arXiv subjects

Jonathan Rodriguez

Publications and source records attributed to Jonathan Rodriguez.

8 recordsLinked to original sources

arXiv2026

Agentic Trust Coordination for Federated Learning through Adaptive Thresholding and Autonomous Decision Making in Sustainable and Resilient Industrial Networks

Distributed intelligence in industrial networks increasingly integrates sensing, communication, and computation across heterogeneous and resource constrained devices. Federated learning (FL) enables collaborative model training in such environments, but its reliability is affected by inconsistent client behaviour, noisy sensing conditions, and the presence of faulty or adversarial updates. Trust based mechanisms are commonly used to mitigate these effects, yet most remain statistical and heuristic, relying on fixed parameters or simple adaptive rules that struggle to accommodate changing operating conditions. This paper presents a lightweight agentic trust coordination approach for FL in sustainable and resilient industrial networks. The proposed Agentic Trust Control Layer operates as a server side control loop that observes trust related and system level signals, interprets their evolution over time, and applies targeted trust adjustments when instability is detected. The approach extends prior adaptive trust mechanisms by enabling context aware intervention decisions, rather than relying on fixed or purely reactive parameter updates. By explicitly separating observation, reasoning, and action, the proposed framework supports stable FL operation without modifying client side training or increasing communication overhead.

cs.AI↗

arXiv2026

Trust Aware Federated Learning for Secure Bone Healing Stage Interpretation in e-Health

This paper presents a trust aware federated learning (FL) framework for interpreting bone healing stages using spectral features derived from frequency response data. The primary objective is to address the challenge posed by either unreliable or adversarial participants in distributed medical sensing environments. The framework employs a multi-layer perceptron model trained across simulated clients using the Flower FL framework. The proposed approach integrates an Adaptive Trust Score Scaling and Filtering (ATSSSF) mechanism with exponential moving average (EMA) smoothing to assess, validate and filter client contributions.Two trust score smoothing strategies have been investigated, one with a fixed factor and another that adapts according to trust score variability. Clients with low trust are excluded from aggregation and readmitted once their reliability improves, ensuring model integrity while maintaining inclusivity. Standard classification metrics have been used to compare the performance of ATSSSF with the baseline Federated Averaging strategy. Experimental results demonstrate that adaptive trust management can improve both training stability and predictive performance by mitigating the negative effects of compromised clients while retaining robust detection capabilities. The work establishes the feasibility for adaptive trust mechanisms in federated medical sensing and identifies extension to clinical cross silo aggregation as a future research direction.

cs.LG↗

arXiv2025

Deep Reinforcement Learning for Backhaul Link Selection for Network Slices in IAB Networks

Integrated Access and Backhaul (IAB) has been recently proposed by 3GPP to enable network operators to deploy fifth generation (5G) mobile networks with reduced costs. In this paper, we propose to use IAB to build a dynamic wireless backhaul network capable to provide additional capacity to those Base Stations (BS) experiencing congestion momentarily. As the mobile traffic demand varies across time and space, and the number of slice combinations deployed in a BS can be prohibitively high, we propose to use Deep Reinforcement Learning (DRL) to select, from a set of candidate BSs, the one that can provide backhaul capacity for each of the slices deployed in a congested BS. Our results show that a Double Deep Q-Network (DDQN) agent using a fully connected neural network and the Rectified Linear Unit (ReLU) activation function with only one hidden layer is capable to perform the BS selection task successfully, without any failure during the test phase, after being trained for around 20 episodes.

cs.NI↗

arXiv2025

Reconfigurable Intelligent Surface-Enabled Physical-Layer Network Coding for Higher Order M-QAM Signals

Physical-Layer Network Coding (PNC) is an effective technique to improve the throughput and latency in wireless networks. However, there are two major challenges for PNC, especially when using higher order modulations: 1) phase synchronization and power control at the paired User Equipments (UEs); and 2) the ambiguity removal of the PNC mapping at the relay node. To address these challenges, in this paper, we apply power control at transmitting UEs and exploit Reconfigurable Intelligent Surfaces (RISs) to synchronize the phase of the transmitted signals and ensure that they arrive at the relay with the same power and phase rotation. Then, we employ modular addition for an unambiguous PNC mapping for M-ary Quadrature Amplitude Modulations (M-QAM). We evaluate the performance of the system in the framework of Orthogonal Frequency Division Multiplexing (OFDM)-PNC for different RIS sizes and modulation orders. Furthermore, we study the sensitivity of PNC systems for Channel Estimation Error (CEE). The results reveal that 1) PNC systems show quite higher sensitivity to CEE compared with RIS-assisted one-way relay channel systems; 2) when the CEE is low, RIS can considerably enhance the Signal-to-Noise Ratio (SNR) of the PNC system, e.g., for a Bit Error Rate (BER) of $10^{-3}$ (without channel coding), increasing the RIS size from one to 256 elements in 28 GHz band leads to 200% improvement in SNR.

cs.NI↗

arXiv2025

Intelligent Backhaul Link Selection for Traffic Offloading in B5G Networks

Fifth Generation (5G) mobile networks considers an expansive set of heterogeneous services with stringent Quality of Service (QoS) requirements, and traffic demand with inherent spatial-temporal distribution, which places the backhaul network deployment under potential strain. In this paper, we propose to harness network slicing, Integrated Access and Backhaul (IAB) technology coupled with satellite connectivity to build a dynamic wireless backhaul network that can provide additional backhaul capacity to the base stations on demand when the wired backhaul link is temporarily out of capacity. To construct the network design, Deep Reinforcement Learning (DRL) models are used to select, for each network slice of the congested base station, an appropriate backhaul link from the pool of available IAB and satellite links that meets the QoS requirements (i.e., throughput and latency) of the slice. Simulation results show that around 20 episodes are sufficient to train a Double Deep Q-Network (DDQN) agent, with one fully-connected hidden layer and Rectified Linear Unit (ReLU) activation function, that adjusts the topology of the backhaul network.

cs.NI↗

arXiv2024

Efficient Anchor Point Deployment for Low Latency Connectivity in MEC-Assisted C-V2X Scenarios

Next-generation cellular networks will play a key role in the evolution of different vertical industries. Low latency will be a major requirement in many related uses cases. This requirement is specially challenging in scenarios with high mobility of end devices, such as vehicular communications. The Multi-Access Edge Computing (MEC) paradigm seeks to satisfy it. In this article we propose the dynamic deployment of anchor point network functions at edge locations and the assignment of terminals to these anchor points with the joint objective of minimizing communications latency and reducing network overhead. We formally define the problem as a multi-objective optimization and also propose a novel heuristic greedy algorithm for approximating the solution. This algorithm compares favorably with baseline and state-of-the-art strategies for latency minimization while reducing the overhead caused by network reconfigurations.

cs.NI↗

arXiv2023

Grain-128PLE: Generic Physical-Layer Encryption for IoT Networks

Physical layer security (PLS) encompasses techniques proposed at the physical layer to achieve information security objectives while requiring a minimal resource footprint. The channel coding-based secrecy and signal modulation-based encryption approaches are reliant on certain channel conditions or a certain communications protocol stack to operate on, which prevents them from being a generic solution. This paper presents Grain-128PLE, a lightweight physical layer encryption (PLE) scheme that is derived from the Grain-128AEAD v2 stream cipher. The Grain-128PLE stream cipher performs encryption and decryption at the physical layer, in between the channel coding and signal modulation processes. This placement, like that of the A5 stream cipher that had been used in the GSM communications standard, makes it a generic solution for providing data confidentiality in IoT networks. The design of Grain-128PLE maintains the structure of the main building blocks of the original Grain-128AEAD v2 stream cipher, evaluated for its security strength during NIST's recent Lightweight Cryptography competition, and is therefore expected to achieve similar levels of security.

cs.CR↗

arXiv2022

End-to-End 3D Hand Pose Estimation from Stereo Cameras

This work proposes an end-to-end approach to estimate full 3D hand pose from stereo cameras. Most existing methods of estimating hand pose from stereo cameras apply stereo matching to obtain depth map and use depth-based solution to estimate hand pose. In contrast, we propose to bypass the stereo matching and directly estimate the 3D hand pose from the stereo image pairs. The proposed neural network architecture extends from any keypoint predictor to estimate the sparse disparity of the hand joints. In order to effectively train the model, we propose a large scale synthetic dataset that is composed of stereo image pairs and ground truth 3D hand pose annotations. Experiments show that the proposed approach outperforms the existing methods based on the stereo depth.

cs.CV↗