The field of Optical Character Recognition (OCR) is the process of converting an image of text into a machine-readable text format. The classification of Arabic manuscripts in general is part of this field. In recent years, the processing of Arabian image databases by deep learning architectures has experienced a remarkable development. However, this remains insufficient to satisfy the enormous wealth of Arabic manuscripts. In this research, a deep learning architecture is used to address the issue of classifying Arabic letters written by hand. The method based on a convolutional neural network (CNN) architecture as a self-extractor and classifier. Considering the nature of the dataset images (binary images), the contours of the alphabets are detected using the mathematical algorithm of the morphological gradient. After that, the images are passed to the CNN architecture. The available database of Arabic handwritten alphabets on Kaggle is utilized for examining the model. This database consists of 16,800 images divided into two datasets: 13,440 images for training and 3,360 for validation. As a result, the model gives a remarkable accuracy equal to 99.02%.
The research involves preparing gold nanoparticles (AuNPs) and studying the factors that influence the shape, sizes and distribution ratio of the prepared particles according to Turkevich method. These factors include (reaction temperature, initial heating, concentration of gold ions, concentration and quantity of added citrate, reaction time and order of reactant addition). Gold nanoparticles prepared were characterized by the following measurements: UV-Visible spectroscopy, X-ray diffraction and scanning electron microscopy. The average size of gold nanoparticles was formed in the range (20 -35) nm. The amount of added citrate was changed and studied. In addition, the concentration of added gold ions was changed and the calibration cur
... Show MoreThe research of three-based financial indicators to create value for shareholders, have been identified research problem in a number of the questions revolved around the extent to which it can express its based performance metrics to create value for the essence and the reality of the surveyed enterprises performance, Can the departments surveyed companies to choose the scale or the most harmonizing index and an expression of the actual performance of the company, has the goal of research is to diagnose the strengths and weaknesses in the performance of the surveyed enterprises through the use of a number of based on the concept of creating economic value and the search for the most suitable indicator to the reality of the perfor
... Show MoreDeep learning (DL) plays a significant role in several tasks, especially classification and prediction. Classification tasks can be efficiently achieved via convolutional neural networks (CNN) with a huge dataset, while recurrent neural networks (RNN) can perform prediction tasks due to their ability to remember time series data. In this paper, three models have been proposed to certify the evaluation track for classification and prediction tasks associated with four datasets (two for each task). These models are CNN and RNN, which include two models (Long Short Term Memory (LSTM)) and GRU (Gated Recurrent Unit). Each model is employed to work consequently over the two mentioned tasks to draw a road map of deep learning mod
... Show MoreFlexible molecular docking is a computational method of structure-based drug design to evaluate binding interactions between receptor and ligand and identify the ligand conformation within the receptor pocket. Currently, various molecular docking programs are extensively applied; therefore, realizing accuracy and performance of the various docking programs could have a significant value. In this comparative study, the performance and accuracy of three widely used non-commercial docking software (AutoDock Vina, 1-Click Docking, and UCSF DOCK) was evaluated through investigations of the predicted binding affinity and binding conformation of the same set of small molecules (HIV-1 protease inhibitors) and a protein target HIV-1 protease enzy
... Show MoreWith time progress importance of hiding information become more and more and all steganography applications is like computer games between hiding and extracting data, or like thieves and police men always thieve hides from police men in different ways to keep him out of prison. The sender always hides information in new way in order not to be understood by the attackers and only the authorized receiver can open the hiding message. This paper explores our proposed random method in detail, how chooses locations of pixel in randomly , how to choose a random bit to hide information in the chosen pixel, how it different from other approaches, how applying information hiding criteria on the proposed project, and attempts to test out in code, and
... Show MoreCadmium oxide (CdO) thin films were deposited using the sequencing ion layer adsorption and reaction (SILAR) method. In this study, the effect of the pH value of an aqueous solution of cadmium acetate at a concentration of 0.2 mol of the cadmium oxide film was determined. The solution source for the cadmium oxide film was cadmium ions and an aqueous ammonia solution. The CdO films were deposited on glass substrates at a temperature of 90 ℃. The cadmium oxide film thickness was determined by the weight difference method at pH values (7.2, 8.2). X-ray diffraction (XRD) and scanning electron microscopy (SEM) showed that the size of the crystals increased with the increase in the solution (pH). While the UV-visible spectra of the fil
... Show MoreThis study is pointed out to estimate the effectiveness of two solvents in the extraction and evaluating the active ingredients and their antioxidant activity as well as anti-cancer efficiency. Therefore, residues from four different Brassica vegetables viz. broccoli, Brussels sprout, cauliflower, and red cherry radish were extracted using two procedures methods: methanolic and water crude extracts. Methanol extracts showed the highest content of total phenolic (TP), total flavonoids (TF), and total tannins (TT) for broccoli and Brussels sprouts residues. Methanolic extract of broccoli and Brussels sprouts residues showed the highest DPPH· scavenging activity (IC50 = 15.39 and 18.64 µg/ml). The methanol and water ex
... Show More