Aurélio Ribeiro Costa

Aurélio Ribeiro Costa

Auto-generated profile, based on publicly available information

Aurélio Ribeiro Costa

Exact Science Institute, University of Braslia,Computer Science Department,Brazil

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
20 December 2022 in Knowledge-Based Systems
Verified
Journal Article
Closed access
ACAurélio Ribeiro Costa
Aurélio Ribeiro Costa
CRCélia Ghedini Ralha
Célia Ghedini Ralha

12 May 2021
Verified
Book Chapter
Closed access
PDF file
NRNatan de Souza Rodrigues
Natan de Souza Rodrigues
ACAurelio Ribeiro Costa
Aurelio Ribeiro Costa
LLLucas Correa Lemos
Lucas Correa Lemos
CRCélia Ghedini Ralha
Célia Ghedini Ralha

26 May 2015
Verified
Conference Paper
Open access
PDF file
ACAurélio Costa
Aurélio Costa
CRCélia Ralha
Célia Ralha
O desempenho de um programa de pós-graduação é aferido pela CAPES, em parte pelo seu nível de publicação, para tanto, faz-se necessário que a gestão do programa seja feita de forma a maximizar a qualidade das publicações que são realizadas pelos pesquisadores associados. No contexto dos relacionamentos de coautoria em publicações, a análise de rede de colaboração científica se mostra uma ferramenta adequada para avaliar as parcerias já formadas, bem como para estimular a formação de novas parcerias. Neste artigo é apresentada uma ferramenta de análise de rede aplicada à gestão de um programa de pós-graduação de uma Universidade Federal. Os dados coletados do programa foram modelados em um banco NoSQL orientado a grafo, incluindo todas as publicações dos docentes vinculados. Ressaltamos a utilidade ao gestor do programa, bem como aos demais pesquisadores, do módulo de recomendação de parcerias. O desenvolvimento da pesquisa utilizou a metodologia Design Science Research para guiar tanto a construção do artefato quanto para elaborar a documentação associada. Preliminarmente, utilizando dados de um programa de pós-graduação, pode-se perceber o potencial de recomendação de novas parcerias de co-autoria na rede de colaboração previamente formada.

5 December 2023
Verified
Conference Paper
Closed access
RLRafael Henrique Nogalha De Lima
Rafael Henrique Nogalha De Lima
ACAurélio Ribeiro Costa
Aurélio Ribeiro Costa
TFThiago De Paulo Faleiros
Thiago De Paulo Faleiros
CRCélia Ghedini Ralha
Célia Ghedini Ralha
This article conducts an ablation study of the Actor-Critic Architecture for Community Detection (AC2CD). The AC2CD uses Deep Reinforcement Learning (DRL) and Graph Attention Networks (GAT). Our ablation study method adheres to the principles of explainable artificial intelligence, focusing on assessing performance factors, including execution time, memory usage, and GPU utilization. We carried out experiments using two real-world datasets: Email-Eu-Core (EC), an email network among members of a European research institution (comprising 1,005 nodes, 25,571 edges, and 42 communities) available through the Stanford Snap Project, and a High School contact and friendship network (HS) in Marseilles, France, from December 2013 (comprising 329 nodes, 45,047 edges, and nine communities), obtainable from the Socio Patterns Website. We evaluated performance while considering three hyperparameters: learn_rate (LR), batch_size (BS), and n_games (NG), varying them at 10%, 30%, 50%, and 70%. The LR of 70% yielded optimal results with execution time for both EC and HS datasets. Furthermore, a BS of 70% indicated an ideal balance between execution time, GPU usage, and memory consumption for the HS dataset.

6 May 2021 in Research Square
Verified
Preprint
Open access
PDF file
ACAurélio Ribeiro Costa
Aurélio Ribeiro Costa
VNVanessa Tavares Nunes
Vanessa Tavares Nunes
CRCélia Ghedini Ralha
Célia Ghedini Ralha
Scientific collaboration networks can present different views of researchers’ interaction. The analysis of these networks allows research transparency focusing on the understanding of how science evolves in different contexts. In this article, we present a scientific collaboration network analysis using social network metrics as average degree, connected components, betweenness and closeness centralities applied to five Brazilian Computer Science graduate programs. An online artifact built upon the design science research paradigm, namely SCI-synergy, was developed to ease the analysis involving publication data available on the Digital Bibliography & Library Project (DBLP) from the graduate program members allied to the Federal University of Minas Gerais (UFMG), the State University of São Paulo (USP), the Federal University of Rio Grande do Norte (UFRN), the Federal University of Amazonas (UFAM), and the University of Brasília (UnB). The objective is to analyze the scientific collaboration network of each program focusing on the researchers’ collaboration to understand patterns considering intra- and inter-program relationships. The analysis covers two database updates of 2019 and 2021. Results show that intra-program relationships are not always bigger among the highest-ranked programs in CAPES. Nevertheless, UFMG presents a greater total of cooperation among the five programs indicating research leadership and good inter-program collaboration patterns. We advocate that the collaboration network analysis using an online artifact can be useful to understand patterns of all the Brazilian Computer Science graduate programs to discover new research perspectives to be improved, avoided or even applied to other contexts.