Disseminating the use of artificial intelligence to solve problems in optics and photonics

• Grant number: 21/01136-0
• Support Opportunities: Scholarships in Brazil - Post-Doctoral
• Start date: March 01, 2021
• End date: February 28, 2023
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Jarbas Caiado de Castro Neto
• Grantee: Renato Feijó Evangelista
• Host Institution: Instituto de Física de São Carlos (IFSC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 13/07276-1 - CEPOF - Optics and Photonic Research Center, AP.CEPID

Abstract

The Center for Research in Optics and Photonics (CEPOF), based in the Institute of Physics of São Carlos (IFSC-USP), investigates innovative aspects through projects founded on the interaction between light and matter. The CEPOF develops research in several areas such as Atomic and Molecular Physics, Biophotonics and Plasmonics, always focused on promoting technological advances and broadening the collaboration with companies. Over years, a large volume of data has been collected and explored using the available statistical and computational tools. However, the accelerated advancements in the computational processing have enabled the application of Data Science and Machine Learning to perform more sophisticated analyzes and to develop robust models with extraordinary potential for simulating complex phenomena within a reasonable amount of time. Moreover, real-time data processing has become feasible with the advent of Artificial Intelligence, creating new application possibilities for technologies developed at the center. In this context, this project pursues not only the investigation of potential improvements to the currently used computational methods, but also to disseminate the practice of applying intelligent algorithms to assist in the research. Initially, two lines of research might benefit from this project; a) in Ophthalmology, focused on the development of a computer vision system capable of detecting subclinical keratoconus based on Zernike polynomials and images of Placido and Scheimpflug tomography; b) in Agriculture, focused on the development of a specialized system for Precision Agriculture that is capable of classifying soybean plants in real time based on multispectral images. Among the expected results are the induction of models with practical applications using machine learning algorithms and the dissemination of concepts from the area to the center's research groups, in order to complement the experience and academic training of students and researchers. (AU)