About
Currently, I am Ph.D. Candidate at Virginia Commonwealth University. My research relies on Data Streams, Imbalanced data and Active Learning.
Data Scientist & Machine Learning Engineer.
- Birthday: 12 November 1996
- Website: https://gabrieljaguiar.github.io/
- Phone: +1 804 610 0264
- City: Richmond, VA, USA
- Age: 27
- Degree: Ph.D. Candidate
- Email: aguiargj@vcu.edu
Resume
This is a brief description of my resume and skills. Here is a full version of my resume.
Education
Ph.D. in Computer Science
2021 - 2024
Virginia Commonwealth University, Richmond, VA, USA
Developing research on Data Stream and Online Learning.
M.Sc. in Computer Science
2018 - 2020
State University of Londrina, Londrina, Brazil
Conduced research on Meta-Learning and Digital Image Processing [Final dissertation]
Bachelor in Computer Science
2014 - 2017
State University of Londrina, Londrina, Brazil
Professional Experience
Research Assistant
2021 - Present
VCU @ Richmond, VA, USA
- Collaborated with a team of researchers to develop and implement cutting-edge algorithms and models for data stream analysis and online learning, with a focus on identifying and addressing challenges related to imbalanced data and semi-supervised learning.
Data Scientist Intern
2024
Microsoft Corp. @ Redmond, WA, USA
- Collaborated with the Network Device Health Team as a Data Scientists giving support for projects regarding anomaly detection.
Resident Researcher
2020 - 2021
SENAI @ Londrina, PR, Brazil
- Developed and deployed machine learning models for the Brazilian industry, leveraging advanced algorithms and techniques to optimize production processes and improve efficiency.
Publications
Journals
-
A comprehensive analysis of concept drift locality in data streams
[Suplementary material]
G.J. Aguiar, A. Cano; Knowledge-Based Systems, 2024. -
Dynamic budget allocation for sparsely labeled drifting data streams
G.J. Aguiar, A. Cano; Information Sciences, 2023. -
A survey on learning from imbalanced data streams: taxonomy, challenges, empirical study, and reproducible experimental framework
[Suplementary material]
G.J. Aguiar, B. Krawczyk, A. Cano; Machine Learning, 2023 -
Multiple voice disorders in the same individual: Investigating handcrafted features, multi-label classification algorithms, and base-learners
S. Barbon, R.C. Guido, G.J. Aguiar, E.J. Santana, M.L.P. Junior, H.A; Patil.Speech Communication, 2023 -
Using Meta-Learning for Multi-target Regression
G.J. Aguiar, E.J Santana, A.C.P.F.L. de Carvalho, S. Barbon; Information Sciences, 2022. -
A meta-learning approach for selecting image segmentation algorithm
G.J. Aguiar, R.G. Mantovani, S.M. Mastelini, A.C.P.F.L. de Carvalho, G.F.C. Campos, S. Barbon; Pattern Recognition Letters, 2019. -
Machine learning hyperparameter selection for Contrast Limited Adaptive Histogram Equalization
G.F.C. Campos, S.M. Mastelini, G.J. Aguiar, R.G. Mantovani, L.F. de Melo, S. Barbon; EURASIP Journal on Image and Video Processing, 2019.
Conferences
-
Enhancing Concept Drift Detection in Drifting and Imbalanced Data Streams through Meta-Learning
G.J. Aguiar, A. Cano; IEEE Conference on Big Data Workshops, 2023. -
An active learning budget-based oversampling approach for partially labeled multi-class imbalanced data streams
G.J. Aguiar, A. Cano; ACM/SIGAPP Symposium on Applied Computing, 2023. -
Towards meta-learning for multi-target regression problems
G.J. Aguiar, E.J. Santana, S.M. Mastelini, R.G. Mantovani, S. Barbon. Brazilian Conference on Intelligent Systems (BRACIS), 2019