arXiv subjects

Amine Abouaomar

Publications and source records attributed to Amine Abouaomar.

17 recordsLinked to original sources

arXiv2026

Sim2Win: A Team-Agnostic, Event-Based Pre-Match Outcome Prediction and Tactical Profiling System for Football

Pre-match tactical decision-making in professional football relies heavily on subjective expert analysis and identity-based scouting systems that cannot generalize to unseen teams. This paper presents Sim2Win, a team-agnostic, event-based pre-match tactical recommendation framework that reframes match outcome prediction as a tactical decision-support problem. Using StatsBomb open event data from eleven competitions spanning 178 teams and 1,411 team-match records, Sim2Win constructs five-match rolling tactical profiles, engineers four interpretable tactical feature ratios, clusters team behaviors into eight playstyles via K-Means, and trains thirteen classifiers to estimate win, draw, and loss probabilities from tactical matchup representations. The system operates without team names or identity features, enabling generalization to teams never seen during training. A rigorous Leave-One-Competition-Out (LOCO) evaluation demonstrates that Sim2Win achieves a mean ROC-AUC of 0.704 and mean accuracy of 55.4% on completely unseen teams, outperforming ELO, Pi-Rating, and GAP baselines on all 21 ROC-AUC comparisons and 19 of 21 accuracy comparisons. Among all evaluated models, CatBoost achieved the strongest in-distribution performance with 60.90% accuracy. These findings suggest that behavioral tactical representations provide transferable predictive signal under distribution shift and offer a viable alternative to identity-dependent football prediction systems.

cs.LG↗

arXiv2025

Optimizing Energy and Latency in 6G Smart Cities with Edge CyberTwins

The proliferation of IoT devices in smart cities challenges 6G networks with conflicting energy-latency requirements across heterogeneous slices. Existing approaches struggle with the energy-latency trade-off, particularly for massive scale deployments exceeding 50,000 devices km. This paper proposes an edge-aware CyberTwin framework integrating hybrid federated learning for energy-latency co-optimization in 6G network slicing. Our approach combines centralized Artificial Intelligence scheduling for latency-sensitive slices with distributed federated learning for non-critical slices, enhanced by compressive sensing-based digital twins and renewable energy-aware resource allocation. The hybrid scheduler leverages a three-tier architecture with Physical Unclonable Function (PUF) based security attestation achieving 99.7% attack detection accuracy. Comprehensive simulations demonstrate 52% energy reduction for non-real-time slices compared to Diffusion-Reinforcement Learning baselines while maintaining 0.9ms latency for URLLC applications with 99.1% SLA compliance. The framework scales to 50,000 devices km with CPU overhead below 25%, validated through NS-3 hybrid simulations across realistic smart city scenarios.

cs.NI↗

arXiv2025

AttriGen: Automated Multi-Attribute Annotation for Blood Cell Datasets

We introduce AttriGen, a novel framework for automated, fine-grained multi-attribute annotation in computer vision, with a particular focus on cell microscopy where multi-attribute 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 full-scale 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.

cs.CV↗

arXiv2025

EYE-DEX: Eye Disease Detection and EXplanation System

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 finetuned 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.

cs.CV↗

arXiv2025

Accelerating Cerebral Diagnostics with BrainFusion: A Comprehensive MRI Tumor Framework

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.

cs.CV↗

arXiv2025

Privacy-Preserving Offloading for Large Language Models in 6G Vehicular Networks

The integration of Large Language Models (LLMs) in 6G vehicular networks promises unprecedented advancements in intelligent transportation systems. However, offloading LLM computations from vehicles to edge infrastructure poses significant privacy risks, potentially exposing sensitive user data. This paper presents a novel privacy-preserving offloading framework for LLM-integrated vehicular networks. We introduce a hybrid approach combining federated learning (FL) and differential privacy (DP) techniques to protect user data while maintaining LLM performance. Our framework includes a privacy-aware task partitioning algorithm that optimizes the trade-off between local and edge computation, considering both privacy constraints and system efficiency. We also propose a secure communication protocol for transmitting model updates and aggregating results across the network. Experimental results demonstrate that our approach achieves 75\% global accuracy with only a 2-3\% reduction compared to non-privacy-preserving methods, while maintaining DP guarantees with an optimal privacy budget of $\varepsilon = 0.8$. The framework shows stable communication overhead of approximately 2.1MB per round with computation comprising over 90\% of total processing time, validating its efficiency for resource-constrained vehicular environments.

cs.CR↗

arXiv2024

Dynamics of Resource Allocation in O-RANs: An In-depth Exploration of On-Policy and Off-Policy Deep Reinforcement Learning for Real-Time Applications

Deep Reinforcement Learning (DRL) is a powerful tool used for addressing complex challenges in mobile networks. This paper investigates the application of two DRL models, on-policy and off-policy, in the field of resource allocation for Open Radio Access Networks (O-RAN). The on-policy model is the Proximal Policy Optimization (PPO), and the off-policy model is the Sample Efficient Actor-Critic with Experience Replay (ACER), which focuses on resolving the challenges of resource allocation associated with a Quality of Service (QoS) application that has strict requirements. Motivated by the original work of Nessrine Hammami and Kim Khoa Nguyen, this study is a replication to validate and prove the findings. Both PPO and ACER are used within the same experimental setup to assess their performance in a scenario of latency-sensitive and latency-tolerant users and compare them. The aim is to verify the efficacy of on-policy and off-policy DRL models in the context of O-RAN resource allocation. Results from this replication contribute to the ongoing scientific research and offer insights into the reproducibility and generalizability of the original research. This analysis reaffirms that both on-policy and off-policy DRL models have better performance than greedy algorithms in O-RAN settings. In addition, it confirms the original observations that the on-policy model (PPO) gives a favorable balance between energy consumption and user latency, while the off-policy model (ACER) shows a faster convergence. These findings give good insights to optimize resource allocation strategies in O-RANs. Index Terms: 5G, O-RAN, resource allocation, ML, DRL, PPO, ACER.

cs.NI↗

arXiv2024

Efficient Collaborations through Weight-Driven Coalition Dynamics in Federated Learning Systems

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.

cs.LG↗

arXiv2023

Vehicles Control: Collision Avoidance using Federated Deep Reinforcement 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.

cs.LG↗

arXiv2023

Federated Learning for Water Consumption Forecasting in Smart Cities

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.

cs.LG↗

arXiv2022

Federated Deep Reinforcement Learning for Open RAN Slicing in 6G Networks

Radio access network (RAN) slicing is a key element in enabling current 5G networks and next-generation networks to meet the requirements of different services in various verticals. However, the heterogeneous nature of these services' requirements, along with the limited RAN resources, makes the RAN slicing very complex. Indeed, the challenge that mobile virtual network operators (MVNOs) face is to rapidly adapt their RAN slicing strategies to the frequent changes of the environment constraints and service requirements. Machine learning techniques, such as deep reinforcement learning (DRL), are increasingly considered a key enabler for automating the management and orchestration of RAN slicing operations. Nerveless, the ability to generalize DRL models to multiple RAN slicing environments may be limited, due to their strong dependence on the environment data on which they are trained. Federated learning enables MVNOs to leverage more diverse training inputs for DRL without the high cost of collecting this data from different RANs. In this paper, we propose a federated deep reinforcement learning approach for RAN slicing. In this approach, MVNOs collaborate to improve the performance of their DRL-based RAN slicing models. Each MVNO trains a DRL model and sends it for aggregation. The aggregated model is then sent back to each MVNO for immediate use and further training. The simulation results show the effectiveness of the proposed DRL approach.

cs.DC↗

arXiv2022

Matching-Game for User-Fog Assignment

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.

cs.NI↗

arXiv2022

A Resources Representation For Resource Allocation In Fog Computing Networks

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.

cs.NI↗

arXiv2022

Mean-Field Game and Reinforcement Learning MEC Resource Provisioning for SFC

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.

cs.NI↗

arXiv2022

A Deep Reinforcement Learning Approach for Service Migration in MEC-enabled Vehicular Networks

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.

cs.NI↗

arXiv2022

Resource Provisioning in Edge Computing for Latency Sensitive Applications

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 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 forming it; thus, it is crucial to devise novel solutions that take into account the different physical resources of each edge device. In this paper, we propose a resource representation scheme, allowing each edge device to expose its resource information to the supervisor of the edge node through the mobile edge computing application programming interfaces proposed by European Telecommunications Standards Institute. The information about the edge device resource is exposed to the supervisor of the EN each time a resource allocation is required. To this end, we leverage a Lyapunov optimization framework to dynamically allocate resources at the edge devices. 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.

cs.NI↗

arXiv2021

Service Function Chaining in MEC: A Mean-Field Game and Reinforcement Learning Approach

Multi-access edge computing (MEC) and network virtualization technologies are important enablers for fifth-generation (5G) networks to deliver diverse applications and services. Services are often provided as fully connected virtual network functions (VNF)s, through service function chaining (SFC). However, the problem of allocating SFC resources at the network edge still faces many challenges related to the way VNFs are placed, chained and scheduled. In this paper, to solve these problems, we propose a game theory-based approach with the objective to reduce service latency in the context of SFC at the network edge. The problem of allocating SFC resources can be divided into two subproblems. 1) The VNF placement and routing subproblem, and 2) the VNF scheduling subproblem. For the former subproblem, we formulate it as a mean field game (MFG) in which VNFs are modeled as entities contending over edge resources with the goal of reducing the resource consumption of MEC nodes and reducing latency for users. We propose a on a reinforcement learning-based technique, where the Ishikawa-Mann learning algorithm (IMLA) is used. For the later subproblem we formulate it as a matching game between the VFNs and an edge resources in order to find the execution order of the VNFs while reducing the latency. To efficiently solve it, we propose a modified version of the many-to-one deferred acceptance algorithm (DAA), called the enhanced multi-step deferred acceptance algorithm (eMSDA). To illustrate the performance of the proposed approaches, we perform extensive simulations. The obtained results show that the proposed approaches outperform the benchmarks other state-of-the-art methods.

cs.NI↗