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

Computer systems and networks are being used in almost every aspect of our daily life, the security threats to computers and networks have increased significantly. Usually, password-based user authentication is used to authenticate the legitimate user. However, this method has many gaps such as password sharing, brute force attack, dictionary attack and guessing. Keystroke dynamics is one of the famous and inexpensive behavioral biometric technologies, which authenticate a user based on the analysis of his/her typing rhythm. In this way, intrusion becomes more difficult because the password as well as the typing speed must match with the correct keystroke patterns. This thesis considers static keystroke dynamics as a transparent layer of t

I n  this  paper ,we 'viii  consider  the density  questions  associC;lted with  the single  hidden layer feed forward  model. We proved  that a FFNN   with   one   hidden   layer  can   uniformly   approximate   any continuous  function  in C(k)(where k is a compact set in R11 ) to any required accuracy.

However, if the set of basis function is dense then the ANN's can has al most one hidden layer. But if the set of basis function  non-dense, then we  need more  hidden layers. Also, we have shown  that there exist  localized functions and that there is no t

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.

Because of cost-effective production and abundant resources of calcium, Ca-ion batteries (CIBs) are an appropriate option to alternate Li-ion batteries (LIBs). A new category of anode materials for CIBs has emerged since the successful synthesis of carbon nanotubes, which are B and N doped derivatives of it. For high-performance CIBs, BC2N nanotube (BC2NNT) has been studied as promising anode materials. In order to comprehend electrochemical attributes, cycling stability, and adsorption behavior of BC2NNT, first-principles computations have been executed. Based on nuclear magnetic resonance computations, two types of hexagonal rings (B2C2N2 (I) and BC4N (II)) were specified that are non-aromatic. Ca has adsorption on B2C2N2 and BC4N with ad

Traumatic Brain Injury (TBI) is still considered a worldwide leading cause of mortality and morbidity. Within the last decades, different modalities were used to assess severity and outcome including Glasgow Coma Scale (GCS), imaging modalities, and even genetic polymorphism, however, determining the prognosis of TBI victims is still challenging requiring the emerging of more accurate and more applicable tools to surrogate other old modalities

Oily carwash wastewater is a high organic and chemical wastewater. This paper targeted to investigate a treatment to decrease the water consumption and contaminants in car-washing stations. Electrocoagulation combined with ultrasonic energy (Sono-Electrocoagulation) was suggested so that the carwash wastewater is treated to be reused. The effect of both the voltage and time of treatment on the removal of COD, turbidity, conductivity, and total dissolved solids (TDS) were studied at constant initial pH 7 and electrode distance 2 cm. The results showed the best results of removal COD, turbidity, TDS, and reduce electrical conductivity is when the voltage was 30 V and a treatment time of 90 minutes.

  <

The shear strength of soil is one of the most important soil properties that should be identified before any foundation design. The presence of gypseous soil exacerbates foundation problems. In this research, an approach to forecasting shear strength parameters of gypseous soils based on basic soil properties was created using Artificial Neural Networks. Two models were built to forecast the cohesion and the angle of internal friction. Nine basic soil properties were used as inputs to both models for they were considered to have the most significant impact on soil shear strength, namely: depth, gypsum content, passing sieve no.200, liquid limit, plastic limit, plasticity index, water content, dry unit weight, and initial