Background: Deep learning (DL)-based medical image classification is becoming increasingly reliable, enabling physicians to make faster and more accurate decisions in diagnosis and treatment. A plethora of algorithms have been developed to classify and analyze various types of medical images. Among them, Convolutional Neural Networks (CNNs) have proven highly effective, particularly in medical image analysis and disease detection. Methods: To further enhance these capabilities, this research introduces MediVision, a hybrid DL-based model that integrates a vision backbone based on CNNs for feature extraction, capturing detailed patterns and structures essential for precise classification. These features are then processed through Long Short-Term Memory (LSTM), which identifies sequential dependencies to better recognize disease progression. An attention mechanism is then incorporated that selectively focuses on salient features detected by the LSTM, improving the model’s ability to highlight critical abnormalities. Additionally, MediVision utilizes a skip connection, merging attention outputs with LSTM outputs along with Grad-CAM heatmap to visualize the most important regions of the analyzed medical image and further enhance feature representation and classification accuracy. Results: Tested on ten diverse medical image datasets (including, Alzheimer’s disease, breast ultrasound, blood cell, chest X-ray, chest CT scans, diabetic retinopathy, kidney diseases, bone fracture multi-region, retinal OCT, and brain tumor), MediVision consistently achieved classification accuracies above 95%, with a peak of 98%. Conclusions: The proposed MediVision model offers a robust and effective framework for medical image classification, improving interpretability, reliability, and automated disease diagnosis. To support research reproducibility, the codes and datasets used in this study have been publicly made available through an open-access repository.

With the deployment of the fifth generation (5G) mobile network systems and the envisioned heterogeneous ultra-dense networks (UDNs), both small cell (SmC) and distributed antenna system (DAS) technologies are required by mobile network operators (MNOs) and venue owners to support multiple spectrum bands, multiple radio access technologies (RATs), multiple optical central offices (COs), and multiple MNOs. As a result, the neutral host business model representing a third party responsible for managing the network enterprise on behalf of multiple MNOs has emerged as a potential solution, mainly influenced by the desire to provide a high user experience without significantly increasing the total cost of ownership (TCO). However, designing a sustainable business model for a neutral host is a nontrivial task, especially when considered in the context of 5G and beyond (5GB) UDNs. In this paper, under an integrated optical wireless network infrastructure, we review how SmC and DAS technologies are evolving towards the adoption of the neutral host business model and identify key challenges and requirements for 5GB support. Thus, we explore recent candidate advancements in heterogeneous network integration technologies for the realization of an efficient 5GB neutral host business model design capable of accommodating both SmC and DAS. Furthermore, we propose a novel design architecture that relies on virtual radio access network (vRAN) to enable real-time dynamic resource allocation and radio over Ethernet (RoE) for flexible and reconfigurable fronthaul. The results from our simulations using MATLAB over two real-life deployment scenarios validate the feasibility of utilizing switched RoE considering end-to-end delay requirements of 5GB under different switching schemes, as long as the queuing delay is kept to a minimum. Finally, the results show that incorporating RoE and vRAN technologies into the neutral host design results in substantial TCO reduction by about 81% in an indoor scenario and 73% in an outdoor scenario.

Mental health challenges in Thalassemia patients are often overlooked, despite their significant impact on quality of life. Traditional statistical and machine learning approaches often fail to capture the complex, nonlinear relationships between psychosocial and clinical variables, limiting both accuracy and interpretability. To overcome this, we propose the Adaptive Multi-Stage Ensemble with Dynamic Feature Interaction (AMSE-DFI)—a novel feature selection framework that dynamically integrates mutual information, ensemble learning, and graph attention mechanisms to capture intricate feature interdependencies often missed by traditional approaches. Using the SF-36 health survey data from 356 Bangladeshi patients, AMSE-DFI effectively identified key predictors such as total SF score, role emotional, and physical health summary, which collectively reflect both physical and psychological well-being. The model outperformed conventional approaches, showing strong predictive reliability and robust generalization, with SMOTE effectively addressing class imbalance in the clinical data. Importantly, Local Interpretable Model-Agnostic Explanations (LIME) based explainable AI offered clear, interpretable insights into how key features affect individual patient outcomes, making the model more understandable and actionable for clinicians. This framework provides a practical, transparent tool to support early detection and personalized management of mental health challenges in Thalassemia care.

This study present a novel approach to dental digital modelling that combines 3D multi-object reconstruction with Finite Element Modelling (FEM) to create anatomically accurate and biomechanically stable dental models. The proposed approach overcomes limitations of traditional imaging techniques, such as resolution constraints, artifacts, noise, and poor soft tissue contrast, enabling precise analysis of stress distribution and material behaviour. A 3D model of a right maxillary central incisor (tooth no. 11) was developed and adapted into 4 variations receiving various prosthetic treatments: fibre post, resin core, and lithium disilicate crown (Model A); fibre post, resin core, and monolithic zirconia crown (Model B); lithium disilicate endocrown (Model C); and monolithic zirconia endocrown (Model D). Models and prosthetic treatments were created in accordance to dimensions reported in the literature. Preliminary Finite Element Analyses (FEAs) were performed to evaluate the mechanical behaviour and structural integrity of the models. Under a static load of 100 N applied at a 45° angle, the simulations revealed no significant deformations or irregular stress concentrations. Model A consisted of 33,235 nodes and 19,718 elements, while the simpler design of Model C reduced computational demands to 28,660 nodes and 17,253 elements. Monolithic zirconia, with an elastic modulus of 202,767 MPa, demonstrated superior structural stability across all simulations. By integrating evidence-based material and structural properties, our approach consistently produces semi-realistic models with adequate mesh density, enabling accurate representation of oral dynamics and precise force transmission across model components. These findings suggest that anatomically accurate dental models generated through advanced digital modelling and analysed using FEA can realistically simulate occlusal forces, offering a reliable platform for assessing new therapeutic dental approaches and improve upon existing treatment methods to optimise clinical outcomes and patient satisfaction.

Dynamic Bandwidth Allocation (DBA) techniques enable Time Division Multiplexing Passive Optical Network (TDM-PON) systems to efficiently manage upstream bandwidth by allowing the centralized Optical Line Terminal (OLT) to coordinate resource allocation among distributed Optical Network Units (ONUs). Conventional DBA techniques struggle to adapt to dynamic traffic conditions, resulting in suboptimal performance under varying load scenarios. This work suggests a Collaborative Split Learning-Based DBA (CSL-DBA) framework that utilizes the recently emerging Split Learning (SL) technique between the OLT and ONUs for the objective of optimizing predictive traffic adaptation and reducing communication overhead. Instead of requiring centralized learning at the OLT, the proposed approach decentralizes the process by enabling ONUs to perform local traffic analysis and transmit only model updates to the OLT. This cooperative strategy guarantees rapid responsiveness to fluctuating traffic conditions. We show by extensive simulations spanning several traffic scenarios, including low, fluctuating, and high traffic load conditions, that our proposed CSL-DBA achieves at least 99% traffic prediction accuracy, with minimal inference latency and scalable learning performance, and it reduces communication overhead by approximately 60% compared to traditional federated learning approaches, making it a strong candidate for next-generation 6G-grade TDM-PON systems.

This paper presents a hybrid adaptive approach based on machine learning (ML) for classifying incoming traffic, feature selection and thresholding, aimed at enhancing downgrade attack detection in Wi-Fi Protected Access 3 (WPA3) networks. The fast proliferation of WPA3 is regarded critical for securing modern Wi-Fi systems, which have become integral to 5G and Beyond (5G&B) Radio Access Networks (RAN) architecture. However, the wireless communication channel remains inherently susceptible to downgrade attacks, where adversaries intentionally cause networks to revert from WPA3 to WPA2, with the malicious intent of exploiting known security flaws. Traditional Intrusion Detection Systems (IDS), which rely on fixed-threshold statistical methods, often fail to adapt to changing network environments and new, sophisticated attack strategies. To address this limitation, we introduce a novel ML-based Feature Selection and Thresholding for Downgrade Attacks Detection (MFST-DAD) approach, which comprises three stages: traffic data preprocessing, baseline adaptive feature selection, and real-time detection and prevention using ML algorithms. Experimental results on a specially generated dataset demonstrate that the proposed approach detects downgrade attacks in WPA3 networks, achieving 99.8% accuracy with a Naive Bayes classifier in both WPA3 personal and enterprise transition modes. These findings confirm the effectiveness of our proposed approach in securing next-generation Wi-Fi systems.