XLIV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais

This work proposes a physics-guided representation learning framework for underwater acoustic communications based on privileged information available only during training. Physical channel descriptors extracted from paired TX-RX cycles are encoded by a descriptor-space teacher and distilled into a model that operates solely on received-signal...

Long-Range Frequency-Hopping Spread Spectrum (LR-FHSS) improves the upload capacity of LoRaWAN networks by fragmenting the payload and transmitting multiple header copies. This method, along with frequency hopping, helps towards mitigating interference. Previous works have identified headers as the primary bottleneck in LR-FHSS networks, and then...

Este artigo propõe o estudo e construção de duas antenas ressonadoras dielétricas cilíndricas constituídas de material cerâmico proveniente do reaproveitamento de telhas e tijolos com baixa permissividade relativa (εr = 3,65) e baixas perdas dielétricas (tan δ = 12 x 10-5) alimentada por estruturas de acoplamento por abertura com a fenda de alimentação...

This work considers finite-horizon status-update systems for real-time IoT monitoring, where multiple devices contend for a shared slotted random-access channel and each device has a strict transmission budget (e.g., due to duty-cycle/energy limits). Unlike a recently proposed single-device perspective, we quantify how cost-effective feedback interacts...

Este trabalho apresenta o projeto, simulação, fabricação e caracterização experimental de uma Superfície Seletiva em Frequência (FSS) baseada em uma geometria inspirada na espiral de Fibonacci para controle de polarização em micro-ondas. A estrutura proposta apresenta comportamento de rejeição em múltiplas bandas, com resposta dependente da polarização...

Mammography is the primary breast cancer screening method, yet manual interpretation yields relevant false-negative rates. CNNs have shown promise for computer-aided diagnosis, but the isolated contribution of ROI extraction, attention, and wavelet pooling remains underexplored. This paper compares ten architectures on the mini-MIAS dataset via...

This paper presents a machine learning framework for diagnosing simple and combined mechanical faults in rotating machines from vibration data. The main goal is to investigate whether a classifier trained mostly on simple faults can generalize to previously unseen fault combinations. The study uses the COMFAULDA dataset, whose instances are represented...

This study presents measurements and modeling of penetration loss through single- and double-layer glass materials in the 1-4 GHz frequency band, relevant to Long-Term Evolution (LTE) and New Radio (NR) mobile networks. Experiments were conducted in an anechoic chamber using a software-defined radio (SDR) and a signal analyzer. We propose a novel...

This paper presents a high-frequency protection mechanism designed to safeguard RF communication systems exposed to high-intensity electromagnetic anomalies. The proposed solution employs a dual-stage architecture that combines a fast-response clamping circuit with an active isolation stage based on a high-frequency relay. The first stage limits...

Este trabalho investiga o uso de recobrimentos condutivos aplicados a invólucros poliméricos produzidos por manufatura aditiva como alternativa de baixo custo para obtenção de blindagem eletromagnética (EMI). O trabalho aplica diferentes tratamentos superficiais em amostras fabricadas em PLA. A efetividade de blindagem foi avaliada em 2,4 GHz por meio de...