Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Food Science and Technology (Campinas) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0101-20612022000101301 |
Resumo: | Abstract In order to realize the rapid nondestructive detection of mildew peanut in the process of peanuts storage, hyperspectral imaging technology was proposed to detect mildew peanut. A total of 200 peanuts were selected from 5 kinds of peanuts purchased in the market for moldy treatment, and the remaining 400 peanuts were kept sterile. After completion, samples were collected with a hyperspectral instrument to obtain spectral data of the samples. According to the characteristics of the data, 10 pre-processing algorithms were used to de-noise the data, and Median Filtering (MF) had the best effect, with the recognition accuracy reaching 97.7%. GBDT, LightGBM, CatBoost and XGBoost algorithms were used to extract important feature bands in the spectral data pre-processed by MF. GBDT, LightGBM, CatBoost and XGBoost algorithms were used to model the extracted feature bands. The results showed that LightGBM is the best algorithm with a detection rate of 99.10%. Optuna algorithm was used to tune its parameters. Compared with the previous model, the running time of the optimized model was improved by about 0.25 s. The results showed that hyperspectral imaging provides an efficient and nondestructive method for detecting mildew in peanut storage. |
id |
SBCTA-1_963dadb7fc875fe5988633252a01ad17 |
---|---|
oai_identifier_str |
oai:scielo:S0101-20612022000101301 |
network_acronym_str |
SBCTA-1 |
network_name_str |
Food Science and Technology (Campinas) |
repository_id_str |
|
spelling |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithmhyperspectralmildewoptunaLightGBMAbstract In order to realize the rapid nondestructive detection of mildew peanut in the process of peanuts storage, hyperspectral imaging technology was proposed to detect mildew peanut. A total of 200 peanuts were selected from 5 kinds of peanuts purchased in the market for moldy treatment, and the remaining 400 peanuts were kept sterile. After completion, samples were collected with a hyperspectral instrument to obtain spectral data of the samples. According to the characteristics of the data, 10 pre-processing algorithms were used to de-noise the data, and Median Filtering (MF) had the best effect, with the recognition accuracy reaching 97.7%. GBDT, LightGBM, CatBoost and XGBoost algorithms were used to extract important feature bands in the spectral data pre-processed by MF. GBDT, LightGBM, CatBoost and XGBoost algorithms were used to model the extracted feature bands. The results showed that LightGBM is the best algorithm with a detection rate of 99.10%. Optuna algorithm was used to tune its parameters. Compared with the previous model, the running time of the optimized model was improved by about 0.25 s. The results showed that hyperspectral imaging provides an efficient and nondestructive method for detecting mildew in peanut storage.Sociedade Brasileira de Ciência e Tecnologia de Alimentos2022-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S0101-20612022000101301Food Science and Technology v.42 2022reponame:Food Science and Technology (Campinas)instname:Sociedade Brasileira de Ciência e Tecnologia de Alimentos (SBCTA)instacron:SBCTA10.1590/fst.71322info:eu-repo/semantics/openAccessZOU,ZhiyongCHEN,JieWANG,LiWU,WeijiaYU,TingjiangWANG,YuchaoZHAO,YongpengHUANG,PengLIU,BiZHOU,ManLIN,PingXU,Lijiaeng2022-08-30T00:00:00Zoai:scielo:S0101-20612022000101301Revistahttp://www.scielo.br/ctaONGhttps://old.scielo.br/oai/scielo-oai.php||revista@sbcta.org.br1678-457X0101-2061opendoar:2022-08-30T00:00Food Science and Technology (Campinas) - Sociedade Brasileira de Ciência e Tecnologia de Alimentos (SBCTA)false |
dc.title.none.fl_str_mv |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm |
title |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm |
spellingShingle |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm ZOU,Zhiyong hyperspectral mildew optuna LightGBM |
title_short |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm |
title_full |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm |
title_fullStr |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm |
title_full_unstemmed |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm |
title_sort |
Nondestructive detection of peanuts mildew based on hyperspectral image technology and machine learning algorithm |
author |
ZOU,Zhiyong |
author_facet |
ZOU,Zhiyong CHEN,Jie WANG,Li WU,Weijia YU,Tingjiang WANG,Yuchao ZHAO,Yongpeng HUANG,Peng LIU,Bi ZHOU,Man LIN,Ping XU,Lijia |
author_role |
author |
author2 |
CHEN,Jie WANG,Li WU,Weijia YU,Tingjiang WANG,Yuchao ZHAO,Yongpeng HUANG,Peng LIU,Bi ZHOU,Man LIN,Ping XU,Lijia |
author2_role |
author author author author author author author author author author author |
dc.contributor.author.fl_str_mv |
ZOU,Zhiyong CHEN,Jie WANG,Li WU,Weijia YU,Tingjiang WANG,Yuchao ZHAO,Yongpeng HUANG,Peng LIU,Bi ZHOU,Man LIN,Ping XU,Lijia |
dc.subject.por.fl_str_mv |
hyperspectral mildew optuna LightGBM |
topic |
hyperspectral mildew optuna LightGBM |
description |
Abstract In order to realize the rapid nondestructive detection of mildew peanut in the process of peanuts storage, hyperspectral imaging technology was proposed to detect mildew peanut. A total of 200 peanuts were selected from 5 kinds of peanuts purchased in the market for moldy treatment, and the remaining 400 peanuts were kept sterile. After completion, samples were collected with a hyperspectral instrument to obtain spectral data of the samples. According to the characteristics of the data, 10 pre-processing algorithms were used to de-noise the data, and Median Filtering (MF) had the best effect, with the recognition accuracy reaching 97.7%. GBDT, LightGBM, CatBoost and XGBoost algorithms were used to extract important feature bands in the spectral data pre-processed by MF. GBDT, LightGBM, CatBoost and XGBoost algorithms were used to model the extracted feature bands. The results showed that LightGBM is the best algorithm with a detection rate of 99.10%. Optuna algorithm was used to tune its parameters. Compared with the previous model, the running time of the optimized model was improved by about 0.25 s. The results showed that hyperspectral imaging provides an efficient and nondestructive method for detecting mildew in peanut storage. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-01-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0101-20612022000101301 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S0101-20612022000101301 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/fst.71322 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Sociedade Brasileira de Ciência e Tecnologia de Alimentos |
publisher.none.fl_str_mv |
Sociedade Brasileira de Ciência e Tecnologia de Alimentos |
dc.source.none.fl_str_mv |
Food Science and Technology v.42 2022 reponame:Food Science and Technology (Campinas) instname:Sociedade Brasileira de Ciência e Tecnologia de Alimentos (SBCTA) instacron:SBCTA |
instname_str |
Sociedade Brasileira de Ciência e Tecnologia de Alimentos (SBCTA) |
instacron_str |
SBCTA |
institution |
SBCTA |
reponame_str |
Food Science and Technology (Campinas) |
collection |
Food Science and Technology (Campinas) |
repository.name.fl_str_mv |
Food Science and Technology (Campinas) - Sociedade Brasileira de Ciência e Tecnologia de Alimentos (SBCTA) |
repository.mail.fl_str_mv |
||revista@sbcta.org.br |
_version_ |
1752126335109562368 |