My research focuses on pattern recognition (machine and deep learning) and signal processing. The applications include different areas: electrical power systems, renewable energies, biomedical systems, industry, computer vision, embedded systems, industrial applications, virtual and intelligent sensing, precision agriculture, robotics, and theoretical aspects of machine learning and deep learning. Here, you can find some of the most relevant aspects (codes, datasets, resources, news, etc.) of the most relevant projects I have worked on.
Embedded Files
Electrical Power Systems
Lightning Overvoltage Monitoring:
Description: measurement and analysis of overvoltages in a power distribution network for detecting lightning-induced events.
Relevant Paper: link.
Nonintrusive Load Monitoring:
Waveform Analysis:
Description: detection and classification of events in power distribution systems using waveform analysis.
Relevant Paper: link.
High Impedance Fault Detection:
Description: a high impedance ground fault results when a primary conductor makes unwanted electrical contact with a road surface, sidewalk, sod, tree limb, or with some other surface, or object which restricts the flow of fault current to a level below that reliably detectable by conventional overcurrent devices.
Relevant Paper: link.
Codes: link.
Datasets: link.
Real dataset: link.
Renewable Energies
Biomedical Systems
sEMG Analysis:
Description: Gesture recognition by surface electromyography (sEMG) signals.
Relevant Paper: link.
EEG-FES-Force-MMG Closed-loop Control:
Computer Vision
Anomaly Detection:
Description: it uses a Convolutional Autoencoder in the anomaly detection context, by applying the reconstruction error of each frame as an anomaly score.
Relevant Paper: link.
Embedded Systems
freePMU:
Description: The FreePMU project delivers an open source Phasor Measurement Unit (PMU) for power system analysis based on the STM32F769 Discovery kit and an instrumentation PCB. Its characteristics are low cost, open architecture and open source code. FreePMU measures fundamental and harmonic synchrophasors as well as the signal frequency for a three-phase distribution circuit.
Relevant Paper: link.
Codes: link.
Smart Transformer:
Description: transformer for the electrical energy distribution network capable of automate network reconnection processes and include communication and remote monitoring functionalities.
Relevant information (in portuguese): link.
Safety Helmet Sensor:
Description: The device was designed to be attached to safety helmets and used by workers during maintenance on electrical networks. It is capable of immediately alerting the professional, through an audible warning, as soon as the minimum safety distance that must be maintained in energized regions is exceeded.
Relevant information (in portuguese): link.
Precision Agriculture
Smart Irrigation:
Description: Irrigation optimization in horticulture is highly relevant due to the high sensitivity of crops to water availability. Methods such as Reinforcement Learning (RL) and Rule-Based Systems (RBS) have been explored for automated irrigation; however, direct comparisons between these approaches for horticultural crops remain limited. This study compares RL and RBS for optimizing irrigation in lettuce cultivation using the AquaCrop-OSPy.
Relevant Paper: link.
Codes: link.
Industrial Informatics
High-Precision RFID Indoor Location:
Description: Object location in indoor environments is challenging when there is no physical contact, a field of view, reflective materials, and an excess of obstacles. Several works propose using Radio Frequency Identification technology (RFID) and machine learning methods to develop location systems in those situations. However, using an object as a target class slows learning and prediction in large-scale environments. To circumvent such problems, we proposed a location system that uses hierarchical classification.
Relevant Paper: link.
Codes: link.
Two-phase Flow Pattern Classification:
Description: Two-phase flow is a complex phenomenon present in several industrial applications, such as chemical reactors, power generation, and in the exploration, production, and transport of oil and natural gas. The classification of the flow pattern is a fundamental step in such applications, as it influences several derived parameters and sub-processes such as flow rate, void fraction, and pressure drop estimation.
Relevant Paper: link.
Codes: link.
Local Digital Twins:
Description: Cyber–Physical Production Systems usher in a new era of smart manufacturing, with Digital Twin being a pivotal concept driving their adoption. Most literature concentrates on global Digital Twin deployment, typically enterprise servers or the cloud. However, manufacturing relies on real-time control and decision-making, demanding swift system response. To address this, we introduce a novel Local Digital Twin architecture, bringing processing to the edge to meet strict timing constraints.
Relevant Paper: link.
Robotics
Edge Device to Detect Positioning Anomalies:
Description: Due to the great rise of robots globally, such equipment has become fundamental for achieving a manufacturing plant's daily productivity and quality goals. A failure or anomaly that may occur with a machine can lead to a major stoppage of the machine or even the production line. In this context, the study of prior detection of anomalies in robots becomes suitable for planned preventive maintenance, production continuity, and equipment longevity, which is the main objective of this work.
Relevant Paper: link.
Google Sites
Report abuse