Research Projects

Ongoing and completed projects spanning healthcare AI, precision agriculture, complex network theory, and language models.

Five pillars of AINET

🕸️

Complex Networks & Graph Learning

High-level data classification using network topology, community detection, structural optimization of networks, K-associated optimal graphs, PSO-guided network search, and multi-label classification via complex network measures.

🧠

Deep Learning & Neural Networks

CNN-LSTM hybrids for biomedical signals, Echo State Networks for EEG coma prognosis, transformers for spectroscopy data generation, and convolutional architectures for molecular pattern detection.

📊

Machine Learning

Support vector machines, random forests, high-level classification, unsupervised learning, dimensionality reduction with K-associated graphs, semantic role labeling, and ensemble methods.

🧬

Bio-Inspired Computing

Synchronous cellular automata for scheduling, bio-inspired network structural optimization, surrogate-assisted genetic algorithms for peptide discovery, and evolutionary computation for hospital management.

🤖

Foundation Models

Large language and foundation models, transfer learning, and generative approaches for spectral data synthesis and domain-specific fine-tuning.

Active Research Projects

All ongoing projects funded and running in the AINET laboratory.

Health · ASD Deep Learning International

AutoML for TEA Detection (international collaboration with Eindhoven/Radboud University)

Collaboration with TU/e (Eindhoven) and Radboud University (Netherlands). Developing an automated ML platform for detecting Autism Spectrum Disorder from saliva using ATR-FTIR spectroscopy with Fourier-transform infrared analysis. Targets AutoML configurations capable of optimizing pre-processing and classification pipelines for a variety of spectral data modalities.

Active · 2024–present CNPq · Google
LLMs FinTech NLP

LLM4Finance

Development of large language models fine-tuned and evaluated for the finance domain. The project investigates domain-specific pre-training strategies, evaluation benchmarks for financial NLP, and deployment-friendly architectures with reliability and explainability constraints.

Active · 2025–present Neospace AI
Deep Learning Spectroscopy EEG

Hybrid Network-Based Learning Architectures for Sequential Data Classification

Design of hybrid learning architectures for mono and multi-sequence classification using EEG and ATR-FTIR spectroscopy data. Focus on detecting patterns in FTIR and electromyography/electroencephalography data. Collaboration with Prof. Liang Zhao (USP) and Prof. Ran Cheng.

Active · 2023–present CNPq
Complex Networks ASD Diagnosis

Data Classification based on Complex Networks for Molecular Diagnosis of Autism Spectrum Disorder

High-level data classification in complex networks for molecular diagnosis of autism spectrum disorder (TEA) from salivary molecular properties analyzed via ATR-FTIR spectroscopy. Investigates structural and dynamic network properties to improve conventional classification methods.

Active · 2022–present CNPq
Deep Learning EEG · Coma

EEG Pattern Learning for Coma Prognosis

Network-based machine learning models for early prognosis of patients in deep coma states, using EEG data. Investigation of Echo State Networks, graph neural networks, and long short-term memory architectures for early prediction of outcomes, aiding organ donation decisions and clinical management.

Active · 2019–present CNPq
Agriculture Geospatial ML

AI for Agriculture & Geospatial Information

Machine learning for agricultural challenges: soybean maturity classification via high-throughput UAV RGB imaging and CNNs; eucalyptus growth and production modelling; coffee harvest time prediction with cellular automata; and general geospatial information processing for Brazilian biomes.

Active · 2019–present CNPq · Ministry of Agriculture

Past Research Projects

COVID-19 Complex Networks Completed

Network-Based Learning for the Salivary Molecular Diagnosis of COVID-19

Complex network-based deep learning models for rapid, non-invasive COVID-19 diagnosis from saliva samples processed via near-infrared spectroscopy. Two-time Google Latin America Research Award winner (2020 & 2022). In collaboration with Prof. Robinson Sabino-Silva and Ministry of Health (Brazil).

Completed · 2020–2026 FAPEMIG · Google · CNPq
COVID-19 Platform Completed

COVID-19 Technological Diagnostic Platform

Development of a scalable technological platform for COVID-19 diagnosis integrating ML-powered spectroscopic analysis, rapid testing workflows, and clinical decision support. Funded by the Brazilian Ministry of Health.

Completed · 2020–2026 Ministério da Saúde
Complex Networks Classification Completed

New Approaches for Data Classification and Clustering in Complex Networks

Investigation of methods and heuristics based on complex networks for data classification and clustering tasks. Develops approaches beyond traditional graph metrics — exploring the dynamic and structural properties of data for multi-label and multi-class scenarios.

Completed · 2019–2026 CNPq · Ministry of Agriculture
COVID-19 Completed

Oral Liberation Nanosystems for COVID-19 Prevention

Nanotechnology-based sustained-release oral liberation system for SARS-CoV-2 prevention. ML-based spectroscopic structure detection for early release triggering.

Completed · 2020–2022 CNPq
Data Mining Completed

Data Mining to Prevent Retention and Dropout at Federal University of Uberlândia

Identification of the main indicators contributing to student evasion and failure in UFU computing courses using data mining techniques. Resulted in institutional improvement actions and one registered software tool (SAGAPEP).

Completed · 2018–2020 PROSSIGA

Patents & Registered Software

Intellectual property resulting from AINET research.

PATENT
Photonic Method for Detecting Methanol in Distilled Beverages via ATR-FTIR Coupled with Machine Learning Algorithms
Khan, F.; Rangel, J.R.; Souza, P.D.S.; Martins, M.M.; Cunha, T.M.; Assis, D.C.; Carneiro, Murilo G.; Sabino-Silva, R. — INPI BR1020250220172, 2025.
PATENT
Salivary Detection of Chikungunya Virus Infection Based on Infrared Vibrational Modes Coupled with a Machine Learning Algorithm
Dias, J.C.V.E.; Sabino-Silva, R.; Guevara-Vega, M.; Rosa, R.B.; Caixeta, D.C.; Costa, M.A.; Souza, R.C.; Ferreira, G.M.; Mundim Filho, A.C.; Carneiro, Murilo G.; Jardim, A.C.G.; Martins, M.M.; Cunha, T.M. — INPI BR1020240248490, 2024.
PATENT
Salivary Detection of Hand-Foot-Mouth Disease Based on Infrared Vibrational Modes Coupled with an Artificial Intelligence Algorithm
Alves, D.C.T.; Jardim, A.C.G.; Santos, I.A.; Leite, F.S.; Souza, L.P.F.; Martins, M.M.; Cunha, T.M.; Silva, G.H.; Caixeta, D.C.; Guevara-Vega, M.; Carneiro, Murilo G.; Sabino-Silva, R. — INPI BR10202401042, 2024.
PATENT
Method for Detecting Arbovirus Infection Caused by Zika Virus Based on a Machine Learning Algorithm Applied to Infrared Spectra
Sabino-Silva, R.; Carneiro, Murilo G. — INPI BR1020230021263, 2023.
PATENT
Hepatitis Delta Detection Based on Infrared Vibrational Modes Coupled with an Artificial Intelligence Algorithm
Sabino-Silva, R.; Dias, J.C.V.E.; Costa, M.A.; Cunha, T.M.; Martins, M.M.; Souza, R.C.; Caixeta, D.C.; Guevara-Vega, M.; Santos, F.A.A.; Mundim Filho, A.C.; Goulart Filho, L.R.; Carneiro, Murilo G. — INPI BR10202302285, 2023.
PCT/WIPO
Spectral Profile System for Diagnosing COVID-19 — Method, System and Platform
Goulart Filho, L.R.; Galvão, L.M.P.; Martins, M.M.; Cunha, T.M.; Sousa, L.C.; Vaz, E.R.; Bastos, T.M.L.C.; Nossol, A.B.S.; Santos, A.R.; Bastos, L.M.; Santos, P.S.; Cunha, T.C.A.; Sabino-Silva, R.; Carneiro, Murilo G. — PCT WO/2021/237330, 2021. Registering institution: WIPO.
SOFTWARE
SAGAPEP (INPI BR512022002131-5, 2022)
Silva, E.A.D.; Palmeira, L.; Sabino-Silva, R.; Andrade, B.S.; Martins, L.G.A.; Carneiro, Murilo G. — Platform for surrogate-assisted genetic algorithm peptide discovery.