XLIV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais

This paper introduces a novel reinforcement learning method, called Truncated Importance-Sampling Emphatic TD3 (TISE-TD3), which is tested in a Home Energy Management Systems (HEMS) framework. Operating in a free-energy market, the model uses real-world household consumption data, weather signals (irradiance and temperature), and price series at 5-minute...

Reliable assessment of respiratory ciliary motion is essential for evaluating mucociliary clearance and supporting the diagnosis of respiratory dysfunctions such as Primary Ciliary Dyskinesia (PCD). Current analysis relies on expert visual inspection of high-speed videos, which is subjective and difficult to scale. This study proposes a supervised,...

This work investigates Low-Density Parity-Check (LDPC) codes in short block-length regimes, which are highly relevant for future communication systems. Although LDPC codes are known for their near-capacity performance, their efficiency can be limited when the code length is reduced, particularly in scenarios involving heterogeneous bit-channel...

This work presents a numerical analysis of two LiDAR architectures for greenhouse gas sensing, with a focus on the detection of CO2 and CH4. The simulations were performed using the Lumerical Interconnect software. The first architecture evaluates a conventional IPDA LiDAR system, in which the laser wavelength is switched between spectral regions inside...

Dynamic time division duplex (D-TDD) in distributed multiple-input multiple-output (D-MIMO) networks allows for efficient management of asymmetric traffic demands but introduces cross link interference (CLI). This paper addresses these operational conflicts by analyzing the joint application of both user clustering and power control strategies. By first...

Television (TV) 3.0 introduces advanced physical-layer technologies to support next-generation digital terrestrial television services, including high-definition and ultra-high-definition video delivery. Among these technologies, dual-polarized 2 × 2 multiple-input multiple-output (MIMO) transmission plays an important role in improving spectral...

The use of 1-bit analog-to-digital converters with temporal oversampling at the receiver has emerged as a solution for energy-constrained wireless systems with increased spectral efficiency. The corresponding receivers consume less energy and have a simpler hardware architectures compared to their high-resolution counterparts. Zero-crossing modulation...

Extracting predictive signals in financial time series is challenging due to inherent noise. This paper proposes a Deep Reinforcement Learning architecture based on DDPG and LSTM (Long Short-Term Memory) networks, structured into a committee of specialist agents across multiple scales (daily, 1h, 30m, and 5m). The actions recommended by individual agents...

Este artigo propõe e valida experimentalmente uma metodologia de calibração conjunta de alcance e ângulo de chegada (AoA) para radares automotivos FMCW de 77 GHz em ambiente não controlado. Utilizando o radar AWR2944EVM em área aberta de baixa refletividade, o método estima por mínimos quadrados os erros sistêmicos de hardware, dispensando câmara...

This paper presents a real-time spectrum sensing system for TV white spaces (TVWS) applications based on offlinetrained deep learning (DL) models for online inference. The system employs an Ettus USRP B210 software-defined radio (SDR) and MATLAB to evaluate, over ultra high frequency (UHF) ISDB-TB signals, three DL-based sensing approaches: a dense fully...