One of the most important features of the Amazon Web Services (AWS) cloud is that the program can be run and accessed from any location. You can access and monitor the result of the program from any location, saving many images and allowing for faster computation. This work proposes a face detection classification model based on AWS cloud aiming to classify the faces into two classes: a non-permission class, and a permission class, by training the real data set collected from our cameras. The proposed Convolutional Neural Network (CNN) cloud-based system was used to share computational resources for Artificial Neural Networks (ANN) to reduce redundant computation. The test system uses Internet of Things (IoT) services through our cameras system to capture the images and upload them to the Amazon Simple Storage Service (AWS S3) cloud. Then two detectors were running, Haar cascade and multitask cascaded convolutional neural networks (MTCNN), at the Amazon Elastic Compute (AWS EC2) cloud, after that the output results of these two detectors are compared using accuracy and execution time. Then the classified non-permission images are uploaded to the AWS S3 cloud. The validation accuracy of the offline augmentation face detection classification model reached 98.81%, and the loss and mean square error were decreased to 0.0176 and 0.0064, respectively. The execution time of all AWS cloud systems for one image when using Haar cascade and MTCNN detectors reached three and seven seconds, respectively.

Image classification is the process of finding common features in images from various classes and applying them to categorize and label them. The main problem of the image classification process is the abundance of images, the high complexity of the data, and the shortage of labeled data, presenting the key obstacles in image classification. The cornerstone of image classification is evaluating the convolutional features retrieved from deep learning models and training them with machine learning classifiers. This study proposes a new approach of hybrid learning by combining deep learning with machine learning for image classification based on convolutional feature extraction using the VGG-16 deep learning model and seven classifiers. A hybrid supervised learning system that takes advantage of rich intermediate features extracted from deep learning compared to traditional feature extraction to boost classification accuracy and parameters is suggested. They provide the same set of characteristics to discover and verify which classifier yields the best classification with our new proposed approach of hybrid learning. To achieve this, the performance of classifiers was assessed depending on a genuine dataset that was taken by our camera system. The simulation results show that the support vector machine (SVM) has a mean square error of 0.011, a total accuracy ratio of 98.80, and an F1 score of 0.99. Moreover, the results show that the LR classifier has a mean square error of 0.035 and a total ratio of 96.42, and an F1 score of 0.96 comes in the second place. The ANN classifier has a mean square error of 0.047 and a total ratio of 95.23, and an F1 score of 0.94 comes in the third place. Furthermore, RF, WKNN, DT, and NB with a mean square error and an F1 score advance to the next stage with accuracy ratios of 91.66, 90.47, 79.76, and 75, respectively. As a result, the main contribution is the enhancement of the classification performance parameters with images of varying brightness and clarity using the proposed hybrid learning approach.

During COVID-19, wearing a mask was globally mandated in various workplaces, departments, and offices. New deep learning convolutional neural network (CNN) based classifications were proposed to increase the validation accuracy of face mask detection. This work introduces a face mask model that is able to recognize whether a person is wearing mask or not. The proposed model has two stages to detect and recognize the face mask; at the first stage, the Haar cascade detector is used to detect the face, while at the second stage, the proposed CNN model is used as a classification model that is built from scratch. The experiment was applied on masked faces (MAFA) dataset with images of 160x160 pixels size and RGB color. The model achieved lower computational complexity and number of layers, while being more reliable compared with other algorithms applied to recognize face masks. The findings reveal that the model's validation accuracy reaches 97.55% to 98.43% at different learning rates and different values of features vector in the dense layer, which represents a neural network layer that is connected deeply of the CNN proposed model training. Finally, the suggested model enhances recognition performance parameters such as precision, recall, and area under the curve (AUC).

أبرزت حالات الاقتحام الأخيرة الحاجة إلى أنظمة الكشف عن اقتحام الشبكة في مقاومة هجمات الشبكة الأكثر تعقيدًا، مع نمو الاتصال بالإنترنت وحجم حركة المرور. كثيرا ما تستخدم أنظمة الكشف عن التسلل تقنيات مثل التعرف على الأنماط واستخراج البيانات لتحديد أنشطة الشبكة كالمعتاد أو الهجوم. نظام الكشف عن التسلل (IDS) هو تقنية نشطة للكشف عن التسلل تقوم تلقائيًا باكتشاف وتصنيف عمليات الاقتحام والاعتداء وانتهاكات السياسة الأمنية على مستوى الشبكة والمضيف. يشير بحثنا إلى أن طرق التعلم الآلي مثل Naiseve Bayes (NB) و K-Nearest Neighbor (KNN) و Decision Tree (DT) قد تعزز فعالية نظام الكشف عن التطفل. دقة الكشف والدقة F1-score والاستدعاء ووقت التنفيذ هي مؤشرات أداء تستخدم لقياس الفعالية. لزيادة كفاءة الكشف، والدقة، وتقليل وقت التنفيذ، تم تطبيق مناهج اختيار الميزات بما في ذلك ANOVA و Mutual Information (MI) و chi-squared (CH-2)، وكانت كل هذه الاستراتيجيات فعالة. عند استخدام ANOVA بنسبة 10٪ من الميزات، تحصل جميع المصنفين على أكبر نتيجة، بدقة 99.99٪ و DT في وقت 0.0089ms

The fundamental of a downlink massive multiple-input multiple-output (MIMO) energy- issue efficiency strategy is known as minimum mean squared error (MMSE) implementation degrades the performance of a downlink massive MIMO energy-efficiency scheme, so some improvements are adding for this precoding scheme to improve its workthat is called our proposal solution as a proposed improved MMSE precoder (PIMP). The energy efficiency (EE) study has also taken into mind drastically lowering radiated power while maintaining high throughput and minimizing interference issues. We further find the tradeoff between spectral efficiency (SE) and EE although they coincide at the beginning but later their interests become conflicting and divergent then leading EE to decrease so gradually while SE continues increasing logarithmically. The results achieved that for a single-cellular massive MU-MIMO downlink model, our PIMP scheme is the appropriate scenario to achieve higher precoding performance system. Furthermore, both maximum ratio transmission (MRT) and PIMP are suitable for performance improvement in massive MIMO results of EE and SE. So, the main contribution comes with this work that highest EE and SE are belong to use a PIMP which performs better appreciably than MRT at bigger ratio of number of antennas to the number of the users.

Dust is a common cause of health risks and also a cause of climate change, one of the most threatening problems to humans. In the recent decade, climate change in Iraq, typified by increased droughts and deserts, has generated numerous environmental issues. This study forecasts dust in five central Iraqi districts using machine learning and five regression algorithm supervised learning system framework. It was assessed using an Iraqi meteorological organization and seismology (IMOS) dataset. Simulation results show that the gradient boosting regressor (GBR) has a mean square error of 8.345 and a total accuracy ratio of 91.65%. Moreover, the results show that the decision tree (DT), where the mean square error is 8.965, comes in second place with a gross ratio of 91%. Furthermore, Bayesian ridge (BR), linear regressor (LR), and stochastic gradient descent (SGD), with mean square error and with accuracy ratios of 84.365%, 84.363%, and 79%. As a result, the performance precision of these regression models yields. The interaction framework was designed to be a straightforward tool for working with this paradigm. This model is a valuable tool for establishing strategies to counter the swiftness of climate change in the area under study.