Marcelo Ribeiro

Marcelo Ribeiro


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2023 in IEEE Latin America Transactions
Verified
Journal Article
Closed access
Alejandro da Silva PereiraAlejandro da Silva Pereira
Alejandro da Silva Pereira
Carlos Alexandre Silva dos SantosCarlos Alexandre Silva dos Santos
Carlos Alexandre Silva dos Santos
Marilton de AguiarMarilton de Aguiar
Marilton de Aguiar
DWDaniel Welfer
Daniel Welfer
MDMarcelo Da Silva Dias
Marcelo Da Silva Dias
MRMarcelo Ribeiro
Marcelo Ribeiro
Diabetes affects millions of people worldwide, and diabetic retinopathy is a complication of diabetes. Brazil is the sixth in the world in the incidence of diabetes and has the highest numbers in Latin America with 15.7 million adults affected by this condition. Typically diabetic retinopathy is identified by lesions such as hard and soft exudates, microaneurysms, and vitreous hemorrhages. Early diagnosis of these lesions is essential to prevent the progression of the disease to severe stages and the consequent loss of vision. As the disease diagnosis is based on image analysis, it is possible to use deep learning models to detect artifacts in the retina. This article proposes a new method that uses a YOLOR-CSP architecture combined with the Slicing Aided Hyper Inference framework to detect fundus lesions. The proposed method was trained, adjusted, and evaluated using the DDR dataset, obtaining a mAP equal to 38.08%. The proposed method achieved values of AP equal to 40.90%, 46.60%, 26.10%, and 38.70% for hard exudates, soft exudates, microaneurysms, and vitreous hemorrhages, respectively, surpassing similar studies found in the literature.


5 October 2026
Verified
Conference Paper
Open access
PDF file
LALui Gill Aquini
Lui Gill Aquini
MRMarcelo Ribeiro
Marcelo Ribeiro
MDMarcelo da Silva Dias
Marcelo da Silva Dias
LJLaura Quevedo Jurgina
Laura Quevedo Jurgina
Marilton de AguiarMarilton de Aguiar
Marilton de Aguiar
LJLeomar Soares da Rosa Junior
Leomar Soares da Rosa Junior
Este artigo apresenta um sistema tutor inteligente de baixo custo baseado em Retrieval-Augmented Generation para o ensino e a preservação da memória histórica e cultural de um município do Rio Grande do Sul, cujo conhecimento local corre risco de dissipação. O corpus de recuperação é composto por obras de referência sobre a história local. A avaliação abrangeu a qualidade da geração, por um especialista de domínio e por LLM as a Judge, e a qualidade da recuperação, pela análise dos trechos top-k e por um teste de verificação factual com informações incorretas. Conjuntamente, tais métodos evidenciam o potencial da referida abordagem para a mediação tecnológica da memória coletiva em contextos educacionais e culturais.