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

Estimating an individual's age from a photograph of their face is critical in many applications, including intelligence and defense, border security and human-machine interaction, as well as soft biometric recognition. There has been recent progress in this discipline that focuses on the idea of deep learning. These solutions need the creation and training of deep neural networks for the sole purpose of resolving this issue. In addition, pre-trained deep neural networks are utilized in the research process for the purpose of facial recognition and fine-tuning for accurate outcomes. The purpose of this study was to offer a method for estimating human ages from the frontal view of the face in a manner that is as accurate as possible and takes

In this study, a traumatic spinal cord injury (TSCI) classification system is proposed using a convolutional neural network (CNN) technique with automatically learned features from electromyography (EMG) signals for a non-human primate (NHP) model. A comparison between the proposed classification system and a classical classification method (k-nearest neighbors, kNN) is also presented. Developing such an NHP model with a suitable assessment tool (i.e., classifier) is a crucial step in detecting the effect of TSCI using EMG, which is expected to be essential in the evaluation of the efficacy of new TSCI treatments. Intramuscular EMG data were collected from an agonist/antagonist tail muscle pair for the pre- and post-spinal cord lesi

The uptake of Cd(II) ions from simulated wastewater onto olive pips was modeled using artificial neural network (ANN) which consisted of three layers. Based on 112 batch experiments, the effect of contact time (10-240 min), initial pH (2-6), initial concentration (25-250 mg/l), biosorbent dosage (0.05-2 g/100 ml), agitation speed (0-250 rpm) and temperature (20-60ºC) were studied. The maximum uptake (=92 %) of Cd(II) was achieved at optimum parameters of 60 min, 6, 50 mg/l, 1 g/100 ml, 250 rpm and 25ºC respectively.

Tangent sigmoid and linear transfer functions of ANN for hidden and output layers respectively with 7 neurons were sufficient to present good predictions for cadmium removal efficiency with coefficient of correlatio

Survival analysis is widely applied in data describing for the life time of item until the occurrence of an event of interest such as death or another event of understudy . The purpose of this paper is to use the dynamic approach in the deep learning neural network method, where in this method a dynamic neural network that suits the nature of discrete survival data and time varying effect. This neural network is based on the Levenberg-Marquardt (L-M) algorithm in training, and the method is called Proposed Dynamic Artificial Neural Network (PDANN). Then a comparison was made with another method that depends entirely on the Bayes methodology is called Maximum A Posterior (MAP) method. This method was carried out using numerical algorithms re

In this paper, an algorithm is suggested to train a single layer feedforward neural network to function as a heteroassociative memory. This algorithm enhances the ability of the memory to recall the stored patterns when partially described noisy inputs patterns are presented. The algorithm relies on adapting the standard delta rule by introducing new terms, first order term and second order term to it. Results show that the heteroassociative neural network trained with this algorithm perfectly recalls the desired stored pattern when 1.6% and 3.2% special partially described noisy inputs patterns are presented.

The present work aims to improve the flux of forward osmosis with the use of Thin Film Composite membrane by reducing the effect of polarization on draw solution (brine solution) side.This study was conducted in two parts. The first is under the effect of polarization in which the flux and the water permeability coefficient (A) were calculated. In the second part of the study the experiments were repeated using a circulating pump at various speeds to make turbulence and reduce the effect of polarization on the brine solution side.
A model capable of predicting water permeability coefficient has been derived, and this is given by the following equations:
Z=Z₀ +C.R.T/9.8(d²/D²+1) [Exp. [-9.8(d

Abstract

This research aim to overcome the problem of dimensionality by using the methods of non-linear regression, which reduces the root of the average square error (RMSE), and is called the method of projection pursuit regression (PPR), which is one of the methods for reducing dimensions that work to overcome the problem of dimensionality (curse of dimensionality), The (PPR) method is a statistical technique that deals with finding the most important projections in multi-dimensional data , and With each finding projection , the data is reduced by linear compounds overall the projection. The process repeated to produce good projections until the best projections are obtained. The main idea of the PPR is to model

Finger vein recognition and user identification is a relatively recent biometric recognition technology with a broad variety of applications, and biometric authentication is extensively employed in the information age. As one of the most essential authentication technologies available today, finger vein recognition captures our attention owing to its high level of security, dependability, and track record of performance. Embedded convolutional neural networks are based on the early or intermediate fusing of input. In early fusion, pictures are categorized according to their location in the input space. In this study, we employ a highly optimized network and late fusion rather than early fusion to create a Fusion convolutional neural network