The early and accurate classification of brain tumors is crucial for guiding effective treatment strategies and improving patient outcomes. This study presents BrainFusion, a significant advancement in brain tumor analysis using magnetic resonance imaging (MRI) by combining fine-tuned convolutional neural networks (CNNs) for tumor classification —including VGG16, ResNet50, and Xception—with YOLOv8 for precise tumor localization with bounding boxes. Leveraging the “Brain Tumor MRI Dataset”, our experiments reveal that the fine-tuned VGG16 model achieves test accuracy of 99.86%, substantially exceeding previous benchmarks. Beyond setting a new accuracy standard, the integration of bounding-box localization and explainable AI techniques further enhances both the clinical interpretability and trustworthiness of the system's outputs. Overall, this approach underscores the transformative potential of deep learning in delivering faster, more reliable diagnoses, ultimately contributing to improved patient care and survival rates.

Retinal disease diagnosis is critical in preventing vision loss and reducing socioeconomic burdens. Globally, over 2.2 billion people are affected by some form of vision impairment, resulting in annual productivity losses estimated at $411 billion. Traditional manual grading of retinal fundus images by ophthalmologists is time-consuming and subjective. In contrast, deep learning has revolutionized medical diagnostics by automating retinal image analysis and achieving expert-level performance. In this study, we present EYE-DEX, an automated framework for classifying 10 retinal conditions using the large-scale Retinal Disease Dataset comprising 21,577 eye fundus images. We benchmark three pre-trained Convolutional Neural Network (CNN) models—VGG16, VGG19, and ResNet50—with our fine-tuned VGG16 achieving a state-of-the-art global benchmark test accuracy of 92.36 %. To enhance transparency and explainability, we integrate the Gradient-weighted Class Activation Mapping (Grad-CAM) technique to generate visual explanations highlighting disease-specific regions, thereby fostering clinician trust and reliability in AI-assisted diagnostics.

We introduce AttriGen, a novel framework for automated, fine-grained multi-attribute annotation in computer vision, with a particular focus on cell microscopy where multiattribute classification remains underrepresented compared to traditional cell type categorization. Using two complementary datasets: the Peripheral Blood Cell (PBC) dataset containing eight distinct cell types and the WBC Attribute Dataset (WBCAtt) that contains their corresponding 11 morphological attributes, we propose a dual-model architecture that combines a CNN for cell type classification, as well as a Vision Transformer (ViT) for multi-attribute classification achieving a new benchmark of 94.62% accuracy. Our experiments demonstrate that AttriGen significantly enhances model interpretability and offers substantial time and cost efficiency relative to conventional fullscale human annotation. Thus, our framework establishes a new paradigm that can be extended to other computer vision classification tasks by effectively automating the expansion of multi-attribute labels.

In the era of the Internet of Things (IoT), decentralized paradigms for machine learning are gaining prominence. In this paper, we introduce a federated learning model that capitalizes on the Euclidean distance between device model weights to assess their similarity and disparity. This is foundational for our system, directing the formation of coalitions among devices based on the closeness of their model weights. Furthermore, the concept of a barycenter, representing the average of model weights, helps in the aggregation of updates from multiple devices. We evaluate our approach using homogeneous and heterogeneous data distribution, comparing it against traditional federated learning averaging algorithm. Numerical results demonstrate its potential in offering structured, outperformed and communication-efficient model for IoT-based machine learning.

In the face of growing urban populations and the escalating number of vehicles on the roads, managing transportation efficiently and ensuring safety have become critical challenges. To tackle these issues, the development of intelligent control systems for vehicles is paramount. This paper presents a comprehensive study on vehicle control for collision avoidance, leveraging the power of Federated Deep Reinforcement Learning (FDRL) techniques. Our main goal is to minimize travel delays and enhance the average speed of vehicles while prioritizing safety and preserving data privacy. To accomplish this, we conducted a comparative analysis between the local model, Deep Deterministic Policy Gradient (DDPG), and the global model, Federated Deep Deterministic Policy Gradient (FDDPG), to determine their effectiveness in optimizing vehicle control for collision avoidance. The results obtained indicate that the FDDPG algorithm outperforms DDPG in terms of effectively controlling vehicles and preventing collisions. Significantly, the FDDPG-based algorithm demonstrates substantial reductions in travel delays and notable improvements in average speed compared to the DDPG algorithm.

Water consumption remains a major concern among the world's future challenges. For applications like load monitoring and demand response, deep learning models are trained using enormous volumes of consumption data in smart cities. On the one hand, the information used is private. For instance, the precise information gathered by a smart meter that is a part of the system's IoT architecture at a consumer's residence may give details about the appliances and, consequently, the consumer's behavior at home. On the other hand, enormous data volumes with sufficient variation are needed for the deep learning models to be trained properly. This paper introduces a novel model for water consumption prediction in smart cities while preserving privacy regarding monthly consumption. The proposed approach leverages federated learning (FL) as a machine learning paradigm designed to train a machine learning model in a distributed manner while avoiding sharing the users data with a central training facility. In addition, this approach is promising to reduce the overhead utilization through decreasing the frequency of data transmission between the users and the central entity. Extensive simulation illustrate that the proposed approach shows an enhancement in predicting water consumption for different households.

The Internet of Things (IoT) is changing today's world, and Machine Learning (ML) is a major contributor to this revolution in terms of data exchange to mature connected objects. In this context, federated learning (FL) is emerging, a new ML paradigm that drives a model on decentralized data, which can be distributed across many IoT devices. FL has grown considerably in recent years, both in academia and industry. However, the majority of FL algorithms assume that all client nodes are honest and willing to participate in cooperative model learning. Thus, each node is able to provide reliable local models to the central server. However, in real-life scenarios, nodes may be corrupt, malicious, or both, and may not cooperate fairly during training phases. In this paper, we address the above challenge by proposing a new FL algorithm called DistFL. The main objective of DistFL is to prevent biased training by identifying malicious nodes during the training phase. We evaluate the effectiveness of our technique and demonstrate it through a concrete implementation, comparing DistFL with conventional FL. Even with up to 50% malicious nodes, the runtime cost of the DistFL model is still better than that of the conventional FL model, and its final accuracy reaches 97% with a loss function convergence rate twice that of the conventional FL model. For this study, we used urban water data to deal with leakage and distribution faults in the water network among different end users in this area.

The challenge of drinking water optimization refers to the need to effectively manage and distribute drinking water in a manner that is sustainable, efficient, and equitable. To address this challenge, governments, communities, and other stakeholders need to work together to develop and implement effective water management strategies, including the use of technology like IoT (Internet of Things) and innovative approaches to improve water efficiency, conserve water resources, and ensure access to safe drinking water for all. In this paper, we propose a new water distribution network architecture conception that can be implemented in new buildings in the context of smart homes. This architecture will allow us to better optimize the management of drinking water at the level of new Moroccan households domain in smart cities while reusing used water at the household level in toilet flushing, using an intelligent system with connected tanks. To preserve water resources and minimize the cost of water distribution.

In this paper, we address the resource provisioning problem for service function chaining (SFC) in terms of the placement and chaining of virtual network functions (VNFs) within a multi-access edge computing (MEC) infrastructure to reduce service delay. We consider the VNFs as the main entities of the system and propose a mean-field game (MFG) framework to model their behavior for their placement and chaining. Then, to achieve the optimal resource provisioning policy without considering the system control parameters, we reduce the proposed MFG to a Markov decision process (MDP). In this way, we leverage reinforcement learning with an actor-critic approach for MEC nodes to learn complex placement and chaining policies. Simulation results show that our proposed approach outperforms benchmark state-of-the-art approaches.

Multi-access edge computing (MEC) is a key enabler to reduce the latency of vehicular network. Due to the vehicles mobility, their requested services (e.g., infotainment services) should frequently be migrated across different MEC servers to guarantee their stringent quality of service requirements. In this paper, we study the problem of service migration in a MEC-enabled vehicular network in order to minimize the total service latency and migration cost. This problem is formulated as a nonlinear integer program and is linearized to help obtaining the optimal solution using off-the-shelf solvers. Then, to obtain an efficient solution, it is modeled as a multi-agent Markov decision process and solved by leveraging deep Q learning (DQL) algorithm. The proposed DQL scheme performs a proactive services migration while ensuring their continuity under high mobility constraints. Finally, simulations results show that the proposed DQL scheme achieves close-to-optimal performance.

Low-latency IoT applications, such as autonomous vehicles, augmented/virtual reality devices, and security applications, require high computation resources to make decisions on the fly. However, these kinds of applications cannot tolerate offloading their tasks to be processed on a cloud infrastructure due to the experienced latency. Therefore, edge computing (EC) is introduced to enable low latency by moving the tasks processing closer to the users at the edge of the network. The edge of the network is characterized by the heterogeneity of edge devices (EDs) forming it; thus, it is crucial to devise novel solutions that take into account the different physical resources of each ED. In this article, we propose a resource representation scheme, allowing each ED to expose its resource information to the supervisor of the edge node through the mobile EC application programming interfaces proposed by the European Telecommunications Standards Institute. The information about the ED resource is exposed to the supervisor of the edge node each time a resource allocation is required. To this end, we leverage a Lyapunov optimization framework to dynamically allocate resources at the EDs. To test our proposed model, we performed intensive theoretical and experimental simulations on a testbed to validate the proposed scheme and its impact on different system's parameters. The simulations have shown that our proposed approach outperforms other benchmark approaches and provides low latency and optimal resource consumption.

Fog computing is emerging as a new paradigm to deal with latency-sensitive applications, by making data processing and analysis close to their source. Due to the heterogeneity of devices in the fog, it is important to devise novel solutions which take into account the diverse physical resources available in each device to efficiently and dynamically distribute the processing. In this paper, we propose a resource representation scheme which allows exposing the resources of each device through Mobile Edge Computing Application Programming Interfaces (MEC APIs) in order to optimize resource allocation by the supervising entity in the fog. Then, we formulate the resource allocation problem as a Lyapunov optimization and we discuss the impact of our proposed approach on latency. Simulation results show that our proposed approach can minimize latency and improve the performance of the system.

Path loss is a main challenge in Molecular Communications. When molecules carry information based only on a natural diffusion, the number of molecules that can be received is inversely proportional to the square distance between the transmitter and the receiver, thus hugely impacting the received signal strength. The use of a Multi-Input Multi-Output (MIMO) technique can improve the performance of molecular communications by increasing the data rate. In this paper, we studied the receiver used in molecular MIMO communications. We focused on three important parameters for the receiver design, which are the channel distance, the distance between the detectors constructing the receiver and the detectors diameter. To optimize the design of a 3×3 MIMO receiver, we used AcCoRD simulator to obtain 3D stochastic simulations for each scenario. We evaluated the simulation results by studying the error probability and the number of molecules representing the signal strength. We then proposed two optimization problems that aim at optimizing the receiver parameters choice, and two algorithms to solve the problems. The study shows that a judicious choice of the three parameters combination can optimize MIMOs receiver design, which can decrease the error probability and improve the performance of Molecular Communication.

Fog computing has emerged as a new paradigm in mobile network communications, aiming to equip the edge of the network with the computing and storing capabilities to deal with the huge amount of data and processing needs generated by the users devices and sensors. Optimizing the assignment of users to fogs is, however, still an open issue. In this paper, we formulated the problem of users-fogs association, as a matching game with minimum and maximum quota constraints, and proposed a Multi-Stage Differed Acceptance (MSDA) in order to balance the use of fogs resources and offer a better response time for users. Simulations results show that the performance of the proposed model compared to a baseline matching of users, achieves lowers delays for users.

Content is not always about medias and files, computing tasks output are also a content that can be described, stored and cached. In this paper, we investigated the problem of edge computing and caching in the fog computing networks. In our scenario, we consider the user requests computing tasks from the fog, that the devices could not handle. Moreover, fogs use their storage and computing capabilities to cache the tasks computation results in order to minimize the latency, and use it storage to offload their resources by caching the significant computing tasks output. We propose a clustering method based on the correlation between the tasks and the cached content to decide what fog will give a better service in term of latency to offer better quality of service and experience. The problem of the users-fogs association was formulated as a coalition game between the users and the fogs. Finally, we use the BoltzmannGibbs learning algorithm to make every entity able to learn the best coalition, in order to enhance the convergence of the system to reach a better and optimal stability.

Files and medias are not the only existing content. Computing tasks output content that can be described, stored, cached and offloaded. In this paper, we investigated the problems of edge computing and offloading in fog computing networks. Edge devices have always been limited in computing capabilities. The problem of latency occurs frequently when having huge amount of data to be processed. In Considering a given number of fogs serving multiple users, this paper investigates the problems of distributing computational tasks among the fogs. We propose a coalition game based solution to motivate the fogs to work together and cooperate, which in turn processes huge amounts of data within a short delay. Simulation results shows that the proposed model offers better latency and improved load balancing of the fogs resources.

Many researches and standardization work on the challenges that 5thnetworks generation raised from the radio perspective while employing advanced techniques such as massive MIMO (Multiple-Input-Multiple-Output) and CoMP (Cooperative Multi-points Processes). However the backhaul problems such as bottlenecks has emerged due to the deployment of ultradense and heavy traffic that should be connected to the core networks. In this paper we investigate the caching as a promising solution to deal with the backhaul problems and the offload of the network. By caching the content near the users, at the base stations or at the device side via device-to-device communications or in advanced architecture of the cloud (In the Fog) is a promising solution to bring the interesting content closer to the users. Caching techniques are many, in this paper we grouped the most interesting ones with regard to different architectures, considering the cases and the quality of the solutions.