This algorithm enhances the ability of the memory to recall the stored patterns when partially described noisy inputs patterns are presented. The algorithm relies on adapting the standard delta rule by introducing new terms, first order term and second order term to it. Results show that the heteroassociative neural network trained with this algorithm perfectly recalls the desired stored pattern when 1.6% and 3.2% special partially described noisy inputs patterns are presented.
In this article, we design an optimal neural network based on new LM training algorithm. The traditional algorithm of LM required high memory, storage and computational overhead because of it required the updated of Hessian approximations in each iteration. The suggested design implemented to converts the original problem into a minimization problem using feed forward type to solve non-linear 3D - PDEs. Also, optimal design is obtained by computing the parameters of learning with highly precise. Examples are provided to portray the efficiency and applicability of this technique. Comparisons with other designs are also conducted to demonstrate the accuracy of the proposed design.
(1)
The purpose of this paper is to introduce and study the concepts of fuzzy generalized open sets, fuzzy generalized closed sets, generalized continuous fuzzy proper functions and prove results about these concepts.
(1)
This paper describes a new proposed structure of the Proportional Integral Derivative (PID) controller based on modified Elman neural network for the DC-DC buck converter system which is used in battery operation of the portable devices. The Dolphin Echolocation Optimization (DEO) algorithm is considered as a perfect on-line tuning technique therefore, it was used for tuning and obtaining the parameters of the modified Elman neural-PID controller to avoid the local minimum problem during learning the proposed controller. Simulation results show that the best weight parameters of the proposed controller, which are taken from the DEO, lead to find the best action and unsaturated state that will stabilize the Buck converter system performan
... Show More
(3)
(5)
In this paper, we study the effects of a magnetic force on the flow of hybrid bio - nano fluid (Cu - Au. NPs) for a peristaltic channel through a porous medium in an asymmetric channel. Nanoparticles of gold and copper as well as the blood (the base fluid) is taken into account. By using the Adomian decomposition method to solve the governing equations, formulas for velocity, stream function, temperature, current density, and magnetic force have been obtained. The findings show that Gold nanoparticles have an elevation magnetic force compared with copper nanoparticles, based on fluid (blood) and hybrid nanofluid. Finally, the phenomenon of trapping is offered as an explanation for the physical behavior of many parameters. The ef
... Show More
(2)
Corrosion rate tests were carried out on carbon steel under concentration cells conditions of oxygen and sodium chloride. The effect of aeration in one compartment on the corrosion rate of both coupled metals was determined. In addition, the effects of time and temperatures on the corrosion rate of both coupled metals and galvanic currents between them were investigated. Corrosion potentials for the whole range of operating conditions under concentration cell conditions were also studied. The results showed that under aeration condition, the formation of concentration cell caused a considerable corrosion rate of the Carbon steel specimens coupled in different concentrations of O2 and NaCl due to the galvanic effect
... Show More
(3)
Methotrexate (MTX), a folic acid antagonist is widely used for the treatment of a variety of tumors. In the present study, the possible protective effect of aqueous green tea extract (AGTE) in methotrexate-induced haematotoxicity was investigated.Four main groups of white Albino rats were used: control group, (MTX) group, following a single dose of MTX (20 mg/kg, i.p.) saline was administered for 5 days. (AGTE) group, was treated with 1.25% concentration of AGTE only for 12 days and the (MTX+AGTE) group, in thism group rats received different concentrations of AGTE (0.625, 1.25 and 2.5%), as their sole source of drinking water, 7days before and 5 days after MTX treatment. MTX induced significant decreases in RBC, Hb, Hct, WBC and pl
... Show More
In this paper the reinforced materials manufactured from steel continues fibers are used in Aluminum matrix to build a composite material. Most of researches concentrated on reinforced materials and its position in the matrix according to its size and distribution, and their effects on the magnitude of different kinds of the stresses, so this paper presents and concentrate on the geometrical shape of reinforced material and its effects on the internal stresses and strains on the composite strength using FEM as a method for analysis after loaded by certain force showing the deference magnitudes of stresses according to the different geometrical shapes of reinforced materials.