The logistic regression model is an important statistical model showing the relationship between the binary variable and the explanatory variables.                                                        The large number of explanations that are usually used to illustrate the response led to the emergence of the problem of linear multiplicity between the explanatory variables that make estimating the parameters of the model not accurate.    

Background: Alopecia areata(AA) is a common autoimmune disease that causes hair loss without scarring. It occurs as a result of T-helper 1 (Th1) and Th17 cells attacking the anagen hair follicles. Genetic factors play a role in the occurrence of infection, which stimulates the production of pro and anti-inflammatory interleukins. Polymorphisms of IL-37 play a role in autoimmune diseases. However, IL37 single nucleotide polymorphisms(SNP) have not been identified in patients with AA. Therefore, this study aimed to reveal the IL37 gene SNP and its relationship to AA. Methods: Genotyping of IL-37 gene single nucleotide polymorphisms SNPs were detected using sequence-specific primer-polymerase chain reaction (SSP-PCR) method was done following

In order to obtain a mixed model with high significance and accurate alertness, it is necessary to search for the method that performs the task of selecting the most important variables to be included in the model, especially when the data under study suffers from the problem of multicollinearity as well as the problem of high dimensions. The research aims to compare some methods of choosing the explanatory variables and the estimation of the parameters of the regression model, which are Bayesian Ridge Regression (unbiased) and the adaptive Lasso regression model, using simulation. MSE was used to compare the methods.

Modern machine-learning applications require GPUs, and modern platforms can leverage numerous GPUs on one or more machines to increase performance. Contemporary deep-learning models are too huge for CPU or GPU training. Training these models with many GPUs without performance degradation is necessary to train them rapidly and maximize GPU consumption. Thus, training deep convolutional neural networks (DCNN) with multiple GPUs has become necessary for improving training. Therefore, we presented a parallel design and development of an efficient model for enhancing face mask CNN performance and improving resource efficiency. This DCNN model is a parallel training system over multiple GPUs, a multi-core CPU, and a multi-process GPU platform wit

This work presents a novel technique for the detection of oil aging in electrical transformers using a single mode optical fiber sensor based on surface plasmon resonance (SPR). The aging of insulating oil is a critical issue in the maintenance and performance of electrical transformers, as it can lead to reduce insulation properties, increase risk of electrical breakdown, and decrease operational lifespan. Many parameters are calculated in this study in order to examine the efficiency of this sensor like sensitivity (S), signal to noise ratio (SNR), resolution (refractive index unit) and figure of merit (FOM) and the values are for figure of merit is 11.05, the signal to noise ratio is 20.3, the sensitivity is 6.63, and the resolution is 3

The production companies in the Iraqi industry environment facing many of the problems related to the management of inventory and control In particular in determining the quantities inventory that should be hold it. Because these companies  adoption on personal experience and some simple mathematical methods which lead to the identification of inappropriate quantities of inventory.

       This research aims to identify the economic quantity of production and purchase for the Pepsi can 330ml and essential components in Baghdad soft drinks Company in an environment dominated by cases of non ensure and High fluctuating as a result of fluctuating demand volumes and costs ass

The convergence speed is the most important feature of Back-Propagation (BP) algorithm. A lot of improvements were proposed to this algorithm since its presentation, in order to speed up the convergence phase. In this paper, a new modified BP algorithm called Speeding up Back-Propagation Learning (SUBPL) algorithm is proposed and compared to the standard BP. Different data sets were implemented and experimented to verify the improvement in SUBPL.