Federal University of Ouro Preto · DECOM

Intelligent Systems Computing Laboratory

Pushing the frontiers of artificial intelligence, computer vision, machine learning and data science — from theory to real‑world application.

CSI Lab in Numbers

312+

Scientific Publications

13

Professors & Researchers

5

Industry Partnerships

50+

Alumni

01About the Lab

Innovation in Intelligent Systems at UFOP

CSI Lab is the Intelligent Systems Computing Laboratory at the Federal University of Ouro Preto (UFOP), affiliated with the Department of Computer Science (DECOM/ICEB).

Our mission is to advance artificial intelligence, machine learning, computer vision, pattern recognition and data science — combining academic excellence with practical applications of social and industrial impact.

  • Research with Real Impact

    We develop models and systems applied to healthcare, finance, environment and language — with publications in Springer, IEEE, SBC and ScienceDirect.

  • Academic and Industrial Partnerships

    We collaborate with companies such as EFI Bank, CGU, Embrapii and BDMG on R&D projects, transferring knowledge to society.

Meet the Team

CSI Lab members gathered in the lab, several wearing the group's T-shirt, at the end-of-year get-together.

16+ Years of Research

Encontro de Saberes UFOP 2023: a smiling CSI Lab student holds the trophy and the certificate for the best undergraduate research work in front of the event banner. ERCAS 2024: a CSI Lab student holds the best paper certificate from the IX Regional School of Computing Applied to Health.

02Research Themes

Areas of Expertise

From deep learning to biometric recognition — our research groups cover the main frontiers of intelligent computing.

  • Artificial Intelligence 

    AI models applied to high-complexity problems in healthcare, finance, language and environmental perception.

  • Computer Vision 

    Visual pattern recognition, image classification, deepfake detection and biometric identification.

  • Machine Learning 

    Deep neural networks, transfer learning, self-supervised learning and efficient architectures (NAS).

  • Natural Language Processing 

    Language models for Portuguese, toxic text classification, speech recognition and prompt optimization.

  • Data Science 

    Credit risk analysis, fraud detection, churn prediction and epidemiological time series.

  • Spatial & Epidemiological Analysis 

    Spatial cluster detection, COVID-19 modeling with GNN and urban mobility, epidemiological surveillance.

  • Biomedical Signals 

    ECG classification, arrhythmia detection, heartbeat segmentation and remote cardiac signals via video (rPPG).

  • Multi-Objective Optimization 

    Evolutionary algorithms, community detection in social networks and Pareto solution dispersion/concentration optimization.

Explore All Research Areas

03Scientific Output

Recent and Most-Cited Papers

Our work in international journals and conferences, synced weekly with Google Scholar.

Latest

  1. 2026Research on Biomedical Engineering

    A systematic review of ECG arrhythmia classification: embedded feasibility, adherence to standards, and fair evaluation (opens in a new tab)

    GAL Silva, PHL Silva, GJP Moreira, VLS Freitas, JC Gertrudes, EJS Luz

  2. 202618th ACM Web Science Conference

    Who Shapes Brazil’s Vaccine Debate? Semi-Supervised Modeling of Stance and Polarization in YouTube’s Media Ecosystem (opens in a new tab)

    GS de Oliveira, APC Silva, F Murai, CHG Ferreira

  3. 2026Applied Soft Computing

    Leveraging graph neural networks and mobility data for COVID-19 forecasting (opens in a new tab)

    FHO Duarte, GJP Moreira, EJS Luz, LBL Santos, VLS Freitas

  4. 2026Proceedings of the 18th ACM Web Science Conference

    Socio-Technical Constraints and Cross-Platform Model Generalization: Text Classification in Brazilian Public Security (opens in a new tab)

    S Rocha, CHV Silva, MJ da Silva, JT Neto, CHG Ferreira, GD Gonçalves

Most Cited

  1. 1,119 citations

    ECG-based heartbeat classification for arrhythmia detection: A survey (opens in a new tab)

    Computer methods and programs in biomedicine2016

  2. 606 citations

    COVID-ABS: An agent-based model of COVID-19 epidemic to simulate health and economic effects of social distancing interventions (opens in a new tab)

    Chaos, Solitons & Fractals2020

  3. 422 citations

    Towards an effective and efficient deep learning model for covid-19 patterns detection in x-ray images (opens in a new tab)

    Research on Biomedical Engineering2021

53 2015 2026
FIG. 03 Papers per year, 2015–20262026: year in progress

312 papers 6,164 citations

Google Scholar · updated October 19, 2026

View All Publications

04Updates

News & Events

Follow the lab's achievements, conference presentations and awards.

Conference

CSI Lab presents 3 papers at IEEE LACCI 2024

The lab was present at the IEEE Latin American Conference on Computational Intelligence with three works in spatial analysis, periocular biometrics and remote cardiac signals.

3 Accepted Papers
Award

Best Paper — ERCAS 2024

IX Regional School of Computing Applied to Health — best paper award given to a work advised by Prof. Eduardo Luz.

All News

05Technology Transfer

Consulting & R&D

Applied research projects with industrial and government partners.

  • EFI Bank

    AI for the Financial Sector

    Ongoing
  • CGU

    NLP Models for the Plataforma Brasil

  • Embrapii / Escola de Minas

    Industrial AI

  • BDMG

    Data Science for Credit

  • BDI

    Credit Risk

    In development
  • Embrapii - CIT/SENAI

    Development of an algorithm for the detection, classification, and proposal of corrections for defects in stamping processes

    Completed
  • SixPro

    Desenvolvimento de um sistema embarcado multicâmera e interface web para inspeção, detecção e classificação de pontos de solda em peças industriais utilizando Inteligência Artificial

    Completed

Explore Our R&D Projects

Interested in Joining CSI Lab?

We welcome undergraduate, master's and PhD students, and we seek partnerships with companies and public institutions. Tell us about your research interests.

Get in Touch