The aim of this paper is to approximate multidimensional functions by using the type of Feedforward neural networks (FFNNs) which is called Greedy radial basis function neural networks (GRBFNNs). Also, we introduce a modification to the greedy algorithm which is used to train the greedy radial basis function neural networks. An error bound are introduced in Sobolev space. Finally, a comparison was made between the three algorithms (modified greedy algorithm, Backpropagation algorithm and the result is published in [16]).
In this study, the first kind Bessel function was used to solve Kepler equation for an elliptical orbiting satellite. It is a classical method that gives a direct solution for calculation of the eccentric anomaly. It was solved for one period from (M=0-360)° with an eccentricity of (e=0-1) and the number of terms from (N=1-10). Also, the error in the representation of the first kind Bessel function was calculated. The results indicated that for eccentricity of (0.1-0.4) and (N = 1-10), the values of eccentric anomaly gave a good result as compared with the exact solution. Besides, the obtained eccentric anomaly values were unaffected by increasing the number of terms (N = 6-10) for eccentricities (0.8 and 0.9). The Bessel
... Show MoreThe objective of this research is employ the special cases of function trapezoid in the composition of fuzzy sets to make decision within the framework of the theory of games traditional to determine the best strategy for the mobile phone networks in the province of Baghdad and Basra, has been the adoption of different periods of the functions belonging to see the change happening in the matrix matches and the impact that the strategies and decision-making available to each player and the impact on societ
... Show MoreThe main object of this article is to study and introduce a subclass of meromorphic univalent functions with fixed second positive defined by q-differed operator. Coefficient bounds, distortion and Growth theorems, and various are the obtained results.
Pesticide poisoning is a serious global public health issue and is responsible for a sizable number of annual fatalities. This study was designed to examine the potentially harmful effects of adult rats being exposed to imidacloprid (IMD) as a nanoparticle by determining the chronic effect of inhalation of (5,10 and 20) mg/kg/b.w. of nano-imidacloprid for a duration of 60 days. The most important biochemical parameters of the serum liver function parameters were aspartate aminotransferase (AST), alanine aminotransferase (ALT), and alkaline phosphatase ALP, kidney function [blood urea, creatinine, and urea], and oxidative stress parameters (MDA, GSH, and CAT) in all treated groups when
In this paper, a new class of non-convex functions called semi strongly (
The objective of this study is to estimate the effect of the hydro-ethanolic catechin extract toward blood glucose, lipid profile and liver functions in alloxan diabetic mice. 50 healthy mice (25-30 g) were divided into five groups of ten animals for each. Group A received normal saline as normal control group. To induce diabetes, alloxan (150 mg/kg), intraperitoneal (i.p.) single dose was injected to groups B, C, D and E. Group B represents diabetic control group. Groups C, D and E received ethanolic catechin extract (30 mg/kg and 40 mg/kg) for different periods of 1, 2 and 3 weeks as treated groups. Blood glucose, serum lipids [Total Cholesterol (TC), Triglycerides (TGs) and High Density Lipoproteins (HDL)], asparagine transaminase (AST),
... Show MoreAn adaptive nonlinear neural controller to reduce the nonlinear flutter in 2-D wing is proposed in the paper. The nonlinearities in the system come from the quasi steady aerodynamic model and torsional spring in pitch direction. Time domain simulations are used to examine the dynamic aero elastic instabilities of the system (e.g. the onset of flutter and limit cycle oscillation, LCO). The structure of the controller consists of two models :the modified Elman neural network (MENN) and the feed forward multi-layer Perceptron (MLP). The MENN model is trained with off-line and on-line stages to guarantee that the outputs of the model accurately represent the plunge and pitch motion of the wing and this neural model acts as the identifier. Th
... Show MoreThe research dealt with the effectiveness of prediction and foresight in design as a phenomenon that plays a role in the recipient's engagement with the design, as it shows the interaction between the recipient and the interior space. The designer is keen to diversify his formal vocabulary in a way that secures visual values that call for aesthetic integration, as well as securing mental and kinetic behavioral understanding in the interior space.
As the designer deals with a three-dimensional space that carries many visual scenes, the designer should not leave anything from it without standing on it with study and investigation, and puts the user as a basic goal as he provides interpretive data through prediction and foresight that le
Some experiments need to know the extent of their usefulness to continue providing them or not. This is done through the fuzzy regression discontinuous model, where the Epanechnikov Kernel and Triangular Kernel were used to estimate the model by generating data from the Monte Carlo experiment and comparing the results obtained. It was found that the. Epanechnikov Kernel has a least mean squared error.