Neural network modeling to support an experimental study of the delignification process of sugarcane bagasse after alkaline hydrogen peroxide pre-treatment

Valim, Isabelle C.; Fidalgo, J.L.G.; Rego, Artur S. C.; Vilani, Cecília; Martins, Ana Rosa Fonseca de Aguiar; Santos, Bettina Steren dos

doi:10.1016/j.biortech.2017.06.029

Cited by 22 publications

(10 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…10,11 ANNs have been used in clinical medicine for diagnosis; prognosis of survival analyses; clinical outcome in the medical domains of cancer, infectious diseases and critical care. [12][13][14]…”

Section: Introductionmentioning

confidence: 99%

Prediction and evaluation of the severity of acute respiratory distress syndrome following severe acute pancreatitis using an artificial neural network algorithm model

Gao

2019

HPB

View full text Add to dashboard Cite

Background: To predict the risk and severity of acute respiratory distress syndrome (ARDS) following severe acute pancreatitis (SAP) by artificial neural networks (ANNs) model. Methods: ANNs model was constructed by clinical data of 217 SAP patients. The model was first trained on 152 randomly chosen patients, validated and tested on the 33 patients and 32 patients respectively. Statistical analysis was used to assess the value of it. Results:The training, validation, and test set were not significantly different for 13 variables. After training, ANNs retained excellent pattern recognition ability. When ANNs model was applied to the test set, it revealed a sensitivity of 87.5%, and an accuracy of 84.43%. Significant differences were found between ANNs model and logistic regression model. When ANNs model is used to identify ARDS, the area under ROC was 0.859 + 0.048. Meanwhile, pancreatic necrosis rate, lactic dehydrogenase and oxyhemoglobin saturation were the most important independent variables. Compared with the Berlin definition, the ANN model shows a good accuracy of 73.1% for total severity of ARDS. Conclusion:ANNs model is a valuable tool in dealing with risk prediction of ARDS following SAP. In addition, it can extract informative risk factors of ARDS via the ANNs model.

show abstract

Section: Introductionmentioning

confidence: 99%

Prediction and evaluation of the severity of acute respiratory distress syndrome following severe acute pancreatitis using an artificial neural network algorithm model

Gao

2019

HPB

View full text Add to dashboard Cite

show abstract

“…Artificial intelligence tools such as ANN and GA are highly efficient, capable of handling incomplete data and deals with non-linear problems at high speeds [10]. ANN was used by Valim et al (2017) and Valim et al (2018) to study the delignification process of sugarcane bagasse via hydrogen peroxide (H 2 O 2 ) and supercritical carbon dioxide (ScCO 2 ), respectively [11,12]. However, there are several limitations associated with these such as the data size required to provide adequate information (>20) for the training of neural networks.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Dissolution Conditions During Fractionation of Corn-cob in ZnCl2.4H2O/Urea Solvent System: A Statistical Approach

Ejekwu¹,

Ayeni²,

Daramola³

2019

TOCENGJ

View full text Add to dashboard Cite

Background and Objectives: The choice of a suitable pretreatment method and the adjustment of the pretreatment parameters for efficient conversion of biomass to value-added products is crucial to a successful biorefinery concept. Pretreatment of corn cob using ZnCl2.4H2O/ Urea was carried out and optimized in this study. Methods: Effect of pretreatment conditions on cellulose recovery, hemicellulose recovery during the pretreatment of corn cob using ZnCl2.4H2O/ Urea was investigated via response surface methodology approach and optimized in this study. Experimental results were analysed and appropriate predictive empirical linear models were developed for each response. Results: For cellulose recovery, time and temperature, and solvent concentration were significant factors. Hemicellulose recovery in the liquid fraction is impacted by time and solvent concentration, while lignin recovery is affected by time and temperature. Using numerical optimization by desirability function, optimum pretreatment conditions obtained were: 90 min, 120°C and concentration of 71.32%/28.68 (w/w) ZnCl2.4H2O/ Urea. At these conditions, the predicted recovery for cellulose, hemicellulose and lignin were 99.03%, 27.18% and 72.43%, respectively, with a desirability of 0.902. The actual recovery was 91%, 29% and 68% for cellulose, hemicellulose and lignin, respectively, at the same conditions. Conclusion: These results indicate that the investigated variables have pronounced effect on the pretreatment of corn cob. Therefore, optimum conditions are required for recovery of desired composition before conversion to value-added products.

show abstract

“…No contexto do pré-tratamento do bagaço da cana-de-açúcar, [61] utilizou ANN na identificação das condições experimentais executadas, além da predição do teor de lignina oxidada na biomassa durante o processo.…”

Section: Redes Neurais Artificiaisunclassified

“…O processo experimental para extração de lignina do bagaço da cana-deaçúcar com H 2 O 2 foi desenvolvido conforme [61], adaptado de [5]. Alíquotas de 2,0 g de bagaço de cana-de-açúcar foram colocadas em erlenmyers de 250 mL.…”

Section: Procedimento Experimentalunclassified

Estratégias De Modelagem E Otimização Aplicadas Ao Processo De Deslignização Do Bagaço Da Cana-De-Açúcar

VALIM¹

View full text Add to dashboard Cite

Ao meu marido Sheriton Valim, com quem amo compartilhar a vida. Obrigada por todo o incentivo e ajuda. À minha família, especialmente minha mãe Vania Cunha e meu irmão Fillipe Cunha por cada sorriso de orgulho perante minhas conquistas. Também sou grata ao meu pai José Luiz que, com certeza, está vibrando lá do céu.Aos professores Brunno Santos e Cecília Vilani. Resumi-los a orientadores é muito pouco para mim. Obrigada por todo apoio e amizade. Obrigada por me fazerem descobrir um novo amor na profissão. À minha "minion" Anna Vieira pela disponibilidade e disposição em trabalhar pelo sucesso desse trabalho.À professora Ana Rosa Martins pela ajuda e disponibilidade dos equipamentos para os primeiros experimentos.Aos meus amigos João Marcos, Mayara Santos, Rafael Fuly e Talita Lisa pela compreensão nos meus momentos de ausência.Aos meus amigos da PUC-Rio Amanda Balassiano, Ana Dourado, Julia Cardoso, Mayra Tavares, Rafael Basílio e Renata Nofal. Em particular, aqueles que pertencem ao meu grupo de pesquisa Artur Serpa, Caroline Dias, Felipe Zanone e Juliana Fidalgo por toda ajuda no trabalho realizado.Ao técnico Henrique Meira por toda assistência prestada durante a etapa do processo realizada na PUC-Rio.Ao Departamento de Física da PUC-Rio pela disponibilidade do equipamento para realização de análises.Ao Instituto de Química Verde SENAI pela parceria nesse trabalho.Ao CNPq e à PUC-Rio, pelos auxílios concedidos, sem os quais este trabalho não poderia ter sido realizado. Palavras-chaveBagaço de cana-de-açúcar; Extração de lignina; Otimização; Planejamento experimental; Inteligência artificial.

show abstract

Neural network modeling to support an experimental study of the delignification process of sugarcane bagasse after alkaline hydrogen peroxide pre-treatment

Cited by 22 publications

References 22 publications

Prediction and evaluation of the severity of acute respiratory distress syndrome following severe acute pancreatitis using an artificial neural network algorithm model

Prediction and evaluation of the severity of acute respiratory distress syndrome following severe acute pancreatitis using an artificial neural network algorithm model

Optimization of Dissolution Conditions During Fractionation of Corn-cob in ZnCl2.4H2O/Urea Solvent System: A Statistical Approach

Estratégias De Modelagem E Otimização Aplicadas Ao Processo De Deslignização Do Bagaço Da Cana-De-Açúcar

Contact Info

Product

Resources

About