Research

Scientific publications

Peer-reviewed research in artificial intelligence and machine learning, published in Brazilian journals and conferences.

Nationally awarded

ENIAC 2021 · Brazilian National Meeting on Artificial and Computational Intelligence

Thompson Sampling in Heuristic Selection for the Quadratic Assignment Problem

Carlos Daniel Pohlod, Sandra M. Venske, Carolina P. Almeida

Award-winning paper and project at ENIAC, the main Brazilian conference on artificial and computational intelligence. Applies Thompson Sampling as a bandit-based strategy to select heuristics for the Quadratic Assignment Problem, a classic NP-hard combinatorial optimization problem.

Reinforcement learningCombinatorial optimizationMetaheuristics

Read the paper

Journal article

Revista Brasileira de Computação Aplicada (RBCA)

Detection and counting of plants via deep learning using images collected by RPA

Deep learning pipeline to detect and count plants in aerial images captured by remotely piloted aircraft, supporting precision agriculture workflows.

Deep learningComputer visionPrecision agriculture

Read the paper

Journal article

Cadernos de Ciência & Tecnologia · Embrapa, 2022

Mapeamento sistemático de detecção e contagem de plantas em imagens agrícolas usando aprendizagem de máquina

Systematic mapping of machine learning approaches for plant detection and counting in agricultural imagery, with a proposed modeling for a production-ready system. Published with Embrapa, the Brazilian Agricultural Research Corporation.

Machine learningSystematic mappingAgriculture

Read the paper