Emerging non-destructive technologies for indirect assessment and prediction of the physical and physicalchemical quality of corn grains as an alternative to physical classification

Abstract

Corn is a cereal of significant socio-economic importance, essential for food security and various industrial sectors. The increase in production and the growing demand for quality require technologies capable of ensuring greater efficiency and precision in grain assessment. Traditionally, visual classification, although regulated, presents limitations due to subjectivity, time consumption, and the difficulty of consistently capturing physicochemical parameters that determine quality. This study, divided into three chapters, proposes an integrated approach by analyze the use of non-destructive technologies and machine learning models for the rapid and precise indirect assessment of corn grain quality from flint and hard groups, as a complementary method to traditional physical classificati