|
|
| 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: |
28/09/2021 |
Data da última atualização: |
10/06/2022 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Autoria: |
CHRISTINELLI, W. A.; SHIMIZU, F. M.; FACURE, M. H. M.; CERRI, R.; OLIVEIRA JUNIOR, O. N.; CORREA, D. S.; MATTOSO, L. H. C. |
Afiliação: |
DANIEL SOUZA CORREA, CNPDIA; LUIZ HENRIQUE CAPPARELLI MATTOSO, CNPDIA. |
Título: |
Two-dimensional MoS2-based impedimetric electronic tongue for the discrimination of endocrine disrupting chemicals using machine learning. |
Ano de publicação: |
2021 |
Fonte/Imprenta: |
Sensors and Actuators: B. Chemical, v. 336, 129696, 2021. |
Páginas: |
1 - 11 |
ISSN: |
0925-4005 |
DOI: |
https://doi.org/10.1016/j.snb.2021.129696 |
Idioma: |
Inglês |
Conteúdo: |
In this paper, we report on machine learning to analyze the capacitance spectra obtained with an electronic tongue (e-tongue) and discriminate three endocrine-disrupting chemicals (EDC): bisphenol A, estrone, and 17- β-estradiol, and their mixtures. The e-tongue comprised seven sensing units made with interdigitated gold electrodes coated with layer-by-layer films of poly(o-methoxy aniline), poly(3-thiophene acetic acid), and molybdenum disulfide (MoS2). The Multilayer Perceptron (MLP), Random Forest, and Extreme Gradient Boosting (XGBoost) models were applied for multi-target regression to predict the concentration of individual contaminants and their mixtures. These machine learning models were evaluated according to the root mean square error (RMSE) values. The best performance was achieved with XGBoost for which RMSE ranged from 0.19 to 3.37 for individual contaminants, from 0.12 to 0.25 for the mixtures, and from 0.34 to 3.46 for the entire dataset. The high performance was only possible with a multi-target regression strategy, including a feature selection procedure. In the latter, the data were plotted with the parallel coordinate technique, and the silhouette coefficient was calculated, which is a quantitative measure of the ability to distinguish similar samples in a dataset. The usefulness of the machine learning methods is demonstrated by noting that the data from mixtures of EDCs could not be distinguished using multidimensional projections. Also significant is that this combination of machine learning and information visualization methodology is entirely generic; it may be applied to analyze data from etongues and other sensing and biosensing devices in prediction tasks as demanding as in the discrimination of mixtures of EDCs at concentrations below nmol L− 1 . MenosIn this paper, we report on machine learning to analyze the capacitance spectra obtained with an electronic tongue (e-tongue) and discriminate three endocrine-disrupting chemicals (EDC): bisphenol A, estrone, and 17- β-estradiol, and their mixtures. The e-tongue comprised seven sensing units made with interdigitated gold electrodes coated with layer-by-layer films of poly(o-methoxy aniline), poly(3-thiophene acetic acid), and molybdenum disulfide (MoS2). The Multilayer Perceptron (MLP), Random Forest, and Extreme Gradient Boosting (XGBoost) models were applied for multi-target regression to predict the concentration of individual contaminants and their mixtures. These machine learning models were evaluated according to the root mean square error (RMSE) values. The best performance was achieved with XGBoost for which RMSE ranged from 0.19 to 3.37 for individual contaminants, from 0.12 to 0.25 for the mixtures, and from 0.34 to 3.46 for the entire dataset. The high performance was only possible with a multi-target regression strategy, including a feature selection procedure. In the latter, the data were plotted with the parallel coordinate technique, and the silhouette coefficient was calculated, which is a quantitative measure of the ability to distinguish similar samples in a dataset. The usefulness of the machine learning methods is demonstrated by noting that the data from mixtures of EDCs could not be distinguished using multidimensional projections. Also significant is t... Mostrar Tudo |
Palavras-Chave: |
Information visualization; Machine learning; XGBoost. |
Categoria do assunto: |
-- |
Marc: |
LEADER 02660naa a2200265 a 4500 001 2134828 005 2022-06-10 008 2021 bl uuuu u00u1 u #d 022 $a0925-4005 024 7 $ahttps://doi.org/10.1016/j.snb.2021.129696$2DOI 100 1 $aCHRISTINELLI, W. A. 245 $aTwo-dimensional MoS2-based impedimetric electronic tongue for the discrimination of endocrine disrupting chemicals using machine learning.$h[electronic resource] 260 $c2021 300 $a1 - 11 520 $aIn this paper, we report on machine learning to analyze the capacitance spectra obtained with an electronic tongue (e-tongue) and discriminate three endocrine-disrupting chemicals (EDC): bisphenol A, estrone, and 17- β-estradiol, and their mixtures. The e-tongue comprised seven sensing units made with interdigitated gold electrodes coated with layer-by-layer films of poly(o-methoxy aniline), poly(3-thiophene acetic acid), and molybdenum disulfide (MoS2). The Multilayer Perceptron (MLP), Random Forest, and Extreme Gradient Boosting (XGBoost) models were applied for multi-target regression to predict the concentration of individual contaminants and their mixtures. These machine learning models were evaluated according to the root mean square error (RMSE) values. The best performance was achieved with XGBoost for which RMSE ranged from 0.19 to 3.37 for individual contaminants, from 0.12 to 0.25 for the mixtures, and from 0.34 to 3.46 for the entire dataset. The high performance was only possible with a multi-target regression strategy, including a feature selection procedure. In the latter, the data were plotted with the parallel coordinate technique, and the silhouette coefficient was calculated, which is a quantitative measure of the ability to distinguish similar samples in a dataset. The usefulness of the machine learning methods is demonstrated by noting that the data from mixtures of EDCs could not be distinguished using multidimensional projections. Also significant is that this combination of machine learning and information visualization methodology is entirely generic; it may be applied to analyze data from etongues and other sensing and biosensing devices in prediction tasks as demanding as in the discrimination of mixtures of EDCs at concentrations below nmol L− 1 . 653 $aInformation visualization 653 $aMachine learning 653 $aXGBoost 700 1 $aSHIMIZU, F. M. 700 1 $aFACURE, M. H. M. 700 1 $aCERRI, R. 700 1 $aOLIVEIRA JUNIOR, O. N. 700 1 $aCORREA, D. S. 700 1 $aMATTOSO, L. H. C. 773 $tSensors and Actuators: B. Chemical$gv. 336, 129696, 2021.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Instrumentação (CNPDIA) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
URL |
Voltar
|
|
Registro Completo
Biblioteca(s): |
Embrapa Caprinos e Ovinos; Embrapa Recursos Genéticos e Biotecnologia. |
Data corrente: |
23/08/2016 |
Data da última atualização: |
27/03/2023 |
Tipo da produção científica: |
Artigo em Periódico Indexado |
Circulação/Nível: |
B - 1 |
Autoria: |
LACERDA, T. S.; CAETANO, A. R.; FACO, O.; FARIA, D. A. de; McMANUS, C. M.; LOBO, R. N. B.; SILVA, K. de M.; PAIVA, S. R. |
Afiliação: |
Thaísa Sant'Anna Lacerda, Universidade de Brasília (UnB) - Brasília, DF, Brazil; ALEXANDRE RODRIGUES CAETANO, Cenargen; OLIVARDO FACO, CNPC; Concepta M. McManus, Universidade de Brasília (UnB) - Brasília, DF, Brazil; RAIMUNDO NONATO BRAGA LOBO, CNPC; KLEIBE DE MORAES SILVA, CNPC; SAMUEL REZENDE PAIVA, SRI. |
Título: |
Single marker assisted selection in Brazilian Morada Nova hair sheepcommunity-based breeding program. |
Ano de publicação: |
2016 |
Fonte/Imprenta: |
Small Ruminant Research, v. 139, p. 15-19, June, 2016. |
DOI: |
http://dx.doi.org/10.1016/j.smallrumres.2016.04.009 |
Idioma: |
Inglês Português |
Conteúdo: |
Abstract: Morada Nova hair sheep show traits desirable for lamb production especially in extensive production systems in Northeastern Brazil, representing an important genetic resource for producing lamb in semi-arid climates in Brazil and elsewhere. Performance testing has been carried out annually with this breed since 2008. In the present study, Morada Nova sheep from two Brazilian states: Ceará (140 animals) and São Paulo (112 animals) were genotyped for a SNP associated with litter size, which is almost only found in Brazilian locally adapted sheep breeds (FecGE). The total observed frequency of FecGE was 0.65, while an increased number of observed heterozygotes was also observed (?2 = 7.274, p< 0.01). No significant FecGE allele frequency differences were observed (p = 0.3708) in 139 performance-tested rams classified as Elite/Superior or Regular/Inferior in the states of Ceará and São Paulo. Considering that litter size has been shown to positively affect farm profitability in medium to high input systems, we suggest that inclusion of FecGE genotyping information in future selection indexes estimated with basis on performance test data, fine-tuned to regional production systems may contribute to increase profitability gains observed in the Morada Nova community-based breeding program. |
Palavras-Chave: |
GDF9; Performance testing; Raça Morada nova; Recurso genético animal; Teste de desempenho. |
Thesagro: |
Genética animal; Ovino. |
Thesaurus NAL: |
Animal genetic resources; Reproductive performance; Sheep. |
Categoria do assunto: |
G Melhoramento Genético |
URL: |
https://ainfo.cnptia.embrapa.br/digital/bitstream/item/180086/1/1-s2.0-S0921448816300979-main.pdf
|
Marc: |
LEADER 02332naa a2200337 a 4500 001 2054185 005 2023-03-27 008 2016 bl uuuu u00u1 u #d 024 7 $ahttp://dx.doi.org/10.1016/j.smallrumres.2016.04.009$2DOI 100 1 $aLACERDA, T. S. 245 $aSingle marker assisted selection in Brazilian Morada Nova hair sheepcommunity-based breeding program.$h[electronic resource] 260 $c2016 520 $aAbstract: Morada Nova hair sheep show traits desirable for lamb production especially in extensive production systems in Northeastern Brazil, representing an important genetic resource for producing lamb in semi-arid climates in Brazil and elsewhere. Performance testing has been carried out annually with this breed since 2008. In the present study, Morada Nova sheep from two Brazilian states: Ceará (140 animals) and São Paulo (112 animals) were genotyped for a SNP associated with litter size, which is almost only found in Brazilian locally adapted sheep breeds (FecGE). The total observed frequency of FecGE was 0.65, while an increased number of observed heterozygotes was also observed (?2 = 7.274, p< 0.01). No significant FecGE allele frequency differences were observed (p = 0.3708) in 139 performance-tested rams classified as Elite/Superior or Regular/Inferior in the states of Ceará and São Paulo. Considering that litter size has been shown to positively affect farm profitability in medium to high input systems, we suggest that inclusion of FecGE genotyping information in future selection indexes estimated with basis on performance test data, fine-tuned to regional production systems may contribute to increase profitability gains observed in the Morada Nova community-based breeding program. 650 $aAnimal genetic resources 650 $aReproductive performance 650 $aSheep 650 $aGenética animal 650 $aOvino 653 $aGDF9 653 $aPerformance testing 653 $aRaça Morada nova 653 $aRecurso genético animal 653 $aTeste de desempenho 700 1 $aCAETANO, A. R. 700 1 $aFACO, O. 700 1 $aFARIA, D. A. de 700 1 $aMcMANUS, C. M. 700 1 $aLOBO, R. N. B. 700 1 $aSILVA, K. de M. 700 1 $aPAIVA, S. R. 773 $tSmall Ruminant Research$gv. 139, p. 15-19, June, 2016.
Download
Esconder MarcMostrar Marc Completo |
Registro original: |
Embrapa Recursos Genéticos e Biotecnologia (CENARGEN) |
|
Biblioteca |
ID |
Origem |
Tipo/Formato |
Classificação |
Cutter |
Registro |
Volume |
Status |
Fechar
|
Nenhum registro encontrado para a expressão de busca informada. |
|
|