Diseases of the heart and blood vessels are one of the most common causes of death worldwide, and early detection is crucial to prevent fatalities. Classical machine learning models tend to be inefficient as they are based on dense numerical computations and ignore the temporal features present in biological signals. This paper introduces a new application of Spiking Neural Network SNNs, a bio-inspiration model of deep learning, to predict heart attack risk on clinical data. The data (from Kaggle) includes patients' cholesterol levels, ECG results, and oxygen saturation. We modeled biologically plausible spike trains with Poisson-based temporal encoding, and trained the network's weights with Leaky Integrate-and-Fire (LIF) neurons. Particle Swarm Optimization (PSO) was applied to fine-tune the architecture parameters. The approach obtained an accuracy of 84.6% and an F1 of 86%, and the AUC was 0.89. This indicates that SNNs can be considered alternatives to classical models that provide effective and interpretable solutions for clinical DSSs.

The COVID-19 pandemic significantly disrupted dental education, hindering hands-on exposure to cutting-edge dental practices and advanced equipment worldwide. Amidst these challenges, the emergence of Metaverse-based learning has presented an innovative solution, fulfilling the growing need for remote educational opportunities in dentistry. Traditional online learning platforms like Zoom have proven inadequate for providing a comprehensive learning experience in dentistry, prompting a shift towards more engaging, immersive educational settings. This trend is especially evident in the dental education sector in the United Arab Emirates (UAE). This research delves into dental students‘ perceptions of how Metaverse technology aids in achieving their educational objectives within the UAE. Our analysis focuses on crucial factors that influence technology adoption, particularly ‘Perceived Value’ and ‘Perceived Satisfaction’. We collected a substantial dataset of 89 responses from the College of Dental Medicine (CDM) at the University of S harjah. To rigorously examine our research model, we applied Partial Least S quares-Structural Equation Modeling (PLS -S EM) and an advanced Machine Learning (ML) technique, based on data from our student survey. Our results highlight the Metaverse's critical role in guiding technology adoption decisions, strongly driven by ‘Perceived Value’ and ‘Perceived Satisfaction’. Remarkably, the ML method demonstrated higher predictive accuracy in identifying the outcome variable compared to other analysis techniques. This research contributes to the scholarly conversation on artificial intelligence, especially its relationship with environmental sustain ability, offering valuable insights for industry stakeholders, policymakers, and AI developers. The findings lay the groundwork for de veloping AI-powered solutions aligned with user preferences and environmental co n si de rati o n s.

Phishing involves malicious activity whereby phishers, in the disguise of legitimate entities, obtain illegitimate access to the victims’ personal and private information, usually through emails. Currently, phishing attacks and threats are being handled effectively through the use of the latest phishing email detection solutions. Most current phishing detection systems assume phishing attacks to be in English, though attacks in other languages are growing. In particular, Arabic is a widely used language and therefore represents a vulnerable target. However, there is a significant shortage of corpora that can be used to develop Arabic phishing detection systems. This article presents the development of a new English-Arabic parallel phishing email corpus that has been developed from the anti-phishing share task text (IWSPA-AP 2018). The email content was to be translated, and the task had been allotted to 10 volunteers who had a university background and were English and Arabic language experts. To evaluate the effectiveness of the new corpus, we develop phishing email detection models using Term Frequency–Inverse Document Frequency and Multilayer Perceptron using 1,258 emails in Arabic and English that have equal ratios of legitimate and phishing emails. The experimental findings show that the accuracy reaches 96.82% for the Arabic dataset and 94.63% for the emails in English, providing some assurance of the potential value of the parallel corpus developed.