In this paper we study the effect of the number of training samples for  Artificial neural networks ( ANN ) which is necessary for training process of feed forward neural network  .Also we design 5 Ann's and train 41 Ann's which illustrate how good the training samples that represent the actual function for Ann's.

The aim of this paper is to design artificial neural network as an alternative accurate tool to estimate concentration of Cadmium in contaminated soils for any depth and time. First, fifty soil samples were harvested from a phytoremediated contaminated site located in Qanat Aljaeesh in Baghdad city in Iraq. Second, a series of measurements were performed on the soil samples. The inputs are the soil depth, the time, and the soil parameters but the output is the concentration of Cu in the soil for depth x and time t. Third, design an ANN and its performance was evaluated using a test data set and then applied to estimate the concentration of Cadmium. The performance of the ANN technique was compared with the traditional laboratory inspecting

Iron is one of the abundant elements on earth that is an essential element for humans and may be a troublesome element in water supplies.  In this research an AAN model was developed to predict iron concentrations in the location of Al- Wahda water treatment plant in Baghdad city by water quality assessment of iron concentrations at seven WTPs up stream Tigris River. SPSS software was used to build the ANN model. The input data were iron concentrations in the raw water for the period 2004-2011. The results indicated the best model predicted Iron concentrations at Al-Wahda WTP with a coefficient of determination 0.9142. The model used one hidden layer with two nodes and the testing error was 0.834. The ANN model coul

    Artificial Neural Network (ANN) is widely used in many complex applications. Artificial neural network is a statistical intelligent technique resembling the characteristic of the human neural network.  The prediction of time series from the important topics in statistical sciences to assist administrations in the planning and make the accurate decisions, so the aim of this study is to analysis the monthly hypertension in Kalar for the period (January 2011- June 2018) by applying an autoregressive –integrated- moving average model  and artificial neural networks and choose the best and most efficient model for patients with hypertension in Kalar through the comparison between neural networks and Box- Je

In the literature, several correlations have been proposed for bubble size prediction in bubble columns. However these correlations fail to predict bubble diameter over a wide range of conditions. Based on a data bank of around 230 measurements collected from the open literature, a correlation for bubble sizes in the homogenous region in bubble columns was derived using Artificial Neural Network (ANN) modeling. The bubble diameter was found to be a function of six parameters: gas velocity, column diameter, diameter of orifice, liquid density, liquid viscosity and liquid surface tension. Statistical analysis showed that the proposed correlation has an Average Absolute Relative Error (AARE) of 7.3 % and correlation coefficient of 92.2%. A

A Novel artificial neural network (ANN) model was constructed for calibration of a multivariate model for simultaneously quantitative analysis of the quaternary mixture composed of carbamazepine, carvedilol, diazepam, and furosemide. An eighty-four mixing formula where prepared and analyzed spectrophotometrically. Each analyte was formulated in six samples at different concentrations thus twenty four samples for the four analytes were tested. A neural network of 10 hidden neurons was capable to fit data 100%. The suggested model can be applied for the quantitative chemical analysis for the proposed quaternary mixture.

This study uses an Artificial Neural Network (ANN) to examine the constitutive relationships of the Glass Fiber Reinforced Polymer (GFRP) residual tensile strength at elevated temperatures. The objective is to develop an effective model and establish fire performance criteria for concrete structures in fire scenarios. Multilayer networks that employ reactive error distribution approaches can determine the residual tensile strength of GFRP using six input parameters, in contrast to previous mathematical models that utilized one or two inputs while disregarding the others. Multilayered networks employing reactive error distribution technology assign weights to each variable influencing the residual tensile strength of GFRP. Temperatur

In this paper, a handwritten digit classification system is proposed based on the Discrete Wavelet Transform and Spike Neural Network. The system consists of three stages. The first stage is for preprocessing the data and the second stage is for feature extraction, which is based on Discrete Wavelet Transform (DWT). The third stage is for classification and is based on a Spiking Neural Network (SNN). To evaluate the system, two standard databases are used: the MADBase database and the MNIST database. The proposed system achieved a high classification accuracy rate with 99.1% for the MADBase database and 99.9% for the MNIST database

  Computer software is frequently used for medical decision support systems in different areas. Magnetic Resonance Images (MRI) are widely used images for brain classification issue. This paper presents an improved method for brain classification of MRI images. The proposed method contains three phases, which are, feature extraction, dimensionality reduction, and an improved classification technique. In the first phase, the features of MRI images are obtained by discrete wavelet transform (DWT). In the second phase, the features of MRI images have been reduced, using principal component analysis (PCA). In the last (third) stage, an improved classifier is developed. In the proposed classifier, Dragonfly algorithm is used instead

Using the Neural network as a type of associative memory will be introduced in this paper through the problem of mobile position estimation where mobile estimate its location depending on the signal strength reach to it from several around base stations where the neural network can be implemented inside the mobile. Traditional methods of time of arrival (TOA) and received signal strength (RSS) are used and compared with two analytical methods, optimal positioning method and average positioning method. The data that are used for training are ideal since they can be obtained based on geometry of CDMA cell topology. The test of the two methods TOA and RSS take many cases through a nonlinear path that MS can move through that region. The result