Optimization of the Bacillus thuringiensis var. kurstaki HD-1 δ-endotoxins production by using experimental mixture design and artificial neural networks

Moreira, Guilherme A.; Micheloud, Gabriela A.; Beccaria, Alejandro José; Goicoechea, Héctor C.

doi:10.1016/j.bej.2006.12.025

Cited by 30 publications

(17 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The modeling of experimental or real-time data with artificial neural network (ANN) techniques has been applied in many research fields, such as biotechnology, pharmaceutical, medicine and food [1][2][3][4][5][6][7][8]. In the biotechnology field, ANN modeling is a commonly applied approach for carrying out estimations, control studies, classification analysis, and fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Modeling of polygalacturonase enzyme activity and biomass production by Aspergillus sojae ATCC 20235

Tokatlı

Tarı

Ünlütürk

et al. 2009

J Ind Microbiol Biotechnol

View full text Add to dashboard Cite

Aspergillus sojae, which is used in the making of koji, a characteristic Japanese food, is a potential candidate for the production of polygalacturonase (PG) enzyme, which of a major industrial significance. In this study, fermentation data of an A. sojae system were modeled by multiple linear regression (MLR) and artificial neural network (ANN) approaches to estimate PG activity and biomass. Nutrient concentrations, agitation speed, inoculum ratio and final pH of the fermentation medium were used as the inputs of the system. In addition to nutrient conditions, the final pH of the fermentation medium was also shown to be an effective parameter in the estimation of biomass concentration. The ANN parameters, such as number of hidden neurons, epochs and learning rate, were determined using a statistical approach. In the determination of network architecture, a cross-validation technique was used to test the ANN models. Goodness-offit of the regression and ANN models was measured by the R 2 of cross-validated data and squared error of prediction. The PG activity and biomass were modeled with a 5-2-1 and 5-9-1 network topology, respectively. The models predicted enzyme activity with an R 2 of 0.84 and biomass with an R 2 value of 0.83, whereas the regression models predicted enzyme activity with an R 2 of 0.84 and biomass with an R 2 of 0.69.

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling of polygalacturonase enzyme activity and biomass production by Aspergillus sojae ATCC 20235

Tokatlı

Tarı

Ünlütürk

et al. 2009

J Ind Microbiol Biotechnol

View full text Add to dashboard Cite

show abstract

“…Son un instrumento matemático que permite tener una estrategia para tomar decisiones a partir de una gran variedad de fuentes, ya que no requiere ninguna restricción fuerte en las estructuras de preferencia. En la industria alimentaria, han venido aplicándose con éxito metodologías experimentales para evaluar de manera consistente y económica la influencia de los factores y/o componentes de la mezcla en el producto final, varios autores presentan investigaciones con diversas metodologías experimentales en el estudio y optimización de productos alimenticios (Álvarez y Salamanca, 2007;Zhou et al, 2007;Sánchez et al, 2007;Moreira et al, 2007;Quintero-Gil y Rueda-Quijano, 2008;Rojas et al, 2010a;Rojas et al, 2010b;Flores et al, 2010;Saltos y Bayas, 2010;Tinoco et al, 2011;Ketelaere et al, 2011). De esta forma, el objetivo planteado en el presente estudio fue de optimizar las dos etapas de producción de este tipo de helado; es decir, encontrar las condiciones óptimas para el proceso de hidrólisis de la lactosa y posteriormente determinar las condiciones óptimas de mezcla y proceso que generen la mayor aceptación sensorial del helado.…”

Section: Introductionunclassified

Experimental design and multicriteria decision making methods for the optimization of ice cream composition

et al. 2012

View full text Add to dashboard Cite

ResumenEl objetivo del presente trabajo fue optimizar las características sensoriales y tecnológicas del helado tipo mantecado. El trabajo comprendió dos etapas: 1) optimización de la hidrólisis enzimática de la lactosa y 2) optimización del proceso y producto. Para la primera etapa se utilizó un diseño factorial completo, el cual fue optimizado utilizando el método de superficie de respuesta y el método de máxima pendiente. En la segunda etapa se utilizó un diseño de mezclas combinado con variables de proceso para establecer el producto que presente la mejor aceptación sensorial, mayor rendimiento y menor costo. La evaluación de la aceptabilidad del producto fue desarrollada por un panel de catadores no entrenados. Como principal resultado se mejoraron las características sensoriales y tecnológicas del producto terminado, estableciendo las condiciones óptimas de su elaboración. Palabras clave: Diseño factorial, diseño de mezclas, función utilidad, superficie de respuesta. AbstractThe aim of the present work was to optimize the sensorial and technological features of ice cream. The experimental work was performed in two stages: 1) optimization of lactose enzymatic hydrolysis, and 2) optimization of the process and product. For the first stage a complete factorial design was developed, optimized using both response surface and the steepest ascent method. In the second stage a mixture design was performed, combining the process variables. The product with the best sensorial acceptance, high yield and low cost was selected. The acceptance of the product was developed by an untrained taster's panel. As a main result the sensorial and technological features of the final product were improved, establishing the optimum parameters for its elaboration.

show abstract

“…Artificial neural network modeling, which was inspired from the functioning of the biological nervous systems, is a powerful technique with its strong ability to learn and predict [9]. It has been successfully applied for modeling nonlinear complex problems in diverse areas and has several acknowledged applications in biological systems [10][11][12][13][14].…”

Section: Introductionmentioning

confidence: 99%

Simultaneous modeling of enzyme production and biomass growth in recombinant Escherichia coli using artificial neural networks

Günay¹,

Nikerel²,

Öner³

et al. 2008

Biochemical Engineering Journal

View full text Add to dashboard Cite

Optimization of the Bacillus thuringiensis var. kurstaki HD-1 δ-endotoxins production by using experimental mixture design and artificial neural networks

Cited by 30 publications

References 45 publications

Modeling of polygalacturonase enzyme activity and biomass production by Aspergillus sojae ATCC 20235

Modeling of polygalacturonase enzyme activity and biomass production by Aspergillus sojae ATCC 20235

Experimental design and multicriteria decision making methods for the optimization of ice cream composition

Simultaneous modeling of enzyme production and biomass growth in recombinant Escherichia coli using artificial neural networks

Contact Info

Product

Resources

About