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

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

Software-defined networking (SDN) is an innovative network paradigm, offering substantial control of network operation through a network’s architecture. SDN is an ideal platform for implementing projects involving distributed applications, security solutions, and decentralized network administration in a multitenant data center environment due to its programmability. As its usage rapidly expands, network security threats are becoming more frequent, leading SDN security to be of significant concern. Machine-learning (ML) techniques for intrusion detection of DDoS attacks in SDN networks utilize standard datasets and fail to cover all classification aspects, resulting in under-coverage of attack diversity. This paper proposes a hybr

order to increase the level of security, as this system encrypts the secret image before sending it through the internet to the recipient (by the Blowfish method). As The Blowfish method is known for its efficient security; nevertheless, the encrypting time is long. In this research we try to apply the smoothing filter on the secret image which decreases its size and consequently the encrypting and decrypting time are decreased. The secret image is hidden after encrypting it into another image called the cover image, by the use of one of these two methods" Two-LSB" or" Hiding most bits in blue pixels". Eventually we compare the results of the two methods to determine which one is better to be used according to the PSNR measurs

Bootstrap is one of an important re-sampling technique which has given the attention of  researches recently. The presence of outliers in the original data set may cause serious problem to the classical bootstrap when the percentage of outliers are higher than the original one. Many methods are proposed to overcome this problem such  Dynamic Robust Bootstrap for LTS (DRBLTS) and Weighted Bootstrap with Probability (WBP). This paper try to show the accuracy of parameters estimation by comparison the results of both methods. The bias , MSE and RMSE are considered. The criterion of the accuracy is based on the RMSE value since the method that provide us RMSE value smaller than other is con

Several correlations have been proposed for bubble point pressure, however, the correlations could not predict bubble point pressure accurately over the wide range of operating conditions. This study presents Artificial Neural Network (ANN) model for predicting the bubble point pressure especially for oil fields in Iraq. The most affecting parameters were used as the input layer to the network. Those were reservoir temperature, oil gravity, solution gas-oil ratio and gas relative density. The model was developed using 104 real data points collected from Iraqi reservoirs. The data was divided into two groups: the first was used to train the ANN model, and the second was used to test the model to evaluate their accuracy and trend stability

Its well known that understanding human facial expressions is a key component in understanding emotions and finds broad applications in the field of human-computer interaction (HCI), has been a long-standing issue. In this paper, we shed light on the utilisation of a deep convolutional neural network (DCNN) for facial emotion recognition from videos using the TensorFlow machine-learning library from Google. This work was applied to ten emotions from the Amsterdam Dynamic Facial Expression Set-Bath Intensity Variations (ADFES-BIV) dataset and tested using two datasets.

Each phenomenon contains several variables. Studying these variables, we find mathematical formula to get the joint distribution and the copula that are a useful and good tool to find the amount of correlation, where the survival function was used to measure the relationship of age with the level of cretonne in the remaining blood of the person. The Spss program was also used to extract the influencing variables from a group of variables using factor analysis and then using the Clayton copula function that is used to find the shared binary distributions using multivariate distributions, where the bivariate distribution was calculated, and then the survival function value was calculated for a sample size (50) drawn from Yarmouk Ho