Advanced search
Start date
Betweenand

Development of new methodologies and machine intelligence-based technological solutions for digital image segmentation and COVID-19 pandemic response

Abstract

This project comprises two distinct research branches: Digital Image Segmentation and Data-Driven Epidemiological Modeling against COVID-19. Our proposal aims at combining theoretical as well as technical advancements as a solution for different applications in the field of Computational Intelligence, whose previous results have been published in high-quality refereed publications such as IEEE CVPR, IEEE TIP and IEEE TPAMI. Considering the image segmentation topic, new concepts and clustering strategies for graphs derived from digital images will be investigated. Also, techniques inspired on spectral cutting and energy minimization rules will be studied, as well as deep learning strategies and graph differential operators in the image processing context, including eigenvalues and eigenfunctions, thus allowing us to design new methodologies and theoretical results. Concerning the Covid-19 research, this proposal extends the ongoing actions and researches now being carried out against the new coronavirus in Brazil, which range from digital inclusion of the Brazilian society to new studies of mathematical models for forecasting coronavirus-related data in the country. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
Articles published in other media outlets (0 total):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
AMARAL, FABIO; CASACA, WALLACE; OISHI, CASSIO M.; CUMINATO, JOSE A.. Simulating Immunization Campaigns and Vaccine Protection Against COVID-19 Pandemic in Brazil. IEEE ACCESS, v. 9, p. 126011-126022, . (21/03328-3, 13/07375-0)

Please report errors in scientific publications list by writing to: cdi@fapesp.br.