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%.
DeepFake is a concern for celebrities and everyone because it is simple to create. DeepFake images, especially high-quality ones, are difficult to detect using people, local descriptors, and current approaches. On the other hand, video manipulation detection is more accessible than an image, which many state-of-the-art systems offer. Moreover, the detection of video manipulation depends entirely on its detection through images. Many worked on DeepFake detection in images, but they had complex mathematical calculations in preprocessing steps, and many limitations, including that the face must be in front, the eyes have to be open, and the mouth should be open with the appearance of teeth, etc. Also, the accuracy of their counterfeit detectio
... Show MoreIn the present article, we implement the new iterative method proposed by Daftardar-Gejji and Jafari (NIM) [V. Daftardar-Gejji, H. Jafari, An iterative method for solving nonlinear functional equations, J. Math. Anal. Appl. 316 (2006) 753-763] to solve two problems; the first one is the problem of spread of a non-fatal disease in a population which is assumed to have constant size over the period of the epidemic, and the other one is the problem of the prey and predator. The results demonstrate that the method has many merits such as being derivative-free, overcome the difficulty arising in calculating Adomian polynomials to handle the nonlinear terms in Adomian Decomposition Method (ADM), does not require to calculate Lagrange multiplier a
... Show MoreA modification to cascaded single-stage distributed amplifier (CSSDA) design by using active inductor is proposed. This modification is shown to render the amplifier suitable for high gain operation in small on-chip area. Microwave office program simulation of the Novel design approach shows that it has performance compatible with the conventional distributed amplifiers but with smaller area. The CSSDA is suitable for optical and satellite communication systems.
Sentiment analysis is one of the major fields in natural language processing whose main task is to extract sentiments, opinions, attitudes, and emotions from a subjective text. And for its importance in decision making and in people's trust with reviews on web sites, there are many academic researches to address sentiment analysis problems. Deep Learning (DL) is a powerful Machine Learning (ML) technique that has emerged with its ability of feature representation and differentiating data, leading to state-of-the-art prediction results. In recent years, DL has been widely used in sentiment analysis, however, there is scarce in its implementation in the Arabic language field. Most of the previous researches address other l
... Show More
XML is being incorporated into the foundation of E-business data applications. This paper addresses the problem of the freeform information that stored in any organization and how XML with using this new approach will make the operation of the search very efficient and time consuming. This paper introduces new solution and methodology that has been developed to capture and manage such unstructured freeform information (multi information) depending on the use of XML schema technologies, neural network idea and object oriented relational database, in order to provide a practical solution for efficiently management multi freeform information system.
Projects suspensions are between the most insistent tasks confronted by the construction field accredited to the sector’s difficulty and its essential delay risk foundations’ interdependence. Machine learning provides a perfect group of techniques, which can attack those complex systems. The study aimed to recognize and progress a wellorganized predictive data tool to examine and learn from delay sources depend on preceding data of construction projects by using decision trees and naïve Bayesian classification algorithms. An intensive review of available data has been conducted to explore the real reasons and causes of construction project delays. The results show that the postpo
Diversity of the aspects of analyzing a specific linguistic issue is considered to be a
familiar phenomenon in learning Arabic in which – at different levels- various linguistic
aspects and phases – sometimes – are involved in a linguistic issue . In this paper , the
problematic issues during linguistic analysis are taken into an account. The Holy Quran
interpretation books include many Quranic expressions which have a lot of meaning described
by different interpreters , from them this paper has selected only one expression ( = كفاتا
receptacle ) from the verse "Have we not made the earth a receptacle " ( Al- Mursalat verse 25
) , this paper believes that this expression is sufficient display the interpret
The synthesis of nanoparticles (GNPs) from the reduction of HAuCl4 .3H2O by aluminum metal was obtained in aqueous solution with the use of Arabic gum as a stabilizing agent. The GNPs were characterized by TEM, AFM and Zeta potential spectroscopy. The reduction process was monitored over time by measuring ultraviolet spectra at a range of λ 520-525 nm. Also the color changes from yellow to ruby red, shape and size of GNP was studied by TEM. Shape was spherical and the size of particles was (12-17.5) nm. The best results were obtained at pH 6.