Amanda Yumi

Doctoral candidate in Information Engineering

Universidade Federal do ABC

Biography

PhD candidate in Information Engineering at the Federal University of ABC (financial support: FAPESP, grants number 2019/17907-5). She has a degree in mathematics from the Institute of Mathematics and Statistics (2011). In her research, she works with Inferences of intercerebral connections using near-infrared spectroscopy (fNIRS) with machine learning.

Interests

Education
Hacking
Machine Learning
Neuroscience

Education

Licenciatura em Matemática, 2011

Universidade de São Paulo

Education

Last updated on Apr 28, 2022

Central de Comandos

Jogo para introduzir noções de lógica de programação. Desplugado, aberto, livre, colorido.

Featured Publications

Applications of graph theory to the analysis of fNIRS data in hyperscanning paradigms

This paper proposes the bootstrap modularity test as a way of determining whether a pair of brains is coactivated. The analysis of these metrics may provide further insights into the neurobiological underpinnings of interaction, such as in educational contexts.

Amanda Yumi, João Ricardo Sato

Applications of graph theory to the analysis of fNIRS data in hyperscanning paradigms

Applying functional near-infrared spectroscopy and eye-tracking in a naturalistic educational environment to investigate physiological aspects that underlie the cognitive effort of children during mental rotation tests

In this study, we evaluate the mental effort of children performing MRT tasks by measuring brain activation and pupil dilation. We use functional near-infrared spectroscopy (fNIRS) concurrently to collect brain hemodynamic responses from children’s prefrontal cortex (PFC) and an Eye-tracking system to measure pupil dilation during MRT.

Raimundo da Silva Soares Jr., Amanda Yumi, Candida S. F. Barreto, João Ricardo Sato

Applying functional near-infrared spectroscopy and eye-tracking in a naturalistic educational environment to investigate physiological aspects that underlie the cognitive effort of children during mental rotation tests

Predicting student performance using machine learning in fNIRS data

We collected data with fNIRS from the prefrontal cortex region (PFC) of 18 students while watching a video lecture. Random forests and penalized logistic regression classify correct answers as a function of oxyhemoglobin and deoxyhemoglobin concentration.

Amanda Yumi, João Ricardo Sato

Predicting student performance using machine learning in fNIRS data

Recent Publications

Filter publications.

Amanda Yumi, Cândida Barreto, João Ricardo Sato (2021). Iluminando o cérebro e rastreando o olhar. Rede Nacional de Ciência para Educação.

PDF Cite DOI

Amanda Yumi, Guilherme Augusto Zimeo Morais, Ana Paula Arantes Bueno, André Fujita, João Ricardo Sato (2019). Potential Confounders in the Analysis of Brazilian Adolescent's Health: A Combination of Machine Learning and Graph Theory. International Journal of Environmental Research and Public Health, 17(1).

PDF Cite DOI

Hacking

Last updated on Apr 19, 2022

Garoa Hacker Clube

Projects

Last updated on Apr 27, 2022

Graphs and hyperscanning fNIRS

Paper in progress: Hyperscanning is a promising tool for investigating the neurobiological underpinning of interaction and affective bonds. In this context, networks can identify brain functional mechanisms and regions involved during interactions.

Last updated on Apr 27, 2022

Predicting student performance using fNIRS data

Increasing student involvement in classes has always been a challenge for teachers and school managers. In online learning, some interactivity mechanisms like quizzes are increasingly used to engage students during classes and tasks.

Last updated on Apr 27, 2022

Potential cofounders in Public Health

By using a combination of gradient boosting machines and centrality hub metric, it was possible to identify potential confounders to be considered when conducting association analyses among variables.

Last updated on Apr 27, 2022