Advanced search
Start date
Betweenand

Analysis of the Dynamic Behavior of Complex Systems and Artificial Neural Networks in Computer Vision and Artificial Intelligence

Grant number: 22/03668-1
Support Opportunities:Scholarships in Brazil - Doctorate
Effective date (Start): December 01, 2022
Effective date (End): June 30, 2025
Field of knowledge:Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
Principal Investigator:Odemir Martinez Bruno
Grantee:Kallil Miguel Caparroz Zielinski
Host Institution: Instituto de Física de São Carlos (IFSC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
Associated research grant:18/22214-6 - Towards a convergence of technologies: from sensing and biosensing to information visualization and machine learning for data analysis in clinical diagnosis, AP.TEM

Abstract

Complex networks are a field of study which combines graph theory and methods from statistical mechanics to represent complex systems. In the area of machine learning, networks have been widely discussed in the literature in computer vision and artificial intelligence tasks, proving to be a tool with great potential for the area in recent years. Recent studies, mostly by researchers from USP in São Carlos, demonstrate that, when combined with cellular automata or artificial neural networks for data classification tasks, complex networks demonstrate great harmony in the integration of methods. However, despite the excellent results obtained, there is still much to be explored in this field of research. Therefore, the objective of this doctorate is to implement, evaluate and propose new methods that integrate the areas of complex networks for computer vision and artificial intelligence problems. Neural network models will be investigated for texture classification, and new architectures will be proposed that can deal with complex networks modeled from images. In addition, current techniques that integrate the areas of complex networks and automata in pattern recognition tasks will be tested on various types of data, such as images, videos, text and structured data. Finally, models that integrate the three areas of study will be approached and proposed. As a way of analyzing the potential of the methods, applications will be considered in data representing real problems, such as biology, medicine and agriculture, areas in which the candidate's research group has partnerships with national and international laboratories, and mainly data from sensors and biosensors in together with collaborators of the thematic project (2018/22214-6) in which this doctorate is inserted.

News published in Agência FAPESP Newsletter about the scholarship:
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)
SCABINI, LEONARDO; ZIELINSKI, KALLIL M.; RIBAS, LUCAS C.; GONCALVES, WESLEY N.; DE BAETS, BERNARD; BRUNO, ODEMIR M.. RADAM: Texture recognition through randomized aggregated encoding of deep activation maps. PATTERN RECOGNITION, v. 143, p. 13-pg., . (22/03668-1, 21/09163-6, 18/22214-6, 21/07289-2, 21/08325-2, 19/07811-0)

Please report errors in scientific publications list using this form.