Comparación de modelos estadísticos en la estimación de indicadores de calidad de uvas tintas a partir de información espectral

  1. Noguera, Miguel 1
  2. Millan, Borja 1
  3. Aquino, Arturo 1
  4. Barragán, Antonio Javier 1
  5. Martínez Bohorquez, Miguel Ángel 1
  6. Andújar-Márquez, José Manuel 1
  1. 1 Universidad de Huelva
    info

    Universidad de Huelva

    Huelva, España

    ROR https://ror.org/03a1kt624

Liburua:
XLIII Jornadas de Automática: libro de actas: 7, 8 y 9 de septiembre de 2022, Logroño (La Rioja)
  1. Carlos Balaguer Bernaldo de Quirós (coord.)
  2. José Manuel Andújar Márquez (coord.)
  3. Ramon Costa Castelló (coord.)
  4. Carlos Ocampo Martínez (coord.)
  5. Jesús Fernández Lozano (coord.)
  6. Matilde Santos Peñas (coord.)
  7. José Enrique Simó Ten (coord.)
  8. Montserrat Gil Martínez (coord.)
  9. Jose Luis Calvo Rolle (coord.)
  10. Raúl Marín Prades (coord.)
  11. Eduardo Rocón de Lima (coord.)
  12. Elisabet Estévez Estévez (coord.)
  13. Pedro Jesús Cabrera Santana (coord.)
  14. David Muñoz de la Peña Sequedo (coord.)
  15. José Luis Guzmán Sánchez (coord.)
  16. José Luis Pitarch Pérez (coord.)
  17. Oscar Reinoso García (coord.)
  18. Oscar Déniz Suárez (coord.)
  19. Emilio Jiménez Macías (coord.)
  20. Vanesa Loureiro Vázquez (coord.)

Argitaletxea: Servizo de Publicacións ; Universidade da Coruña

ISBN: 978-84-9749-841-8

Argitalpen urtea: 2022

Orrialdeak: 568-574

Biltzarra: Jornadas de Automática (43. 2022. Logroño)

Mota: Biltzar ekarpena

DIALNET GOOGLE SCHOLAR lock_openRUC editor

Laburpena

The methods traditionally used for the determination of fruit quality status have a low spatial and temporal resolution due to their limitations (high cost and wide time gap between sampling and access to information). In the last decades, numerous research has informed about the potential of spectroscopy based methods for estimate plant biophysical parameters. In addition, the recent boom in the electronics industry has led to cheaper components, generating interest in the development of new devices. Encouraged by this context, this work presents a low-cost multispectral device based on a commercial sensor (AS7265x, AMS) sensitive to 18 bands between 410 and 940 nm. Aiming at the comparative evaluation of 3 non-parametric estimation models (two linear (Multiple Linear Regression and Partial Least Squares Regression) and one non-linear (Artificial Neural Networks) in the modelling of quality indicators of red grapes (total soluble solids and acidity). Among the models explored, the neural network proved to be the most effective in adjusting the relationship between the spectral information acquired with the proposed sensor and the quality indicators considered.

Datuen iturria: Dialnet