XLIV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais

Calorimeters with fine sensor segmentation used in High Energy Physics experiments suffer from mutual interference due to electromagnetic coupling between neighboring sensor cells. Crosstalk affects the characterization and measurement of incident particle properties, like energy and time of flight, degrading the quality of event reconstruction. This...

A crescente densidade de usuários em redes 5G impõe desafios significativos para a alocação eficiente de recursos em sistemas sem fio. Nesse contexto, arquiteturas Cell-Free Massive MIMO (CF-mMIMO) combinadas com Rate-Splitting Multiple Access (RSMA) surgem como uma solução promissora para mitigar interferências e melhorar a eficiência espectral. No...

This paper employs the NIH ChestX-ray14 dataset to compare the VGG16 and InceptionV3 architectures for multi-label chest X-ray classification. The impact of CLAHE-based contrast enhancement on convolutional neural network performance is investigated. Transfer learning was applied using ImageNet-pretrained weights. ROC curves and AUC metrics were used to...

Este trabalho apresenta uma abordagem interdisciplinar para o ensino de sistemas lineares e invariantes no tempo (LTI), utilizando o filtro RC passa-baixa como elemento integrador entre Circuitos Elétricos, Sinais e Sistemas e Cálculo Numérico. A proposta articula representações nos domínios do tempo e da frequência, incluindo modelagem por equações...

Neste trabalho, é apresentado um sistema de monitoramento acústico florestal em tempo real que utiliza aprendizado de máquina no próprio dispositivo para detecção de eventos. A solução tem como base o uso da arquitetura do YAMNet como extrator de características para gerar um modelo refinado que classifica sons críticos como "motosserra", "motor" e...

We investigate the remote tracking of a Markovian source in an energy-harvesting wireless system within the goal-oriented communication framework. We propose a Predictive transmission policy that exploits the source dynamics to suppress redundant updates while preserving energy for correcting persistent errors. The proposed policy employs prediction at...

Fifth Generation (5G) Networks research requires high-fidelity testbeds that balance the scalability of emulation with the realism of bare-metal setups. This paper introduces Ygarapé, a cloud-native architecture solution for transport network emulation that integrates Mininet into Kubernetes. Using an automated interface-hijacking and a Representational...

This work proposes a framework integrating technical network indicators from Brazil's Telecommunications Service Quality Regulation with consumer complaints filed at the national regulatory agency for Mobile Service (2022-2025). Complaint rates per thousand subscribers are spatially smoothed using Empirical Bayes estimation and associated with eight...

This paper presents the design and experimental evaluation of a low-cost LoRa-based temperature monitoring system deployed in an operational indoor environment. Each node consists of a waterproof enclosure coupled to an NTC 10 kΩ sensor, transmitting readings every 10 minutes with a 2-year battery lifetime. LoRa link performance was evaluated in a 444 m²...

This work presents the design and comparative analysis of two 90º hybrids for phase-shift applications on OFDM signal processing in the context of 5G NR systems operating at 900 MHz (Band n8). Both designs were validated by electrical simulation and measurements that show two main conclusions: the low-cost (FR4) and the high precision (RO4003C)...