My name is Morsinaldo Medeiros. I hold a Bachelor’s degree in Computer Science from the Federal Institute of Rio Grande do Norte (IFRN), where I graduated as class laureate, and a Bachelor’s degree in Computer Engineering from the Federal University of Rio Grande do Norte (UFRN). I have completed my Master’s degree in Electrical and Computer Engineering (PPgEEC/UFRN) and I am currently a Ph.D. student in the same graduate program.
I am a researcher affiliated with the Conect2AI Research Group, which focuses on artificial intelligence, embedded systems, and intelligent applications.
🌐 https://conect2ai.dca.ufrn.br/
📸 https://www.instagram.com/conect2ai/
💻 https://github.com/conect2ai
My research interests focus on embedded artificial intelligence, machine learning for vehicular systems, edge computing, and intelligent transportation systems. I work mainly with real-world sensor data (OBD-II, GPS, inertial sensors), lightweight and incremental learning algorithms, and the integration of Small Language Models (SLMs) with agents into constrained embedded environments.
-
Analysis of Language-Model-Powered Chatbots for Query Resolution in PDF-Based Automotive Manuals
Vehicles, MDPI, 2023.
This paper evaluates the use of language-model-based chatbots for querying automotive technical manuals in PDF format, comparing accuracy, usability, and practical deployment aspects.
https://www.mdpi.com/2624-8921/5/4/76 -
A Multi-Layered Methodology for Driver Behavior Analysis Using TinyML and Edge Computing
IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS), 2024.
Proposes a multi-layered edge-based methodology combining soft sensors, the TEDA framework, and incremental clustering for real-time driver behavior analysis using TinyML techniques.
https://ieeexplore.ieee.org/document/10570025 -
Evolving Online Clustering for Real-Time Driver Behavior Analysis in IoT-Enabled Vehicles
Evolving Systems, Springer, 2025.
Introduces an evolving online clustering approach for real-time driver behavior analysis using vehicular IoT data, focusing on adaptability and incremental learning.
https://link.springer.com/article/10.1007/s12530-025-09745-2 -
Anomaly Detection in Simulated Vehicle Dynamics Using BeamNG.tech and the TEDA Framework
Simpósio de Sistemas Veiculares (SSV), SBC, 2024.
Presents an integrated methodology combining the BeamNG.tech simulator and the TEDA framework to detect anomalies in vehicle speed data for driver behavior analysis.
https://sol.sbc.org.br/index.php/ssv/article/view/32625
-
🔭 I’m currently working as a researcher at UFRN, affiliated with the Conect2AI Research Group
-
🌱 I’m currently studying TinyML, Language Models, and Agents
-
👯 I’m open to collaboration on research and applied AI projects
-
💬 Ask me about Machine Learning, Data Science, Embedded AI, and Vehicular Systems
-
📫 How to reach me: morsinaldo.medeiros.075@ufrn.edu.br
