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.
A mathematical method with a new algorithm with the aid of Matlab language is proposed to compute the linear equivalence (or the recursion length) of the pseudo-random key-stream periodic sequences using Fourier transform. The proposed method enables the computation of the linear equivalence to determine the degree of the complexity of any binary or real periodic sequences produced from linear or nonlinear key-stream generators. The procedure can be used with comparatively greater computational ease and efficiency. The results of this algorithm are compared with Berlekamp-Massey (BM) method and good results are obtained where the results of the Fourier transform are more accurate than those of (BM) method for computing the linear equivalenc
... Show More
(7)
In this paper, our aim is to solve analytically a nonlinear social epidemic model as an initial value problem (IVP) of ordinary differential equations. The mathematical social epidemic model under study is applied to alcohol consumption model in Spain. The economic cost of alcohol consumption in Spain is affected by the amount of alcohol consumed. This paper refers to the study of alcohol consumption using some analytical methods. Adomian decomposition and variation iteration methods for solving alcohol consumption model have used. Finally, a compression between the analytic solutions of the two used methods and the previous actual values from 1997 to 2007 years is obtained using the absolute and
... Show More
(3)
Solar energy is one of the immeasurable renewable energy in power generation for a green, clean and healthier environment. The silicon-layer solar panels absorb sun energy and converts it into electricity by off-grid inverter. Electricity is transferred either from this inverter or from transformer, consumed by consumption unit(s) available for residential or economic purposes. The artificial neural network is the foundation of artificial intelligence and solves many complex problems which are difficult by statistical methods or by humans. In view of this, the purpose of this work is to assess the performance of the Solar - Transformer - Consumption (STC) system. The system may be in complete breakdown situation due to failure of both so
... Show More
(6)
(2)
The influence of acid activation of a mixture of illite, kaolinite, and chlorite clays collected from the area of Zorbatiya (east of Iraq) on the adsorption of methyl violet 6B (MV6B) as a cationic dye was studied. The activation was carried out by using 0.25M HCl and 0.25M . Raw and acid-activated clays were analyzed by atomic force microscopy (AFM), scanning electron microscopy (SEM), and X-ray diffraction (XRD).
Batch adsorption method was used to study the adsorption of MV6B onto the raw and acid activated clays. The impacts of different factors on the adsorption process were studied, such as clay weight, agitation time, starting MV6B concentration, temperature, ionic strength, and solution pH. The adsorption process was desc
... Show More
(4)
(2)
(4)
(4)
The objective of this study is to apply Artificial Neural Network for heat transfer analysis of shell-and-tube heat exchangers widely used in power plants and refineries. Practical data was obtained by using industrial heat exchanger operating in power generation department of Dura refinery. The commonly used Back Propagation (BP) algorithm was used to train and test networks by divided the data to three samples (training, validation and testing data) to give more approach data with actual case. Inputs of the neural network include inlet water temperature, inlet air temperature and mass flow rate of air. Two outputs (exit water temperature to cooling tower and exit air temperature to second stage of air compressor) were taken in ANN.
... Show Morethis paper give a proof of known conditions for the existence of peridic conincidence points of continuius maps using lindemann theotem on transcendental numbers
In this study, Iraqi bentonite taken from Trefawi area/ Al-Anbar region province/ Iraq, was activated to enhance its rheological and filtration properties and increase its quality by decreasing the non-clay minerals (impurities), in order to be used in Iraqi oil companies instead of commercial bentonite. Bentonite was characterized by X-ray diffraction (XRD), X-ray fluorescence (XRF) and particle size distribution (PSD) before and after activation to show the effects on its mineral and chemical properties. The rheological properties of bentonite were enhanced by using different weights (0.4, 0.5, 0.6, 0.7 and 0.8 gm) of sodium carbonate (Na₂CO₃), whereas the filtration properties were enhanced by using different weights (0.5
... Show More
(4)
(5)
(2)
(1)