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.

Traditionally, path selection within routing is formulated as a shortest path optimization problem. The objective function for optimization could be any one variety of parameters such as number of hops, delay, cost...etc. The problem of least cost delay constraint routing is studied in this paper since delay constraint is very common requirement of many multimedia applications and cost minimization captures the need to
distribute the network. So an iterative algorithm is proposed in this paper to solve this problem. It is appeared from the results of applying this algorithm that it gave the optimal path (optimal solution) from among multiple feasible paths (feasible solutions).

The aim of this paper is to design suitable neural network (ANN) as an alternative accurate tool to evaluate concentration of Copper in contaminated soils. First, sixteen (4x4) soil samples were harvested from a phytoremediated contaminated site located in Baghdad city in Iraq. Second, a series of measurements were performed on the soil samples. Third, design an ANN and its performance was evaluated using a test data set and then applied to estimate the concentration of Copper. The performance of the ANN technique was compared with the traditional laboratory inspecting using the training and test data sets. The results of this study show that the ANN technique trained on experimental measurements can be successfully applied to the rapid est

In this paper we present a method to analyze five types with fifteen wavelet families for eighteen different EMG signals. A comparison study is also given to show performance of various families after modifying the results with back propagation Neural Network. This is actually will help the researchers with the first step of EMG analysis. Huge sets of results (more than 100 sets) are proposed and then classified to be discussed and reach the final.

The speech recognition system has been widely used by many researchers using different
methods to fulfill a fast and accurate system. Speech signal recognition is a typical
classification problem, which generally includes two main parts: feature extraction and
classification. In this paper, a new approach to achieve speech recognition task is proposed by
using transformation techniques for feature extraction methods; namely, slantlet transform
(SLT), discrete wavelet transforms (DWT) type Daubechies Db1 and Db4. Furthermore, a
modified artificial neural network (ANN) with dynamic time warping (DTW) algorithm is
developed to train a speech recognition system to be used for classification and recognition
purposes. T

Specialized hardware implementations of Artificial Neural Networks (ANNs) can offer faster execution than general-purpose microprocessors by taking advantage of reusable modules, parallel processes and specialized computational components. Modern high-density Field Programmable Gate Arrays (FPGAs) offer the required flexibility and fast design-to-implementation time with the possibility of exploiting highly parallel computations like those required by ANNs in hardware. The bounded width of the data in FPGA ANNs will add an additional error to the result of the output. This paper derives the equations of the additional error value that generate from bounded width of the data and proposed a method to reduce the effect of the error to give

In recent years, with the rapid development of the current classification system in digital content identification, automatic classification of images has become the most challenging task in the field of computer vision. As can be seen, vision is quite challenging for a system to automatically understand and analyze images, as compared to the vision of humans. Some research papers have been done to address the issue in the low-level current classification system, but the output was restricted only to basic image features. However, similarly, the approaches fail to accurately classify images. For the results expected in this field, such as computer vision, this study proposes a deep learning approach that utilizes a deep learning algorithm.