Foundation deep learning (DL) models are general models, designed to learn general, robust and adaptable representations of their target modality, enabling finetuning across a range of downstream tasks. These models are pretrained on large, unlabeled datasets using self-supervised learning (SSL). Foundation models have demonstrated better generalization than traditional supervised approaches, a critical requirement for wireless communications where the dynamic environment demands model adaptability. In this work, we propose and demonstrate the effectiveness of a Vision Transformer (ViT) as a radio foundation model for spectrogram learning. We introduce a Masked Spectrogram Modeling (MSM) approach to pretrain the ViT in a selfsupervised fashion. We evaluate the ViT-based foundation model on two downstream tasks: Human Activity sensing and Spectrogram Segmentation. Experimental results demonstrate competitive performance to supervised training while generalizing across diverse domains. Notably, the pretrained ViT model outperforms a four-times larger model that is trained from scratch on the spectrogram segmentation task, while requiring significantly less training time, and achieves competitive performance on the human activity sensing task. This work demonstrates the effectiveness of ViT with MSM for pretraining as a promising technique for scalable foundation model development in future 6G networks.

Cell-free networks have emerged as a new paradigm for beyond-5G networks, offering uniform coverage and improved control over interference. However, scalability poses a challenge in full cell-free networks, where all access points (APs) serve all users. This challenge is addressed by user-centric clustering, where each user is served by a subset of APs, reducing complexity while maintaining coverage. In this paper, we provide an analysis of the relation between the user-centric clustering and pilot assignment problems in cell-free networks, and introduce a formulation which decouples both problems enabling each to be solved independently. We present a general problem formulation for the user-centric clustering problem, allowing the use of diverse per-user and network-wide performance metrics. Specifically, we focus on one instance of this framework, utilizing per-user spectral efficiency and network-wide sum spectral efficiency (SE) as metrics. Additionally, we formulate the pilot assignment problem to minimize overall channel estimation error while considering the user-centric clusters in evaluating the desirability of pilot assignments, which leads to better performing solutions. Both problems are classified as binary nonlinear programs that are at least NP-hard. To solve these optimization problems, our proposed methodology employs sample average approximation coupled with surrogate optimization for the user-centric clustering problem and utilizes the genetic algorithm for the pilot assignment problem. Numerical experiments demonstrate that the optimized solutions surpass baseline solutions, leading to significant improvements in spectral efficiency.

Deploying large-scale foundation models (FMs) in resource-constrained devices presents critical challenges due to their substantial computational and memory requirements. This is particularly relevant for multi-task wireless sensing FMs running on sensors. To overcome these limitations, we propose a tiny federated wireless foundation model (WFM) framework that combines spectrogram-guided structured block-wise pruning with federated learning (FL) for efficient on-device deployment. Our approach prunes non-essential encoder blocks in vision transformers (ViTs) by leveraging the masked spectrogram modeling (MSM) pretraining loss as an importance indicator, ensuring only the most structurally significant components are retained. This enables federated adaptation with frozen backbones and lightweight, task-specific heads, minimizing both computational burden and communication overhead. The pruning strategy preserves the integrity of spectrogram reconstruction, while federated fine-tuning supports decentralized learning across clients with heterogeneous data distributions. Experimental results on human activity sensing and radio signal identification tasks confirm the efficacy of our approach. Specifically, the pruned ViT-based WFMs achieve up to 93% multiply-accumulate operations (MACs) reduction, 85% lower CPU inference time, and 49% reduction in communication overhead, all while maintaining high task accuracy. Our method demonstrates strong generalization and robustness across varying pruning ratios and data heterogeneity levels, while substantially reducing communication overhead, making it highly suitable for real-world industrial IoT deployments.

Foundational deep learning (DL) models are general models, trained on large, diverse, and unlabelled datasets, typically using self-supervised learning techniques - and have led to significant advancements especially in natural language processing. These pretrained models can be fine-tuned for related downstream tasks, offering faster development and reduced training costs, while often achieving improved performance. In this work, we introduce Masked Spectrogram Modeling, a novel self-supervised learning approach for pretraining foundational DL models on radio signals. Adopting a Convolutional LSTM architecture for efficient spatio-temporal processing, we pretrain the model with an unlabelled radio dataset collected from over-the-air measurements. Subsequently, the pretrained model is fine-tuned for two downstream tasks: spectrum forecasting and segmentation. Experimental results demonstrate that our methodology achieves competitive performance in both forecasting accuracy and segmentation, validating its effectiveness for developing foundational radio models.

The adoption of Internet of Things (IoT) and monitoring devices in 5G and beyond networks has been widespread. Unmanned aerial vehicles (UAVs) have shown success in connecting rural and remote areas due to the high cost of deploying infrastructures like cellular network base stations and optical fiber connections in vast landscapes with sparse populations. The constrained energy of UAVs results in limited coverage area and flight time, which in turn reduces the potential of UAVs to provide task-oriented wireless communication links. In this article, we explore path optimization and transmission organization algorithms to minimize flight time and extend the range of UAVs performing collaborative federated learning (FL) among geographically dispersed nodes communicating through wireless connections offered by UAVs coupled with device-to-device (D2D) networks. The UAV orchestrates FL between spatially scattered homes via long-range radio wireless communication. We formulate the drone path optimization as a traveling salesman problem (TSP) and employ self-organizing maps (SOM) for path planning. Additionally, knowledge distillation (KD)-based FL is used to reduce communication overhead for the resource-constrained UAV-IoT system. Experimental results demonstrate SOM’s ability to represent the topological structure of nodes and produce a cost-efficient Hamiltonian cycle, from which the drone path is derived. Our results demonstrate the communication efficiency and utility of KD-based FL compared to model-based FL methods. The proposed hybrid solution enables energy-constrained UAVs to perform FL over large areas leveraging a shared data set for KD and a SOM-based path optimization algorithm.

This paper addresses the user-centric clustering and pilot assignment problems in cell-free networks, recognizing the need to solve both problems simultaneously. The motivation of this research stems from the absence of benchmarks, general formulations, and the reliance on subjectively designed objective functions and heuristic algorithms prevalent in existing literature. To tackle these challenges, we formulate stochastic non-linear binary integer programs for both the user-centric clustering and pilot assignment problems. We specifically design the pilot assignment formulation to incorporate user-centric clusters when evaluating the desirability of pilot assignments, resulting in improved efficiency. To solve the problems, the proposed methodology employs sample average approximation coupled with surrogate optimization for the user-centric clustering problem and the genetic algorithm for the pilot assignment problem. Numerical experiments demonstrate that the optimized solutions outperform baseline solutions, leading to significant gains in spectral efficiency.

Students are facing various difficulties in courses like Programming and Data Structure through undergraduate programs, which is why failure rates and dropouts in these courses are high. Identifying students at risk of failure at an early stage of a semester is a serious challenge in higher education, so predicting students' academic performance is one of the most essential research topics to reduce failure rates, and to improve the performance of students by the end of a semester. We are developing a predictive model based on a deep artificial neural network to predict students' academic performance of upcoming courses based on their grades in previous courses of the first academic year. We have used one of the most common resampling methods, which is the SMOTE approach to handle the problem of the imbalanced dataset. The preliminary results show that our proposed model has achieved 86% accuracy. To put our system in context, we compared our results to some traditional machine learning techniques such as Decision Tree, K-Nearest Neighbor, and Random Forest, which were applied to an online dataset that has been widely used in some previous works. The comparison showed that our experimental results have achieved better results than the other traditional models. In future work, we will use a larger dataset to improve the accuracy of our models. Using other oversampling techniques such as SVM-SMOTE and Random Over Sampler will be used to evaluate their performance in comparison to the algorithms used in our work.

In the recent times, social media has become important in the field of health care as a major resource of valuable health information. Social media can provide massive amounts of data in real-time through user interaction, and this data can be analysed to reflect the harms and benefits of treatment by using the personal health experiences of users to improve health outcomes. In this study, we propose an enhanced data mining framework for analysing user opinions on Twitter and on a health-care forum. The proposed framework measures the degree of satisfaction of consumers regarding the drug Xeljanz, which is used to treat rheumatoid arthritis. The proposed framework is based on seven steps distributed in two phases. The first phase involves aggregating data related to the drug Xeljanz. This data is pre-processed to produce a list of words with a term frequency-inverse document frequency score. The word list is then classified into the following three categories: positive, negative and neutral. The second phase involves modelling social media posts using network analysis, identifying sub-graphs, calculating average opinions and detecting influential users. The results showed 77.3% user satisfaction with Xeljanz. Positive opinions were especially pronounced among users who switched to Xeljanz based on advice from a physician. Negative opinions of Xeljanz typically pertained to the high cost of the drug.

The purpose of this work is to develop a computer-aided diagnosis (CAD) system for detecting and localizing prostate cancer from diffusion-weighted magnetic resonance imaging (DWI) acquired at five distinct b-values. The first step in the proposed system depends on nonnegative matrix factorization (NMF) to fuse intensity features of prostate voxels, spatial features of neighboring voxels, and shape prior features to guide the evolution of a level set function for accurate prostate segmentation. The second step in the proposed system involves calculating the apparent diffusion coefficient (ADC) maps of the segmented prostate regions as a discriminating feature between malignant and healthy cases. These ADC maps are used in the last step of the CAD system to train a convolutional neural network (CNN)-based model to identify the ADC maps with malignant tumors. To evaluate the accuracy of the system, 50% of the ADC maps are randomly chosen to train the CNN-model while the second 50% of the ADC maps are used to evaluate the accuracy of the trained model. The proposed CAD system resulted in an average area under the receiver operating characteristic curve (AUC) of 0.93 at the five b-values.

The rapid growth of social networks opens interesting research opportunities to make use of the massive information exchanged in day-to-day communication. One of the active research issues related to this aspect is the study of online community formation and evolution in dynamic social networks. As community structure is usually ambiguous, then defining how it evolves over time becomes a challenge in terms of tracking mechanism and evaluation method. In this study, we review the online communities and their evolution tracking mechanisms and discuss the main categories of approaches for tracking community evolution and how they work. We analyse the different solutions proposed under each community evolution tracking category and provide an assessment of their projected performance. Finally, a discussion of analysis insights concerning community evolution and its influence is introduced.

The world is experiencing exponential growth in the use of SCADA systems in many industrial fields. The increased and considerable growth in information and communication technology has been forcing SCADA organizations to shift their SCADA systems from proprietary technology and protocol-based systems into internet-based ones. This paradigm shift has also increased the risks that target SCADA systems. To protect such systems, a risk management process is needed to identify all the risks. This study presents a detailed investigation on twenty-one scientific articles, guidelines, and databases related to SCADA risk identification parameters and provides a comparative study among them. The study next proposes a comprehensive risk identification model for SCADA systems. This model was built based on the risk identification parameters of ISO 31000 risk management principles and guidelines. The model states all risk identification parameters, identifies the relationships between those parameters, and uses a hierarchical-based method to draw complete risk scenarios. In addition, the proposed model defines the interdependency risk map among all risks stated in the model. This risk map can be used in understanding the evolution of the risks through time in SCADA systems. The proposed model is then transformed into a benchmark database containing 19,163 complete risk scenarios that can affect SCADA systems. Finally, a case study is presented to demonstrate one of the usages of the proposed model and its benchmark database. This case study provides 306 possible attack scenarios that Hacktivist can use to affect SCADA systems.

This paper addresses the issue of early diagnosis of prostate cancer from diffusion-weighted magnetic resonance imaging (DWI) using a convolutional neural network (CNN) based computer-aided diagnosis (CAD) system. The proposed CNN-based CAD system first segments the prostate using a geometric deformable model. The evolution of this model is guided by a stochastic speed function that exploits first- and second-order appearance models besides shape prior. The fusion of these guiding criteria is accomplished using a nonnegative matrix factorization (NMF) model. Then, the apparent diffusion coefficients (ADCs) within the segmented prostate are calculated at each b-value. They are used as imaging markers for the blood diffusion of the scanned prostate. For the purpose of classification/diagnosis, a three dimensional CNN has been trained to extract the most discriminatory features of these ADC maps for distinguishing malignant from benign prostate tumors. The performance of the proposed CNN-based CAD system is evaluated using DWI datasets acquired from 45 patients (20 benign and 25 malignant) at seven different b-values. The acquisition of these DWI datasets is performed using two different scanners with different magnetic field strengths (1.5 Tesla and 3 Tesla). The conducted experiments on in-vivo data confirm that the use of ADCs makes the proposed system nonsensitive to the magnetic field strength.

Software architects cannot avoid the consideration of quality attributes when designing software architecture. Architectural styles such as Layers and Client-Server are often used by architects to describe the overall structure and behavior of software. Although an architectural style affects the achievement of quality attributes, these quality attributes are directly performed by design decisions called architectural tactics. While the implementation of an architectural tactic supports a specific quality attribute, it often enhances or hurts other quality attributes in the software. In this paper, a framework for selecting the most appropriate architectural tactics according to their best achievement of the required levels of quality attributes when developing transaction processing systems is proposed. The proposed framework is based on fuzzy measures using Choquet Integral approach and takes into account the impact of architectural tactics on quality attributes, the preferences of quality attributes and the interactions between them. It can also be used to compare different potential architectures in terms of their supporting of quality attributes. The abilities and the advantages of the proposed framework are clarified via practical experiments using a case study.

In this paper, we propose a novel non-invasive framework for the early diagnosis of prostate cancer from diffusion-weighted magnetic resonance imaging (DW-MRI). The proposed approach consists of three main steps. In the first step, the prostate is localized and segmented based on a new level-set model. In the second step, the apparent diffusion coefficient (ADC) of the segmented prostate volume is mathematically calculated for different b-values. To preserve continuity, the calculated ADC values are normalized and refined using a Generalized Gauss-Markov Random Field (GGMRF) image model. The cumulative distribution function (CDF) of refined ADC for the prostate tissues at different b-values are then constructed. These CDFs are considered as global features describing water diffusion which can be used to distinguish between benign and malignant tumors. Finally, a deep learning auto-encoder network, trained by a stacked non-negativity constraint algorithm (SNCAE), is used to classify the prostate tumor as benign or malignant based on the CDFs extracted from the previous step. Preliminary experiments on 53 clinical DW-MRI data sets resulted in 100% correct classification, indicating the high accuracy of the proposed framework and holding promise of the proposed CAD system as a reliable non-invasive diagnostic tool.