Alfalfa quality detection by means of VIS-NIR optical fiber reflection spectroscopy

  • C. R. Zamarreno
  • , A. Gracia-Moises
  • , I. Vitoria
  • , J. J. Imas
  • , L. Castano
  • , A. Avedillo
  • , Ignacio R. Matias

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A first approach study for the classification of alfalfa (medicago sativa) quality has been performed by means of VIS-NIR optical fiber reflection spectroscopy. Reflection spectral data has been obtained from alfalfa samples comprising six different qualities. Obtained data has been classified and organized to feed supervised self-learning algorithms. Neural networks have been used in order to differentiate the quality level of the samples. Obtained results permit to validate the proposed approach with 72% of the samples properly classified. In addition, proposed solution was implemented in a low cost automated detection prototype suitable to be used by non-qualified operators. Obtained equipment consist of a first step towards its utilization in quality monitoring and classification of many other products in the agri-food field.

Original languageEnglish
Title of host publication2022 IEEE Sensors, SENSORS 2022 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665484640
DOIs
Publication statusPublished - 2022
Externally publishedYes
Event2022 IEEE Sensors Conference, SENSORS 2022 - Dallas, United States
Duration: 30 Oct 20222 Nov 2022

Publication series

NameProceedings of IEEE Sensors
Volume2022-October
ISSN (Print)1930-0395
ISSN (Electronic)2168-9229

Conference

Conference2022 IEEE Sensors Conference, SENSORS 2022
Country/TerritoryUnited States
CityDallas
Period30/10/222/11/22

Keywords

  • alfalfa
  • neural networks
  • optical fiber
  • optical spectroscopy
  • reflection

Fingerprint

Dive into the research topics of 'Alfalfa quality detection by means of VIS-NIR optical fiber reflection spectroscopy'. Together they form a unique fingerprint.

Cite this