Rafael Orsi
← Home

Research projects

Applied research with scientific, educational and technological impact. Below is a summary of each project; the full project pages, with stages and details, are in Portuguese.

Featured research lineIn progress

Tacit knowledge and visual behavior

Eye tracking and computational modeling to turn implicit cognitive strategies into explicit representations.

Eye trackingMachine learningGraphsTime series

Partners: Centro Paula Souza · FEI · FMJ · ESEFJ

Additive manufacturing and computer visionIn contracting

Intelligent visual monitoring of the melt pool for trajectory correction in robotic wire-arc directed energy deposition

Computer vision and machine learning to recognize visual and temporal melt-pool patterns in wire-arc directed energy deposition (DED-Arc) of metals. The project builds an annotated dataset and reproducible models, and does not include closed-loop robot control.

FAPESP
Project funded by FAPESPRegular Innovation Grant (AIR) — Technological Initiation · Process 2026/27446-9 · 18 months, starting February 2027
Computer visionPattern recognitionMachine learningTime series

Partners: FAPESP · FATEC Zona Leste · Centro Paula Souza

Education and computer visionIn progress

Eye tracking and Irlen Syndrome

Recognition of visual patterns associated with reading discomfort and educational inclusion.

Eye trackingStatisticsAI

Partners: Centro Paula Souza · Faculdade de Medicina de Jundiaí

Digital healthIn progress

Visual perception of neonatal pain

Analysis of visual attention while assessing facial expressions of pain in newborns.

Eye trackingImage processingStatistics

Partners: Centro Universitário FEI · UNIFESP

Production systemsCompleted

Predictive supply management

Data science and artificial intelligence applied to forecasting and decision-making in supply management.

Machine learningPredictive modeling

Partners: Centro Paula Souza

Production systemsIn progress

MATIS — Multivariate Atmospheric Temperature Inference System

Machine learning framework that estimates monthly mean temperature from environmental and temporal variables, with an interactive simulator.

Machine learningMultivariate modelingFeature engineeringAblation analysisSpatial validationEnsemble learningPredictive inference

Partners: Centro Estadual de Educação Tecnológica Paula Souza — CEETEPS