| |
|
|
|
Registro Completo |
|
Biblioteca(s): |
Embrapa Mandioca e Fruticultura. |
|
Data corrente: |
08/10/2008 |
|
Data da última atualização: |
19/02/2009 |
|
Tipo da produção científica: |
Resumo em Anais de Congresso |
|
Autoria: |
FUKUDA, W.; SANTOS, V.; OLIVEIRA, L.; PEREIRA, M.; CEBALLOS, H.; NUTTI, M.; CARVALHO, J.; DITA, MIGUEL. |
|
Afiliação: |
Wania Maria Gonçalves Fukuda, CNPMF; Vanderlei da Silva Santos, CNPMF; Luciana Alves de Oliveira, CNPMF; Marcio Eduardo Canto Pereira, CNPMF; Hernan Ceballos, CIAT; Marilia Nutti, CTAA; José Carvalho, CTAA; Miguel Angel Dita, CNPMF. |
|
Título: |
Breeding cassava for enhancement of carotenoid, iron and zinc contents. |
|
Ano de publicação: |
2008 |
|
Fonte/Imprenta: |
In: SCIENTIFIC MEETING OF THE GLOBAL CASSAVA PARTNERSHIP, 1., 2008, Ghent. Cassava: meeting the challenges of the new millennium.Ghent:: IPBO, 2008. p. 106. |
|
Idioma: |
Inglês |
|
Notas: |
S7-9. |
|
Conteúdo: |
The goal of this project is to improve the nutritional quality of cassava varieties for provitamin A, Fe and Zn contents, in the HarvestPlus program. Initialy, a total of 1800 cassava accessions from the germplasm bank at Embrapa Cassava & Tropical Fruits, were screened. Total carotenoid content in one-year old roots of the 72 landraces selected ranged from 0.63 to 15.51 ug.g-1 (fresh weight). It was observed that accessions with higher total carotenoid contents also presented elevated HCN levels. Based on, the low cyanogenic potential required for cassava consumption as boiled roots (where carotenoid retention is higher), 7 landraces with total carotenoid concentrations ranging from 1.50 to 4.49 ug.g-¹ were selected as parents. In the first generation (228 genotypes), hybrids with total carotenoid increment of more than 100% in relation to the parents were identified. Total carotenoid levels in the population ranged from 0.87 to 10.47 ug.g-¹. Analyses of beta-carotenes revealed an approximated, but not linear relation with the total carotenoid contents. In the second generation (136 hybrids) additional increment of total carotenoid contents with respect to the first was verified, reaching the maxim concentration of 12.41 ug.g-¹. Regarding Fe and Zn contens, the 72 yellow landraces initially selected as well as all the hybrids of two generations were evaluated by atomic absorption. Keeping low HCN and hight and high total carotenoid concentrations as priority, hybrids with more than 10 ug.g-¹ of total carotenoids and high levels of Zn and Fe were selected. These hybrids are currently under agronomical evaluations to be recommended as varieties. MenosThe goal of this project is to improve the nutritional quality of cassava varieties for provitamin A, Fe and Zn contents, in the HarvestPlus program. Initialy, a total of 1800 cassava accessions from the germplasm bank at Embrapa Cassava & Tropical Fruits, were screened. Total carotenoid content in one-year old roots of the 72 landraces selected ranged from 0.63 to 15.51 ug.g-1 (fresh weight). It was observed that accessions with higher total carotenoid contents also presented elevated HCN levels. Based on, the low cyanogenic potential required for cassava consumption as boiled roots (where carotenoid retention is higher), 7 landraces with total carotenoid concentrations ranging from 1.50 to 4.49 ug.g-¹ were selected as parents. In the first generation (228 genotypes), hybrids with total carotenoid increment of more than 100% in relation to the parents were identified. Total carotenoid levels in the population ranged from 0.87 to 10.47 ug.g-¹. Analyses of beta-carotenes revealed an approximated, but not linear relation with the total carotenoid contents. In the second generation (136 hybrids) additional increment of total carotenoid contents with respect to the first was verified, reaching the maxim concentration of 12.41 ug.g-¹. Regarding Fe and Zn contens, the 72 yellow landraces initially selected as well as all the hybrids of two generations were evaluated by atomic absorption. Keeping low HCN and hight and high total carotenoid concentrations as priority, hybrids with ... Mostrar Tudo |
|
Categoria do assunto: |
-- |
|
Marc: |
LEADER 02345naa a2200217 a 4500
001 1637542
005 2009-02-19
008 2008 bl uuuu u00u1 u #d
100 1 $aFUKUDA, W.
245 $aBreeding cassava for enhancement of carotenoid, iron and zinc contents.
260 $c2008
500 $aS7-9.
520 $aThe goal of this project is to improve the nutritional quality of cassava varieties for provitamin A, Fe and Zn contents, in the HarvestPlus program. Initialy, a total of 1800 cassava accessions from the germplasm bank at Embrapa Cassava & Tropical Fruits, were screened. Total carotenoid content in one-year old roots of the 72 landraces selected ranged from 0.63 to 15.51 ug.g-1 (fresh weight). It was observed that accessions with higher total carotenoid contents also presented elevated HCN levels. Based on, the low cyanogenic potential required for cassava consumption as boiled roots (where carotenoid retention is higher), 7 landraces with total carotenoid concentrations ranging from 1.50 to 4.49 ug.g-¹ were selected as parents. In the first generation (228 genotypes), hybrids with total carotenoid increment of more than 100% in relation to the parents were identified. Total carotenoid levels in the population ranged from 0.87 to 10.47 ug.g-¹. Analyses of beta-carotenes revealed an approximated, but not linear relation with the total carotenoid contents. In the second generation (136 hybrids) additional increment of total carotenoid contents with respect to the first was verified, reaching the maxim concentration of 12.41 ug.g-¹. Regarding Fe and Zn contens, the 72 yellow landraces initially selected as well as all the hybrids of two generations were evaluated by atomic absorption. Keeping low HCN and hight and high total carotenoid concentrations as priority, hybrids with more than 10 ug.g-¹ of total carotenoids and high levels of Zn and Fe were selected. These hybrids are currently under agronomical evaluations to be recommended as varieties.
700 1 $aSANTOS, V.
700 1 $aOLIVEIRA, L.
700 1 $aPEREIRA, M.
700 1 $aCEBALLOS, H.
700 1 $aNUTTI, M.
700 1 $aCARVALHO, J.
700 1 $aDITA, MIGUEL.
773 $tIn: SCIENTIFIC MEETING OF THE GLOBAL CASSAVA PARTNERSHIP, 1., 2008, Ghent. Cassava: meeting the challenges of the new millennium.Ghent:: IPBO, 2008. p. 106.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Mandioca e Fruticultura (CNPMF) |
|
|
Nenhum exemplar cadastrado para este documento. |
Voltar
|
|
|
 | Acesso ao texto completo restrito à biblioteca da Embrapa Instrumentação. Para informações adicionais entre em contato com cnpdia.biblioteca@embrapa.br. |
Registro Completo
|
Biblioteca(s): |
Embrapa Instrumentação. |
|
Data corrente: |
24/05/2022 |
|
Data da última atualização: |
23/01/2024 |
|
Tipo da produção científica: |
Artigo em Periódico Indexado |
|
Circulação/Nível: |
A - 2 |
|
Autoria: |
OSCO, L. P.; FURUYA, D. E. G.; FURUYA, M. T. G.; CORRÊA, D. V.; GONÇALVEZ, W. N.; MARCATO JUNIOR, J.; BORGES, M.; BLASSIOLI-MORAES, M. C.; MICHEREFF, M. F. F.; AQUUINO, M. F. S.; LAUMANN, R. A.; LISENBERG, V.; RAMOS, A. P. M.; JORGE, L. A. de C. |
|
Afiliação: |
MIGUEL BORGES, Cenargen; MARIA CAROLINA BLASSIOLI MORAES, Cenargen; RAUL ALBERTO LAUMANN, Cenargen; LUCIO ANDRE DE CASTRO JORGE, CNPDIA. |
|
Título: |
An impact analysis of pre-processing techniques in spectroscopy data to classify insect-damaged in soybean plants with machine and deep learning methods. |
|
Ano de publicação: |
2022 |
|
Fonte/Imprenta: |
Infrared Physics & Technology, v. 123, 104203, 2022. |
|
Páginas: |
13 p. |
|
ISSN: |
1350-4495 |
|
DOI: |
10.1016/j.infrared.2022.104203 |
|
Idioma: |
Inglês |
|
Conteúdo: |
Spectroscopy is essential to understand a series of phenomena in multiple fields of study. In remote sensing, vegetation analysis is one of the most prominent fields to explore, aiming to improve a specific task. As a task, modeling insect damage in the plants is essential to establish the correct management of agricultural farmlands. Hyperspectral data, which can be acquired with field spectroscopy at plant or leaf level, is a non-direct, rapid, and trustworthy approach to indicate its health. However, the spectral redundancy inherent is a challenge for the information extraction process, making the pre-processing phase an essential part of the analysis. Currently, artificial intelligence techniques, mostly based on machine and deep learning methods, are a standard application in data processing, being pre-processing techniques an essential part of it. But few studies aimed to measure the impact of such processes in vegetation monitoring, specifically with insect damage and spectral data. Here, we provide an analysis of the impact of pre-processing techniques on machine learning algorithms’ performance over said classification task. For this, we used a field spectroradiometer that operates within the 350–1,000 nm and 1,000–2,500 nm ranges. The dataset was composed of multiple spectral measurements that took place on different days in a controlled environment with soybean plants. As pre-processing techniques, methods like baseline removal, smoothing, first and second-order derivatives, standard normal variate (SNV), multiplicative scatter correction (MSC), and principal components analysis (PCA) were investigated. Several machine learning algorithms and one deep learning method were applied to model the datasets. The impact of the pre-processing techniques was measured within validation metrics relate to its accuracy. Our results indicated that the Extra-Tree (ExT) algorithm was better, mainly when first-order derivative data were extracted from the dataset (accuracy equal to 93.68%). A ranking approach indicated that the most contributive spectral region situates at the near-infrared, between 784 and 911 nm. Our investigation also demonstrates that a deep neural network (DNN) did not return a satisfactory result over raw reflectance data. However, when considering a combination of PCA over the 2nd derivative data, it achieved similar results to the ExT algorithm (accuracy of 91.95%). The implications of such, alongside the ranking approach, are discussed in this paper. We hope that the information presented here serves as a framework for future research when applying pre-processing techniques alongside the machine and deep learning methods over spectral data. MenosSpectroscopy is essential to understand a series of phenomena in multiple fields of study. In remote sensing, vegetation analysis is one of the most prominent fields to explore, aiming to improve a specific task. As a task, modeling insect damage in the plants is essential to establish the correct management of agricultural farmlands. Hyperspectral data, which can be acquired with field spectroscopy at plant or leaf level, is a non-direct, rapid, and trustworthy approach to indicate its health. However, the spectral redundancy inherent is a challenge for the information extraction process, making the pre-processing phase an essential part of the analysis. Currently, artificial intelligence techniques, mostly based on machine and deep learning methods, are a standard application in data processing, being pre-processing techniques an essential part of it. But few studies aimed to measure the impact of such processes in vegetation monitoring, specifically with insect damage and spectral data. Here, we provide an analysis of the impact of pre-processing techniques on machine learning algorithms’ performance over said classification task. For this, we used a field spectroradiometer that operates within the 350–1,000 nm and 1,000–2,500 nm ranges. The dataset was composed of multiple spectral measurements that took place on different days in a controlled environment with soybean plants. As pre-processing techniques, methods like baseline removal, smoothing, first and second-order d... Mostrar Tudo |
|
Palavras-Chave: |
DNN; Field spectroscopy. |
|
Categoria do assunto: |
-- |
|
Marc: |
LEADER 03727naa a2200337 a 4500
001 2143404
005 2024-01-23
008 2022 bl uuuu u00u1 u #d
022 $a1350-4495
024 7 $a10.1016/j.infrared.2022.104203$2DOI
100 1 $aOSCO, L. P.
245 $aAn impact analysis of pre-processing techniques in spectroscopy data to classify insect-damaged in soybean plants with machine and deep learning methods.
260 $c2022
300 $a13 p.
520 $aSpectroscopy is essential to understand a series of phenomena in multiple fields of study. In remote sensing, vegetation analysis is one of the most prominent fields to explore, aiming to improve a specific task. As a task, modeling insect damage in the plants is essential to establish the correct management of agricultural farmlands. Hyperspectral data, which can be acquired with field spectroscopy at plant or leaf level, is a non-direct, rapid, and trustworthy approach to indicate its health. However, the spectral redundancy inherent is a challenge for the information extraction process, making the pre-processing phase an essential part of the analysis. Currently, artificial intelligence techniques, mostly based on machine and deep learning methods, are a standard application in data processing, being pre-processing techniques an essential part of it. But few studies aimed to measure the impact of such processes in vegetation monitoring, specifically with insect damage and spectral data. Here, we provide an analysis of the impact of pre-processing techniques on machine learning algorithms’ performance over said classification task. For this, we used a field spectroradiometer that operates within the 350–1,000 nm and 1,000–2,500 nm ranges. The dataset was composed of multiple spectral measurements that took place on different days in a controlled environment with soybean plants. As pre-processing techniques, methods like baseline removal, smoothing, first and second-order derivatives, standard normal variate (SNV), multiplicative scatter correction (MSC), and principal components analysis (PCA) were investigated. Several machine learning algorithms and one deep learning method were applied to model the datasets. The impact of the pre-processing techniques was measured within validation metrics relate to its accuracy. Our results indicated that the Extra-Tree (ExT) algorithm was better, mainly when first-order derivative data were extracted from the dataset (accuracy equal to 93.68%). A ranking approach indicated that the most contributive spectral region situates at the near-infrared, between 784 and 911 nm. Our investigation also demonstrates that a deep neural network (DNN) did not return a satisfactory result over raw reflectance data. However, when considering a combination of PCA over the 2nd derivative data, it achieved similar results to the ExT algorithm (accuracy of 91.95%). The implications of such, alongside the ranking approach, are discussed in this paper. We hope that the information presented here serves as a framework for future research when applying pre-processing techniques alongside the machine and deep learning methods over spectral data.
653 $aDNN
653 $aField spectroscopy
700 1 $aFURUYA, D. E. G.
700 1 $aFURUYA, M. T. G.
700 1 $aCORRÊA, D. V.
700 1 $aGONÇALVEZ, W. N.
700 1 $aMARCATO JUNIOR, J.
700 1 $aBORGES, M.
700 1 $aBLASSIOLI-MORAES, M. C.
700 1 $aMICHEREFF, M. F. F.
700 1 $aAQUUINO, M. F. S.
700 1 $aLAUMANN, R. A.
700 1 $aLISENBERG, V.
700 1 $aRAMOS, A. P. M.
700 1 $aJORGE, L. A. de C.
773 $tInfrared Physics & Technology$gv. 123, 104203, 2022.
Download
Esconder MarcMostrar Marc Completo |
|
Registro original: |
Embrapa Instrumentação (CNPDIA) |
|
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
| Expressão de busca inválida. Verifique!!! |
|
|
