Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of <i>Brachiaria brizantha</i> Seed Vigor
Laser-induced breakdown spectroscopy (LIBS) associated with machine learning algorithms (ML) was used to evaluate the <i>Brachiaria</i> seed physiological quality by discriminating the high and low vigor seeds. A 2<sup>3</sup> factorial design was used to optimize the LIBS ex...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/22/14/5067 |
_version_ | 1797416067925016576 |
---|---|
author | Guilherme Cioccia Carla Pereira de Morais Diego Victor Babos Débora Marcondes Bastos Pereira Milori Charline Z. Alves Cícero Cena Gustavo Nicolodelli Bruno S. Marangoni |
author_facet | Guilherme Cioccia Carla Pereira de Morais Diego Victor Babos Débora Marcondes Bastos Pereira Milori Charline Z. Alves Cícero Cena Gustavo Nicolodelli Bruno S. Marangoni |
author_sort | Guilherme Cioccia |
collection | DOAJ |
description | Laser-induced breakdown spectroscopy (LIBS) associated with machine learning algorithms (ML) was used to evaluate the <i>Brachiaria</i> seed physiological quality by discriminating the high and low vigor seeds. A 2<sup>3</sup> factorial design was used to optimize the LIBS experimental parameters for spectral analysis. A total of 120 samples from two distinct cultivars of <i>Brachiaria brizantha</i> seeds exhibiting high vigor (HV) and low vigor (LV) in standard tests were studied. The raw LIBS spectra were normalized and submitted to outlier verification, previously to the reduction data dimensionality from principal component analysis. Supervised machine learning algorithm parameters were chosen by leave-one-out cross-validation in the test samples, and it was tested by external validation using a new set of data. The overall accuracy in external validation achieved 100% for HV and LV discrimination, regardless of the cultivar or the classification algorithm. |
first_indexed | 2024-03-09T05:58:25Z |
format | Article |
id | doaj.art-8c4c9a8eacbd4242a2317d01f368aad3 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-09T05:58:25Z |
publishDate | 2022-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-8c4c9a8eacbd4242a2317d01f368aad32023-12-03T12:11:50ZengMDPI AGSensors1424-82202022-07-012214506710.3390/s22145067Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of <i>Brachiaria brizantha</i> Seed VigorGuilherme Cioccia0Carla Pereira de Morais1Diego Victor Babos2Débora Marcondes Bastos Pereira Milori3Charline Z. Alves4Cícero Cena5Gustavo Nicolodelli6Bruno S. Marangoni7SISFOTON-UFMS—Laboratório de Óptica e Fotônica, UFMS—Universidade Federal de Mato Grosso do Sul, Campo Grande 79070-900, MS, BrazilEmbrapa Instrumentation, São Carlos 13560-970, SP, BrazilEmbrapa Instrumentation, São Carlos 13560-970, SP, BrazilEmbrapa Instrumentation, São Carlos 13560-970, SP, BrazilPrograma de Pós-Graduação em Agronomia, UFMS—Universidade Federal de Mato Grosso do Sul, Chapadao do Sul 79560-000, MS, BrazilSISFOTON-UFMS—Laboratório de Óptica e Fotônica, UFMS—Universidade Federal de Mato Grosso do Sul, Campo Grande 79070-900, MS, BrazilDepartamento de Física, Universidade Federal de Santa Catarina, Florianópolis 88020-302, SC, BrazilSISFOTON-UFMS—Laboratório de Óptica e Fotônica, UFMS—Universidade Federal de Mato Grosso do Sul, Campo Grande 79070-900, MS, BrazilLaser-induced breakdown spectroscopy (LIBS) associated with machine learning algorithms (ML) was used to evaluate the <i>Brachiaria</i> seed physiological quality by discriminating the high and low vigor seeds. A 2<sup>3</sup> factorial design was used to optimize the LIBS experimental parameters for spectral analysis. A total of 120 samples from two distinct cultivars of <i>Brachiaria brizantha</i> seeds exhibiting high vigor (HV) and low vigor (LV) in standard tests were studied. The raw LIBS spectra were normalized and submitted to outlier verification, previously to the reduction data dimensionality from principal component analysis. Supervised machine learning algorithm parameters were chosen by leave-one-out cross-validation in the test samples, and it was tested by external validation using a new set of data. The overall accuracy in external validation achieved 100% for HV and LV discrimination, regardless of the cultivar or the classification algorithm.https://www.mdpi.com/1424-8220/22/14/5067LIBSmachine learningdesign of experimentsdiscriminatingbrachiaria seed |
spellingShingle | Guilherme Cioccia Carla Pereira de Morais Diego Victor Babos Débora Marcondes Bastos Pereira Milori Charline Z. Alves Cícero Cena Gustavo Nicolodelli Bruno S. Marangoni Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of <i>Brachiaria brizantha</i> Seed Vigor Sensors LIBS machine learning design of experiments discriminating brachiaria seed |
title | Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of <i>Brachiaria brizantha</i> Seed Vigor |
title_full | Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of <i>Brachiaria brizantha</i> Seed Vigor |
title_fullStr | Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of <i>Brachiaria brizantha</i> Seed Vigor |
title_full_unstemmed | Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of <i>Brachiaria brizantha</i> Seed Vigor |
title_short | Laser-Induced Breakdown Spectroscopy Associated with the Design of Experiments and Machine Learning for Discrimination of <i>Brachiaria brizantha</i> Seed Vigor |
title_sort | laser induced breakdown spectroscopy associated with the design of experiments and machine learning for discrimination of i brachiaria brizantha i seed vigor |
topic | LIBS machine learning design of experiments discriminating brachiaria seed |
url | https://www.mdpi.com/1424-8220/22/14/5067 |
work_keys_str_mv | AT guilhermecioccia laserinducedbreakdownspectroscopyassociatedwiththedesignofexperimentsandmachinelearningfordiscriminationofibrachiariabrizanthaiseedvigor AT carlapereirademorais laserinducedbreakdownspectroscopyassociatedwiththedesignofexperimentsandmachinelearningfordiscriminationofibrachiariabrizanthaiseedvigor AT diegovictorbabos laserinducedbreakdownspectroscopyassociatedwiththedesignofexperimentsandmachinelearningfordiscriminationofibrachiariabrizanthaiseedvigor AT deboramarcondesbastospereiramilori laserinducedbreakdownspectroscopyassociatedwiththedesignofexperimentsandmachinelearningfordiscriminationofibrachiariabrizanthaiseedvigor AT charlinezalves laserinducedbreakdownspectroscopyassociatedwiththedesignofexperimentsandmachinelearningfordiscriminationofibrachiariabrizanthaiseedvigor AT cicerocena laserinducedbreakdownspectroscopyassociatedwiththedesignofexperimentsandmachinelearningfordiscriminationofibrachiariabrizanthaiseedvigor AT gustavonicolodelli laserinducedbreakdownspectroscopyassociatedwiththedesignofexperimentsandmachinelearningfordiscriminationofibrachiariabrizanthaiseedvigor AT brunosmarangoni laserinducedbreakdownspectroscopyassociatedwiththedesignofexperimentsandmachinelearningfordiscriminationofibrachiariabrizanthaiseedvigor |