Mosab Hamdan

In this paper, sand and dust storm characteristics and attenuation prediction methods were reviewed and summarized comprehensively. The impact of humidity on the attenuation prediction process is focally discussed while highlighting the need to incorporate it in the modeling process for accurate attenuation prediction. This review is driven by the need to develop precise prediction models that account for the impact of meteorological factors, particularly humidity, on millimeter-wave attenuation during dust storms. By addressing these shortcomings, the review seeks to improve the design of resilient communication systems to support the ultra-reliable 5G and 6G networks in challenging environments. A critique of the previous studies that highlight the contributions and drawbacks is presented in the paper. This is followed by a taxonomy of models based on their prediction concepts and the timeline of developments. Furthermore, open issues and challenges for research were presented. The review study found that existing theoretical models have failed to predict measured attenuation accurately, often deviating significantly. Most of the theoretical and analytical approaches for estimating dust storm attenuation are found to neglect the critical influence of humidity. Few empirical and machine-learning models proposed recently, have demonstrated closer alignment with measurements after considering humidity and other metrological parameters.

With the rapid growth of internet usage and the increasing number of connected devices, there is a critical need for advanced Network Traffic Classification (NTC) solutions to ensure optimal performance and robust security. Traditional NTC methods, such as port-based analysis and deep packet inspection, struggle to cope with modern network complexities, particularly dynamic port allocation and encrypted traffic. Recently, Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) have been employed to develop classification models to accomplish this task. Existing models for NTC often require significant computational resources due to their large number of parameters, leading to slower inference times and higher memory consumption. To overcome these limitations, we introduce a lightweight NTC model based on Depthwise Separable Convolutions and compare its performance against CNN, RNN, and state-of-the-art models. In terms of computational efficiency, our proposed lightweight CNN exhibits a markedly reduced computational footprint. It utilizes only 30,611 parameters and 0.627 MFLOPS, achieving inference times of 1.49 seconds on the CPU and 0.43 seconds on the GPU. This corresponds to roughly 4× fewer FLOPS than the RNN baseline and 16× fewer than the CNN baseline, while also offering an ultracompact design compared to state-of-the-art models. Such efficiency makes it exceptionally well-suited for real-time applications in resource-constrained environments. In addition, we have integrated eXplainable Artificial Intelligence techniques, specifically LIME and SHAP, to provide valuable insights into model predictions. LIME and SHAP help interpret the contribution of each feature in decision-making, enhancing the transparency and trust in the model's predictions, without compromising its lightweight nature. To support reproducibility and foster collaborative development, all associated code and resources have been made publicly available.

The increasing sophistication of cyber threats has led to the evolution of Security Operations Centers (SOCs) towards more intelligent and adaptive systems. This review explores the integration of Artificial Intelligence (AI) in SOCs, focusing on their current state, challenges, opportunities, and advantages over traditional methods. We address three key questions: (1) What are the current AI approaches in SOCs? (2) What challenges and opportunities exist with these approaches? (3) What benefits do AI models offer in SOC environments compared to traditional methods? We analyzed 38 studies using a structured methodology involving database searches, quality checks, and data extraction. Our findings show that Machine Learning (ML) techniques dominate SOC research, with a trend towards multi-approach AI methods. We classified these into ML, Natural Language Processing, multi-approach, and others, forming a detailed taxonomy of AI applications in SOCs. Challenges include data quality, model interpretability, legacy system integration, and the need for constant adaptation. Opportunities involve task automation, enhanced threat detection, real-time analysis, and adaptive learning. AI-driven SOCs show better accuracy, reduced false positives, greater scalability, and predictive capabilities than traditional approaches. This review defines Cognitive SOCs, emphasizing their ability to mimic human-like processes. We offer practical insights for SOC designers and managers on implementing AI to improve security operations. Finally, we suggest future research directions in explainable AI, human-AI collaboration, and privacy-preserving AI for SOCs.

The article reflects on the classification of brain tumors where several deep learning (DL) approaches are used. Both primary and secondary brain tumors reduce the patient’s quality of life, and therefore, any sign of the tumor should be treated immediately for adequate response and survival rates. DL, especially in the diagnosis of brain tumors using MRI and CT scans, has applied its abilities to identify excellent patterns. The proposed ensemble framework begins with the image preprocessing of the brain MRI to enhance the quality of images. These images are then utilized to train seven DL models and all of these models recognize the features related to the tumor. There are four models which are General, Glioma, Meningioma, and Pituitary tumors or No Tumor model, which helps in reaching a joint profitable prediction and concentrating solely on the strength of the estimation and outcome. This is a significant improvement over all the individual models, attaining a 99. 43% accuracy. The data used in this research was gotten from Kaggle website and comprised of 7023 images belonging to four classes. The further works will be to increase the data size more investigate other DL architectures, further enhance real time detection to enhance on the diagnostic scans’ accuracy and overall relevancy to clinical practice.