Deep learning techniques are used across a wide range of fields for several applications. In recent years, deep learning-based object detection from aerial or terrestrial photos has gained popularity as a study topic. The goal of object detection in computer vision is to anticipate the presence of one or more objects, along with their classes and bounding boxes. The YOLO (You Only Look Once) modern object detector can detect things in real-time with accuracy and speed. A neural network from the YOLO family of computer vision models makes one-time predictions about the locations of bounding rectangles andclassification probabilities for an image. In layman's terms, it is a technique for instantly identifying and rec

نتيجة للتطورات الأخيرة في أبحاث الطرق السريعة بالإضافة إلى زيادة استخدام المركبات، كان هناك اهتمام كبير بنظام النقل الذكي الأكثر حداثة وفعالية ودقة (ITS) في مجال رؤية الكمبيوتر أو معالجة الصور الرقمية، يلعب تحديد كائنات معينة في صورة دورًا مهمًا في إنشاء صورة شاملة. هناك تحدٍ مرتبط بالتعرف على لوحة ترخيص السيارة (VLPR) بسبب الاختلاف في وجهة النظر، والتنسيقات المتعددة، وظروف الإضاءة غير الموحدة في وقت الحصول

Optical Mark Recognition (OMR) is an important technology for applications that require speedy, high-accuracy processing of a huge volume of hand-filled forms. The aim of this technology is to reduce manual work, human effort, high accuracy in assessment, and minimize time for evaluation answer sheets. This paper proposed OMR by using Modify Bidirectional Associative Memory (MBAM), MBAM has two phases (learning and analysis phases), it will learn on the answer sheets that contain the correct answers by giving its own code that represents the number of correct answers, then detection marks from answer sheets by using analysis phase. This proposal will be able to detect no selection or select more than one choice, in addition, using M

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.

The Back-Propagation (BP) is the best known and widely used learning algorithm in training multiple neural network. A vast variety of improvements to BP algorithm have been proposed since ninety’s. in this paper, the effects of changing the number of hidden neurons and activation equation are investigated. According to the simulation results, the convergence speed have been improved and become much faster by the previous two modifications on the BP algorithm.

BP algorithm is the most widely used supervised training algorithms for multi-layered feedforward neural net works. However, BP takes long time to converge and quite sensitive to the initial weights of a network. In this paper, a modified cuckoo search algorithm is used to get the optimal set of initial weights that will be used by BP algorithm. And changing the value of BP learning rate to improve the error convergence. The performance of the proposed hybrid algorithm is compared with the stan dard BP using simple data sets. The simulation result show that the proposed algorithm has improved the BP training in terms of quick convergence of the solution depending on the slope of the error graph.

This research suggests a robust and systematic way for Arabic Sentiment Analysis using a vast dataset of 66,666 text reviews. One of the main advantages of this study is that the dataset was perfectly balanced (33,333 positive samples and 33,333 negative samples). In machine learning, this 50/50 split is important because it eliminates class bias and enables the predictive model to treat both sentiment classes equally. As shown in the values of the metrics — overall accuracy, weighted precision, weighted recall, and F1 score — there is great similarity among them, indicating a stable and reliable assessment of the model's real potential throughout the Arabic dataset. Based on data profile, the average word count per review is 42.3

Arabic language processing with artificial intelligence has evolved significantly in the past decades, from traditional rule- and dictionary-based techniques, through statistical models to modern deep and transformer models. This review intends to present an overview of the most well-known Arabic models as well as datasets used for its training, and the main practical applications such as sentiment analysis, machine translation, speech recognition, and smart assistant. AI-based Arabic NLP has had good progress in the previous decades, from rule and dictionary-based approaches to statistical methods and deep transformative learning models nowadays. In addition to it, the most popular state-of-the-art models that are fine-tuned for the Arabi

Face recognition and identity verification are now critical components of current security and verification technology. The main objective of this review is to identify the most important deep learning techniques that have contributed to the improvement in the accuracy and reliability of facial recognition systems, as well as highlighting existing problems and potential future research areas. An extensive literature review was conducted with the assistance of leading scientific databases such as IEEE Xplore, ScienceDirect, and SpringerLink and covered studies from the period 2015 to 2024. The studies of interest were related to the application of deep neural networks, i.e., CNN, Siamese, and Transformer-based models, in face recogni

Abstract: Password authentication is one of the mechanisms that are widely used to authenticate an authorized user. In this research proposed password authentication for both graphical and textual password by using new technique is Modify Multi-connect architecture (MMCA) algorithm for more efficient in speed and accuracy. Among 100 test the accuracy result is 100% for graphical and textual password to authenticate a user, and the process time to authenticate each user is 0.5 and 1 seconds for textual password and graphical password respectively.

This project presents an enhanced Iraqi vehicle plate identification system, incorporating digital processing technologies and the XOR Auto-Associative Memory advanced associative memory algorithm, towards a fast and efficient performance under diverse conditions of imagery. The system consists of three major stages: identification of the panel area, or localization, using edge transformations and morphological operations; symbol segmentation, or segmentation, based on horizontal and vertical projections for the exact extraction of numbers and letters; and finally, recognition use of XOR operations and a binary distance criterion known as Hamming Distance. The model was tested on 420 images of panels in different scenarios of lighting