An application of neural network technique was introduced in modeling the point efficiency of sieve tray, based on a
data bank of around 33l data points collected from the open literature.Two models proposed,using back-propagation
algorithm, the first model network consists: volumetric liquid flow rate (QL), F foctor for gas (FS), liquid density (pL),
gas density (pg), liquid viscosity (pL), gas viscosity (pg), hole diameter (dH), weir height (hw), pressure (P) and surface
tension between liquid phase and gas phase (o). In the second network, there are six parameters as dimensionless
group: Flowfactor (F), Reynolds number for liquid (ReL), Reynolds number for gas through hole (Reg), ratio of weir
height to hole diqmeter

       In this paper, we focus on designing feed forward neural network (FFNN) for solving Mixed Volterra – Fredholm Integral Equations (MVFIEs) of second kind in 2–dimensions. in our method, we present a multi – layers model consisting of a hidden layer which has five hidden units (neurons) and one linear output unit. Transfer function (Log – sigmoid) and training algorithm (Levenberg – Marquardt) are used as a sigmoid activation of each unit. A comparison between the results of numerical experiment and the analytic solution of some examples has been carried out in order to justify the efficiency and the accuracy of our method.

A research was conducted to determine the feasibility of using adsorption process to remove boron from aqueous solutions using batch technique. Three adsorbent materials; magnesium, aluminum and iron oxide were investigated to find their abilities for boron removal. The effects of operational parameters on boron removal efficiency for each material were determined.
The experimental results revealed that maximum boron removal was achieved at pH 9.5 for magnesium oxide and 8 for aluminum and iron oxide. The percentage of boron adsorbed onto magnesium,aluminum and iron oxide reaches up to 90, 42.5 and 41.5% respectively under appropriate conditions. Boron concentration in effluent water after adsorption via magnesium oxide comply with th

Abstract

The removal of water turbidity by using crumb rubber filter was investigated .The present study was conducted to evaluate the effect of variation of influent water turbidity (10, 25 and 50 NTU), media size (0.6and 1.14mm), filtration rate (25, 45 and 65 l/hr) and bed depth (30 and 60 cm) on the performance of mono crumb rubber filter in response to the effluent filtered water turbidity and head loss development, and compare it with that of conventional sand filter.Results revealed that 25 l/hr flow rate and 25 NTU influent turbidity were the best operating conditions.  smaller media size and higher bed depth gave the best removal efficiency while higher media size and small bed depth gave lower head

Image Fusion Using A Convolutional Neural Network

Information from 54 Magnetic Resonance Imaging (MRI) brain tumor images (27 benign and 27 malignant) were collected and subjected to multilayer perceptron artificial neural network available on the well know software of IBM SPSS 17 (Statistical Package for the Social Sciences). After many attempts, automatic architecture was decided to be adopted in this research work. Thirteen shape and statistical characteristics of images were considered. The neural network revealed an 89.1 % of correct classification for the training sample and 100 % of correct classification for the test sample. The normalized importance of the considered characteristics showed that kurtosis accounted for 100 % which means that this variable has a substantial effect

In information security, fingerprint verification is one of the most common recent approaches for verifying human identity through a distinctive pattern. The verification process works by comparing a pair of fingerprint templates and identifying the similarity/matching among them. Several research studies have utilized different techniques for the matching process such as fuzzy vault and image filtering approaches. Yet, these approaches are still suffering from the imprecise articulation of the biometrics’ interesting patterns. The emergence of deep learning architectures such as the Convolutional Neural Network (CNN) has been extensively used for image processing and object detection tasks and showed an outstanding performance compare