XLIV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais

Event photography produces large collections of images that are difficult to search manually, limiting participants ability to retrieve photographs in which they appear. This work presents a face-based image retrieval system designed for this context, combining a ResNet face encoder with Euclidean distance search over a pre-indexed gallery of embeddings....

This paper presents a low-complexity tensor-based channel estimation framework for downlink mmWave massive MIMO systems using passive Butler-matrix beamforming. By modeling received signals as a third-order PARAFAC tensor, we exploit known pilot structures via bilinear alternating least-squares (BALS) optimization to significantly reduce computational...

Precise pulse reconstruction in high-rate environments is a critical challenge for high-energy physics calorimetry systems, where signal pile-up and baseline fluctuations cause severe distortions. This paper presents a streamlined Convolutional Neural Network (CNN) architecture for real-time energy estimation in the ATLAS Tile Calorimeter channels under...

Este trabalho apresenta uma arquitetura vestível IoMT de baixo consumo baseada no ESP32-S3, integrando monitoramento de sinais vitais e detecção de proximidade via Wi-Fi Fine Time Measurement (FTM). O sistema utiliza o sensor MAX30102 para aquisição biométrica e o acelerômetro LIS3DH como gatilho de ativação do coprocessador ULP RISC-V, permitindo...

The integration of optical and radiofrequency (RF) systems is a key solution for the current and next telecommunication networks. This paper presents a study on optical interfaces applied to RF devices and equipment. The goal is mapping the interfaces that have been exploited to enable optical-wireless systems, as well as identifying gaps and...

This work presents an over-the-air (OTA) OFDM software-defined radio (SDR) prototype using GNU Radio and two HackRF One devices to evaluate classical and quantum-kernel channel estimation. LS, LMMSE, Support Vector Regression (SVR), and quantum-kernel SVR (QSVR) are compared on identical received IQ samples under controlled Gaussian and impulsive noise....

This paper proposes a user-scheduling framework for full-band multi-cell MU-MIMO-OFDM downlink systems. Each base station schedules users over a common 100 MHz carrier, while spatial separation is achieved through regularized zero-forcing precoding. The scheduling problem is coupled across cells due to inter-cell interference. We formulate it as a...

High-speed low-density parity-check (LDPC) decoding is a major bottleneck in continuous-variable quantum key distribution (CV-QKD) and motivates hardware acceleration with fixed-point arithmetic. This work compares the sum-product algorithm (SPA), min-sum algorithm (MSA), and normalized min-sum (NMS) under a unified low-SNR fixed-point framework using...

Este trabalho apresenta um sistema para detecção automática de sopro cardíaco a partir de sinais de fonocardiograma utilizando técnicas de aprendizado de máquina. A abordagem proposta combina a extração de características acústicas com uma rede neural convolucional para realizar a classificação entre sinais normais e sinais com sopro cardíaco. O modelo...

Radio frequency spectrum management requires analyzing vast documentation, challenging regulatory efficiency. As a solution, this work investigates the implementation of an AI assistant based on Retrieval-Augmented Generation (RAG) within the Brazilian telecommunications regulatory context. The focus is on analyzing how the quantity and scope of data...