XLIV Simpósio Brasileiro de Telecomunicações e Processamento de Sinais

Indoor positioning is vital for many applications such as asset tracking, context-aware automation, and human-machine interaction, yet achieving sub-meter accuracy remains challenging. This paper proposes a sensor fusion approach that integrates Bluetooth Low Energy (BLE) and millimeter-wave (mmWave) radar to improve positioning performance. We show...

This work presents the development and validation of a low-cost national Internet of Things (IoT) collar for monitoring Puma concolor, Panthera onca, and Chrysocyon brachyurus. The solution acquires environmental, behavioral, and energy-related variables, with data transmission via LoRa (Long Range) to three gateways. Signal source estimation is based on...

Sistemas de radar de contrabateria operam em ambientes dinâmicos e incertos, nos quais a rápida identificação de ameaças é importante para a tomada de decisão. Nesse contexto, torna-se fundamental a classificação confiável de projéteis balísticos sob severas restrições computacionais. Este trabalho compara algoritmos clássicos de aprendizado de máquina e...

Semantic communication represents a paradigm shift from traditional bit-level to meaning-centric wireless communication. This paper introduces Knowledge-Enhanced Network (KE-Net) semantic communication, a novel framework that leverages external knowledge graphs (KGs) to improve semantic transmission accuracy over wireless channels. The proposed approach...

This paper proposes a lightweight architecture for speaker recognition and verification that combines Reservoir Computing (RC) with multi-scale and multi-head attention. A fixed recurrent reservoir models long-term temporal dynamics, while attention selectively aggregates speaker-discriminative information across temporal resolutions, restricting...

This study investigates the contribution of vocal tremor-related acoustic features to the automatic detection of Parkinson's disease (PD) from sustained vowel phonations. While most voice-based approaches rely on conventional perturbation and spectral descriptors, tremor-related parameters remain underexplored despite their physiological relevance to...

This paper introduces an interactive 3-D modular framework for optimizing Body Node Coordinator (BNC) placement and sensor transmission power in Wireless Body Area Networks (WBANs). Using meta-heuristic algorithms Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) to solves a multi-objective problem that maximizes connectivity and minimizes...

This work evaluates whether the Bluetooth Low Energy (BLE) Received Signal Strength Indicator (RSSI) alone can support human-action recognition (HAR) in a star-topology Wireless Body-Area Network (WBAN). Nine participants performed three activities (standing, walking, and sitting) while wearing a chest-mounted central node and four peripheral nodes on...

This paper investigates a YOLOv26 model for automated detection of radio signals in spectrogram representations. The proposed method formulates the problem as single-class object detection in the time--frequency domain, allowing the recognition of emissions in the RF spectrum. Raw IQ data from the CSRD2025 dataset are converted into spectrograms and used...

This work investigates the automatic classification of radio access technologies from spectrograms using the MobileNetV3-Small architecture. To address the large variability in image size, a spectrogram partitioning strategy is adopted to preserve relevant time-frequency patterns while enabling compatibility with the classifier input. In addition, the...