Image compression plays an important role in reducing the size and storage of data while increasing the speed of its transmission through the Internet significantly. Image compression is an important research topic for several decades and recently, with the great successes achieved by deep learning in many areas of image processing, especially image compression, and its use is increasing Gradually in the field of image compression. The deep learning neural network has also achieved great success in the field of processing and compressing various images of different sizes. In this paper, we present a structure for image compression based on the use of a Convolutional AutoEncoder (CAE) for deep learning, inspired by the diversity of human eyes' observation of the different colors and features of images. We propose a multi-layer hybrid system for deep learning using the unsupervised CAE architecture and using the color clustering of the K-mean algorithm to compress images and determine their size and color intensity. The system is implemented using Kodak and Challenge on Learned Image Compression (CLIC) dataset for deep learning. Experimental results show that our proposed method is superior to the traditional compression methods of the autoencoder, and the proposed work has better performance in terms of performance speed and quality measures Peak Signal To Noise Ratio (PSNR) and Structural Similarity Index (SSIM) where the results achieved better performance and high efficiency With high compression bit rates and low Mean Squared Error (MSE) rate the results recorded the highest compression ratios that ranged between (0.7117 to 0.8707) for the Kodak dataset and (0.7191 to 0.9930) for CLIC dataset. The system achieved high accuracy and quality in comparison to the error coefficient, which was recorded (0.0126 to reach 0.0003) below, and this system is onsidered the most quality and accurate compared to the methods of deep learning compared to the deep learning methods of the autoencoder
This research is devoted to study the effect of different in weight percentage of Sio2 particles and glass fibers (5, 10, 15, 20) wt. % on the wear rate epoxy resin. The results show that the value of hardness increase with the increase for the weight percentage of reinforcing particles and fibers, while the wear rate decrease with the increase the load level of the reinforcing particles and fibers . The largest value of the hardness, and the lowest value of the wear rate for epoxy reinforced with 20% of SiO2, the wear rate increase in general with increasing the applied load.
(2)
أهمية البحث اعداد تدريبات الهيت في تطوير القوة الانفجارية وفقا لمؤشر معدل النبض التي تتطلب تكيف الأداء البدني للوصول إلى كفاءة عالية لدى لاعبي الريشة الطائرة. يهدف البحث اعداد تدريبات الهيت في تطوير القوة الانفجارية وفقا لمؤشر معدل النبض لدى لاعبي الريشة الطائرة وكانت مشكلة البحث إن تنوع لأساليب التدريبية واختلاف تأثيراتها يجعلان لاعبي الريشة الطائرة بحاجة إلى إعداد بدني يتناسب مع إمكانياتهم وقدراتهم
... Show More
Galvanic corrosion of stainless steel 316 (SS316) and carbon steel (CS) coupled in 5% wt/v sulfuric acid solution at agitation velocity was investigated. The galvanic behavior of coupled metals was also studied using zero resistance ammeter (ZRA) method. The effects of agitation velocity, temperature, and time on galvanic corrosion current and loss in weight of both metals in both free corrosion and galvanic corrosion were investigated. The trends of open circuit potential (OCP) of each metal and galvanic potential (Eg) of the couple were, also, determined. Results showed that SS316 was cathodic relative to CS in galvanic couple and its OCP was much more positive than that of CS for all investigated ranges of
... Show MoreThis study aimed to isolate and phenotype lymphocytes in untreated children patients with chronic allergic asthma. To reach such aim the study involved (25) patients from children (17 male and 9 female) whom their ages where between (3-10) years, in addition to (15) apparently healthy children (9 male and 6 female) in the same ages involved as control group. The data demonstrated that there was a significant increase in the mean percentages of T-lymphocytes (CD3+ cells) in the peripheral blood of patients (66.75±0.29)**, in comparison with control group (43.58±0.19), a significant increase in the mean percentages of T-helper lymphocytes (CD4+ cells) in the pe
... Show More
The ground state properties including the density distributions of the neutrons, protons and matter as well as the corresponding root mean square (rms) radii of proton-rich halo candidates 8B, 12N, 23Al and 27P have been studied by the single particle Bear– Hodgson (BH) wave functions with the two-body model of (core+p). It is found that the rms radii of these proton-rich nuclei are reproduced well by this model and the radial wave functions describe the long tail of the proton and matter density distributions. These results indicate that this model achieves a suitable description of the possible halo structure. The plane wave Born approximation (PWBA) has been used to compute the elastic charge form factors.
(5)
(3)
Abstract
The research Compared two methods for estimating fourparametersof the compound exponential Weibull - Poisson distribution which are the maximum likelihood method and the Downhill Simplex algorithm. Depending on two data cases, the first one assumed the original data (Non-polluting), while the second one assumeddata contamination. Simulation experimentswere conducted for different sample sizes and initial values of parameters and under different levels of contamination. Downhill Simplex algorithm was found to be the best method for in the estimation of the parameters, the probability function and the reliability function of the compound distribution in cases of natural and contaminateddata.
... Show More
The article describes a certain computation method of -arcs to construct the number of distinct -arcs in for . In this method, a new approach employed to compute the number of -arcs and the number of distinct arcs respectively. This approach is based on choosing the number of inequivalent classes } of -secant distributions that is the number of 4-secant, 3-secant, 2-secant, 1-secant and 0-secant in each process. The maximum size of -arc that has been constructed by this method is . The new method is a new tool to deal with the programming difficulties that sometimes may lead to programming problems represented by the increasing number of arcs. It is essential to reduce the established number of -arcs in each cons
... Show More
(3)
(1)
The AlAdhaim Dam is located 133 kilometers northeast of Baghdad. It is a multipurpose dam and joints the Iraqi dam system in 2000. It has a storage capacity of 1.5 billion m3. The dam has an ogee spillway with a length of 562 m, a crest level of 131.5 m.a.m.s.l. and a maximum discharge capacity of 1150 m3/s at its maximum storage height of 143 m.a.m.s.l. This research aimed to investigate the hydrodynamics performance of the spillway and the stilling basin of AlAdhiam Dam by using numerical simulation models under gated situations. It was suggested to modify the dam capacity by increasing the dam's storage capacity by installing gates on the crest of the dam spillway. The FLUENT program was used to
... Show More
(3)
(2)
Classifying an overlapping object is one of the main challenges faced by researchers who work in object detection and recognition. Most of the available algorithms that have been developed are only able to classify or recognize objects which are either individually separated from each other or a single object in a scene(s), but not overlapping kitchen utensil objects. In this project, Faster R-CNN and YOLOv5 algorithms were proposed to detect and classify an overlapping object in a kitchen area. The YOLOv5 and Faster R-CNN were applied to overlapping objects where the filter or kernel that are expected to be able to separate the overlapping object in the dedicated layer of applying models. A kitchen utensil benchmark image database and
... Show More
(33)
(25)
Maximizing the net present value (NPV) of oil field development is heavily dependent on optimizing well placement. The traditional approach entails the use of expert intuition to design well configurations and locations, followed by economic analysis and reservoir simulation to determine the most effective plan. However, this approach often proves inadequate due to the complexity and nonlinearity of reservoirs. In recent years, computational techniques have been developed to optimize well placement by defining decision variables (such as well coordinates), objective functions (such as NPV or cumulative oil production), and constraints. This paper presents a study on the use of genetic algorithms for well placement optimization, a ty
... Show More