A three-stage learning algorithm for deep multilayer perceptron (DMLP) with effective weight initialisation based on sparse auto-encoder is proposed in this paper, which aims to overcome difficulties in training deep neural networks with limited training data in high-dimensional feature space. At the first stage, unsupervised learning is adopted using sparse auto-encoder to obtain the initial weights of the feature extraction layers of the DMLP. At the second stage, error back-propagation is used to train the DMLP by fixing the weights obtained at the first stage for its feature extraction layers. At the third stage, all the weights of the DMLP obtained at the second stage are refined by error back-propagation. Network structures an

This study comprised three traverses extending parallel through the Northern, Central and Southern Mahmudiya districts, and perpendicular to the course of the Euphrates River. They were identified to collect (15) soil samples and some water samples as distributed within the land cover classes of the study area. Those classes were determined by visual interpretation and supervised classification for Landsat (TM) images obtained in August/2007. The digital classification was based on Maximum Likelihood method using six spectral bands excluding the thermal band. Chemical and physical laboratory analysis for the soil characteristics was performed to determine the types of land degradation in the study area.
The results showed that the hig

One of the diseases on a global scale that causes the main reasons of death is lung cancer. It is considered one of the most lethal diseases in life. Early detection and diagnosis are essential for lung cancer and will provide effective therapy and achieve better outcomes for patients; in recent years, algorithms of Deep Learning have demonstrated crucial promise for their use in medical imaging analysis, especially in lung cancer identification. This paper includes a comparison between a number of different Deep Learning techniques-based models using Computed Tomograph image datasets with traditional Convolution Neural Networks and SequeezeNet models using X-ray data for the automated diagnosis of lung cancer. Although the simple details p

In the years recently city planning projects have been confirmed sustainable high concentration on planning streets and pedestrian paths being the most prominent component of the urban structure in the city and these me and diverse departments link the city’s sectors and serve as a space for economic, service, and social activities. On the other hand, pedestrian traffic is an essential component of the various means of transportation within the city. Suffer cities in the Middle East and Arab cities in particular are neglecting pedestrian paths in the vital urban environment. Vehicle control mechanisms on roads, and changing the uses of pedestrian paths as result of encroaching on the sidewalks designated for pedestrians. Which leads to a

Radiation therapy plays an important role in improving breast cancer cases, in order to obtain an appropriateestimate of radiation doses number given to the patient after tumor removal; some methods of nonparametric regression werecompared. The Kernel method was used by Nadaraya-Watson estimator to find the estimation regression function forsmoothing data based on the smoothing parameter h according to the Normal scale method (NSM), Least Squared CrossValidation method (LSCV) and Golden Rate Method (GRM). These methods were compared by simulation for samples ofthree sizes, the method (NSM) proved to be the best according to average of Mean Squares Error criterion and the method(LSCV) proved to be the best according to Average of Mean Absolu

This paper introduces a non-conventional approach with multi-dimensional random sampling to solve a cocaine abuse model with statistical probability. The mean Latin hypercube finite difference (MLHFD) method is proposed for the first time via hybrid integration of the classical numerical finite difference (FD) formula with Latin hypercube sampling (LHS) technique to create a random distribution for the model parameters which are dependent on time t . The LHS technique gives advantage to MLHFD method to produce fast variation of the parameters’ values via number of multidimensional simulations (100, 1000 and 5000). The generated Latin hypercube sample which is random or non-deterministic in nature is further integrated with the FD method t

Abstract:-

            The approach maintenance and replacement one of techniques of operations research whom cares of the failure experienced by a lot of production lines which consist of a set of machines and equipment, which in turn exposed to the failure or work stoppages over the lifetime, which requires reducing the working time of these machines or equipment below what can or conuct  maintenance process once in a while or a replacement for one part of the machine or replace one of the machines in production lines. In this research is the study of the failure s that occur in some parts of one of the machines for the General Company for Vege

          The use of silicon carbide is increasing significantly in the fields of research and technology. Topological indices enable data gathering on algebraic graphs and provide a mathematical framework for analyzing the chemical structural characteristics. In this paper, well-known degree-based topological indices are used to analyze the chemical structures of silicon carbides. To evaluate the features of various chemical or non-chemical networks, a variety of topological indices are defined. In this paper, a new concept related to the degree of the graph called "bi-distance" is introduced, which is used to calculate all the additive as well as multiplicative degree-based indices for the isomer of silicon carbide, Si₂

(Use of models of game theory in determining the policies to maximize profits for the Pepsi Cola and Coca-Cola in the province of Baghdad)

Due to the importance of the theory of games especially theories of oligopoly in the study of the reality of competition among companies or governments and others the researcher linked theories of oligopoly to Econometrics to include all the policies used by companies after these theories were based on price and quantity only the researcher applied these theories to data taken from Pepsi Cola and Coca-Cola In Baghdad Steps of the solution where stated for the models proposed and solutions where found to be balance points is for the two companies according to the princi