The chest X-ray is considered a significant clinical utility for basic examination and diagnosis. The human lung area can be affected by various infections, such as bacteria and viruses, leading to pneumonia. Efficient and reliable classification method facilities the diagnosis of such infections. Deep transfer learning has been introduced for pneumonia detection from chest X-rays in different models. However, there is still a need for further improvements in the feature extraction and advanced classification stages. This paper proposes a classification method with two stages to classify different cases from the chest X-ray images based on a proposed Advanced Squirrel Search Optimization Algorithm (ASSOA). The first stage is the feature learning and extraction processes based on a Convolutional Neural Network (CNN) model named ResNet-50 with image augmentation and dropout processes. The ASSOA algorithm is then applied to the extracted features for the feature selection process. Finally, the Multi-layer Perceptron (MLP) Neural Network's connection weights are optimized by the proposed ASSOA algorithm (using the selected features) to classify input cases. A Kaggle chest X-ray images (Pneumonia) dataset consists of 5,863 X-rays is employed in the experiments. The proposed ASSOA algorithm is compared with the basic Squirrel Search (SS) optimization algorithm, Grey Wolf Optimizer (GWO), and Genetic Algorithm (GA) for feature selection to validate its efficiency. The proposed (ASSOA + MLP) is also compared with other classifiers, based on (SS + MLP), (GWO + MLP), and (GA + MLP), in performance metrics. The proposed (ASSOA + MLP) algorithm achieved a classification mean accuracy of (99.26%). The ASSOA + MLP algorithm also achieved a classification mean accuracy of (99.7%) for a chest X-ray COVID-19 dataset tested from GitHub. The results and statistical tests demonstrate the high effectiveness of the proposed method in determining the infected cases.

Recently, unmanned aerial vehicles (UAVs) communications gained significant concentration as a talented technology for future wireless communications using its remarkable advantages and broad applicability. Furthermore, UAV networks’ high complex configurations and designs encourage researchers to leverage relevant artificial intelligence (AI) techniques for better beyond fifth-generation (B5G)/sixth-generation (6G) services. This article summarizes AI-aided UAV solutions designated for forthcoming wireless networks. Besides, we deliver a comprehensive summary of machine learning (ML) approaches, including their applications and valuable contributions towards effective UAV network implementations, particularly advanced ML ones like bandits, federated learning (FL), meta-learning, etc. Finally, detailed UAV communication-related future research scopes and challenges is highlighted.

On one hand combining Unmanned Aerial Vehicles (UAVs) and Non-Orthogonal Multiple Access (NOMA) is a remarkable direction to sustain the exponentially growing traffic requirements of the forthcoming Sixth Generation (6G) networks. In this paper, we investigate effective Power Allocation (PA) and Trajectory Planning Algorithm (TPA) for UAV-aided NOMA systems to assist multiple survivors in a post-disaster scenario, where ground stations are malfunctioned. Here, the UAV maneuvers to collect data from survivors, which are grouped in multiple clusters within the disaster area, to satisfy their traffic demands. On the other hand, while the problem is formulated as Budgeted Multi-Armed Bandits (BMABs) that optimize the UAV trajectory and minimize battery consumption, challenges may arise in real-world scenarios. Herein, the UAV is the bandit player, the disaster area clusters are the bandit arms, the sum rate of each cluster is the payoff, and the UAV energy consumption is the budget. Hence, to tackle these challenges, two Upper Confidence Bound (UCB) BMAB schemes are leveraged to handle this issue, namely BUCB1 and BUCB2. Simulation results confirm the superior performance of the proposed BMAB solution against benchmark solutions for UAV-aided NOMA communication. Notably, the BMAB-NOMA solution exhibits remarkable improvements, achieving 60% enhancement in the total number of assisted survivors, 80% improvement in convergence speed, and a considerable amount of energy saving compared to UAV-OMA.

Forecasting student performance, sorting students into groups according to their strengths, and working to improve future test scores are all crucial for any institution in today's competitive world. It is important to give students ample notice before a school year begins if they are to be coached to improve their grades by focusing on a certain subject area. Examining this can helps a school significantly reduce its dropout rate. This analysis predicts how well students will do in a given course based on how they did in previous, similar courses. Discovering previously unknown relationships among vast stores of data is the goal of data mining. Insights and forecasts might be gained from these recurring structures. The term education data mining describes the assortment of data mining programs used in the educational sector. The primary focus of these tools is on analyzing the information gathered from classrooms and educators. Potential applications of this research include classification and forecasting. It looks into several machine learning methods, including Naive Bayes, ID3, C4.5, and SVM. The experimental analysis uses data collection containing UCI machinery students' grades and other outcomes. Accuracy and error rate are two metrics used to evaluate algorithms.

American scientific publishing group