XLIV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais

Learning low-dimensional representations from multi-view relational data is challenging when underlying geometries differ across views. We propose Bary-GWMDS, a Gromov-Wasserstein-based method that operates directly on distance matrices to learn a consensus embedding preserving shared relational structure. By leveraging intrinsic distances, the approach...

Quantum circuit learning (QCL) has recently been proposed as a framework for optimizing eavesdropping attacks on the BB84 protocol. In this work, we investigate how learned attacks behave under realistic noisy conditions by systematically analyzing multiple single-qubit noise models, including depolarizing, bit-flip, phase-flip, amplitude damping, phase...

This paper proposes an intelligent road monitoring architecture integrating private 5G networks, LEO satellites as backhaul infrastructure, and Edge AI with Federated Learning, addressing coverage gaps across 6,600 kilometers of Brazilian federal highways. Replacing raw video streaming with locally processed SLM model gradients at (RSUs) reduces data...

This paper investigates the use of symbolic regression to derive analytical models for large-scale propagation in the Atlantic Forest environment using LoRa measurements. Unlike traditional empirical or machine learning approaches, symbolic regression provides concise and interpretable equations. Models are obtained using distance and spreading factor as...

This paper presents a computer vision-based framework for real-time impurity detection in cassava conveyor belts used in starch production. A YOLOv11m model was trained using transfer learning on a dataset collected from artisanal processing units, incorporating data augmentation to enhance generalization. The model achieved 80% precision and over 80%...

The increasing demand for wireless communication highlights the relevance of ultra-high frequency (UHF) systems, particularly for TV white space (TVWS) applications. However, existing designs struggle to simultaneously achieve compact size, dual-band operation, and high-isolation Multiple-Input Multiple-Output (MIMO) performance. This work proposes two...

This work presents a microstrip patch antenna (MPA) based on the Firat outer model fractal for compact dual-band TV White Space (TVWS) applications. The proposed Firat fractal MPA with reflector plane operates at 560 MHz and 680 MHz on an FR-4 substrate. Our approach indicates a patch area reduction exceeding 70% at each operating frequency, confirming...

Este trabalho propõe a caracterização espectral e energética de sinais musicais no espaço bidimensional arousal-valence, com o objetivo de identificar padrões discriminativos por quadrante nos domínios do tempo e da frequência. Utilizouse a base DEAM (1802 faixas), particionada pelas medianas de arousal e valence em quatro grupos: Q1 (alto arousal, alta...

This paper investigates the impact of Beyond-Diagonal Reconfigurable Intelligent Surfaces (BD-RIS), considering single-, group-, and fully-connected architectures, on the achievable rate region of an uplink system with coexisting eMBB and URLLC services under OMA, NOMA, and RSMA-based RAN slicing. A Genetic Algorithm (GA)-based optimization method is...

Accurate spectrum hole geolocation (SHG) is essential for efficient dynamic spectrum access. NCSS enables direct mapping between sensing decisions and sensor locations, but sparse observations limit spatial reconstruction. This paper proposes a deep learning-assisted non-cooperative spectrum sensing (NCSS) framework for SHG in Internet of Things (IoT)...