Early and precise diagnosis of brain tumors is essential for successful treatment planning and improved patient outcomes. This paper introduces a novel hybrid deep model that incorporates DenseNet121, a convolutional neural network (CNN), and the Swin Transformer, a vision transformer model, by feature-level fusion to classify brain tumors from magnetic resonance imaging (MRI) scans. The suggested method provides a more discriminative and better representation by uniting the global context capability of the Transformer model with the local feature extraction capability of the CNN model. The suggested method was trained and assessed on a publicly available brain MRI dataset of four classes: glioma, meningioma, pituitary tumor, and no tumor. Experimental results indicate that the proposed approach outperforms many baseline models including VGG16, MobileNetV2, and AlexNet with an accuracy of 99.39%, precision of 99.36%, recall of 99.34%, and F1-score of 99.35%. Grad-CAM was utilized to visualize class-discriminative regions in the MRI scans to enhance interpretability, hence validating the model's emphasis on tumor-relevant regions. These outcomes prove the efficacy of coupling Transformer and CNN architectures in obtaining accurate and interpretable brain tumor classification from MRI scans.

 Fuzzy Neural Networks (FNNs) enhance conventional Artificial Neural Networks (ANNs) by incorporating fuzzy membership functions, which enable the handling of uncertainty, ambiguity, and imprecise information. While Fuzzy Backpropagation Neural Networks (FBNNs) improve classification performance across noisy datasets, the effectiveness of fuzzification heavily depends on the proper tuning of membership function parameters—typically optimized manually. This paper presents a novel Artificial Immune System framework for optimizing Fuzzy Backpropagation Neural Networks used in the classification of biological image data. The approach integrates a fuzzy min–max fuzzification layer with a feed-forward backpropagation network and applies an optimization version of an Artificial Immune Network model, derived from opt-aiNet, to tune trapezoidal membership functions. Experimental results confirm that the proposed immune-driven optimization is an effective technique for enhancing FBNN robustness and generalization.

Ischemic brain stroke is the most prevalent type of stroke caused by the occlusion of blood vessels via thrombi or blockages and is the second most common cause of mortality globally, after ischemic heart disease. To improve patient outcomes, ischemic stroke must be diagnosed timely and precise. This paper introduces a novel approach toward ischemic stroke detection from computed tomography (CT) images by integrating deep learning and optimization techniques for feature extraction and selection. The VGG16 model is utilized to extract high-dimensional spatially rich features that efficaciously capture the intricate texture and spatial patterns within the CT scans. To optimize these features, a genetic algorithm (GA) is leveraged to select the most discriminative subset and reduce redundancy. The new method was developed and evaluated on a unique, first-hand dataset gathered from a specialized private hospital in Palestine. The findings show that the suggested combined technique VGG16-GA highly enhances the performance of all classifiers. Notably, the VGG16-GA-XGB model attained superior outcomes, with an accuracy of 98.89%, precision of 98.85%, recall of 98.93%, and an F1-score of 98.92%.

The electric power system network has become more self-sufficient and less dependent on fossil fuel-based units due to the increasing integration of renewable energy resources. It is crucial to have an efficient method or technology for managing the system’s economics, security, reliability,  environmental damage, and the un- certainties that come with fluctuating loads. In this context, this paper utilizes a framework based on probabi- listic simulation of a demand-side management approach and computational intelligence to calculate the optimal value of saving utility cost (SUC). Unlike traditional methods that dispatch peak-clipped resource blocks sequentially, a modified artificial bee colony (MABC) algorithm is employed. The SUC is then reported through a sequential valley-filling procedure. Consequently, the SUC is derived from the overall profitability of the gen- eration system and includes savings in energy costs, capacity costs, and expected cycle costs. Further investi- gation to obtain the optimal value of SUC was conducted by comparing the SUC determined directly and indirectly, explicitly referring to the peak clipping energy of thermal units (PCETU). The comparisons utilized the MABC algorithm and a standard artificial bee colony, and the results were verified using the modified IEEE RTS- 79 with varying peak load demands. The findings illustrate that the proposed method demonstrated robustness in determining the global optimal values of SUC increments, achieving increases of 7.26 % for 2850 MW and 5 % for 3000 MW, compared to indirect estimation based on PCETU. Moreover, SUC increments of 18.13 % and 25.47 % were also achieved over the conventional method.

Abstract—In the current landscape of power system utilities, ensuring stability and reliability is more crucial than ever, highlighting the  importance of your expertise and contributions. Protecting transmission lines is essential for  maintaining these key attributes in power delivery. This study introduces an innovative approach  using wavelet transform (WT) to an effective wavelet transform (WT) approach. Detect and classify  transmission line faults. The unique capabilities of wavelets make them ideal for addressing  transient disturbances in power systems. Our algorithm utilizes the discrete wavelet transform  (DWT) to extract the three-phase current signal in the case of a single line-to-ground fault.  Carefully selecting the Daubechies4 mother wavelet significantly enhances our ability to gather  helpful information about fault conditions. The classification process is based on careful  calculation. The absolute sum of the signal details at level 2 over a single cycle window provides  precise insights. We employed Power System Computer-Aided Design / Electromagnetic Transients with  DC (PSCAD/EMTDC) to generate the three-phase current signal in a tested 230 kv transmission system.  The simulation results robustly demonstrate that our proposed algorithm excels in detecting and  classifying both faulted and healthy phases, ensuring a future of heightened reliability in power  systems.

ABSTRACT: This paper focuses on using natural language processing (NLP) in chatbots to manage stress in war-affected countries. A Java-based chatbot was designed to alleviate stress using two algorithms: TextRank and Stanford_CoreNLP. The problem was solved by integrating different languages using a plugin. The chatbot was tested with fifteen people and received positive feedback. Modifications were made based on user feedback, with journaling being a winner. However, the chatbot faced limitations like a lack of Arabic language support and voice chat features.

This study provides a comprehensive evaluation of the compliance of key Libyan government websites with the Web Content Accessibility Guidelines (WCAG) 2.2, the latest international standard for digital accessibility published in October 2023. The assessment focuses on the nine new success criteria introduced in WCAG 2.2, which aim to improve accessibility for users with low vision, cognitive, and motor disabilities. By conducting thorough automated and manual testing, this research identifies the specific strengths and weaknesses of the evaluated websites in meeting WCAG 2.2 requirements at the A, AA, and AAA levels. The findings reveal significant areas for improvement across the government's online presence and provide actionable recommendations for Libyan institutions to enhance their digital accessibility efforts and create a more inclusive online environment for all citizens. KEYWORDS: digital accessibility, web accessibility, compliance, Libyan government websites

Daily incidents significantly impact the workflow of ambulance and healthcare personnel, whose critical role involves providing immediate medical treatment and facilitating transportation to hospitals. This study presents the design of a medical expert system aimed at enhancing first-aid response in ambulances and educating users on fundamental first-aid principles. The proposed system integrates a comprehensive knowledge base that catalogs disease symptoms and corresponding treatments, functioning similarly to a medical professional's guidance. While the system relies on pre-programmed symptoms, it allows for the continuous addition of new symptoms and diseases, ensuring adaptability in emergencies. This expert system is particularly beneficial for novice healthcare providers, equipping them with reliable diagnostic support and improving patient outcomes during medical emergencies.

The Libyan healthcare system faces significant challenges in medication management, with high rates of medication errors posing serious risks to patient safety. Digital transformation, particularly through the adoption of electronic medical prescriptions, offers a promising solution to enhance prescription accuracy, improve patient outcomes, and streamline healthcare processes. This technical paper examines the implementation of digital medical prescriptions in Libya, focusing on the role of health informatics, the validation of prescriptions, and the potential barriers to success. The paper also highlights efforts in Arab and African countries similar to Libya, showcasing best practices and lessons learned.

Keywords: Digital prescriptions, Libya healthcare system, Medication errors, Patient safety, Digital transformation, Prescription practices, Prescription accuracy, Handwritten prescriptions, Prescription software, electronic health record systems (EHRS).

The increasing use of inverter-based generation (IBG) in power grids raises concern about system  strength. This is partly due to the inherent interactions among multiple IBGs in close proximity to  one another. This paper proposes an approach to identifying the existential boundary of interaction  in a network using the relative electrical distance (RED) concept. The mathematical formulation of  the RED concept to address the interaction problem among the IBGs involved utilising the power  system network’s admittance matrix to capture its structural characteristics. An interaction matrix  derived from the RED values of all IBG pairs was then developed to identify the interacting IBG  groups. The proposed approach was demonstrated using the IEEE 39-bus system and a practical 72-bus  Nigerian power grid. Results showed that RED values effectively group interacting IBGs, with values  closer to 0 signifying higher interaction levels, values closer to 1 indicating lower interaction,  and a value of 1 denoting no interaction. Time-domain simulations confirmed the accuracy of the  approach, demon- strating that the effect of control interaction propagates proportionally to  neighbouring IBGs based on RED values. However, fault currents can influence the impact of control  interactions. This approach, which requires less computational effort, provides a quick  identification tool for potential areas of concern based on the degree of interaction, enhancing  the reliability of power grids with high IBG penetration.