Modelling and Optimization of Biogenic Synthesis of Gold Nanoparticles from Leaf Extract of Swertia chirata Using Artificial Neural Network

Journal of Cluster Science (2018) 29:1151–1159

DOI: 10.1007/s10876-018-1429-8

Swertia chirata is a medicinal plant studied for its ability to synthesize polyshaped gold nanoparticles (AuNP). The process of AuNP biosynthesis was studied using artificial neural networks (ANN) with different activation function on output node (logistic or linear) and different training algorithm (back propagation or Levenberg–Marquardt). The maximum biosyn- thesis was checked under the optimized condition of 17.24% leaf extract, pH 4.61, gold chloride concentration 4 mM and temperature 53.61 °C. A significant improvement in the model efficiency for predicting AuNP biosynthesis around 37.60%, in terms of root mean square error was obtained with the developed ANN-linear2 model, compared to the traditional response surface methodology.

Modelling the isothermal degradation kinetics of metrafenone and mepanipyrim in a grape juice analog

Food Research International, 108, 339-346, 2018

DOI: 10.1016/j.foodres.2018.03.058

Five photodegradation products of metrafenone (MTF) and six of mepanipyrim (MEP) were identified in synthetic grape juice at 25 °C and the structures of the main reaction products established. The degradation of MTF and MEP was modelled by using three different strategies involving monitoring (a) the disappearance of the parent compound, (b) the conversion of the parent compound into its main structurally related reaction products and (c) the degradation of the parent compound to all intermediates and degradation end-products. The kinetic coefficients of degradation for these fungicides were determined and the corresponding half-lives found to be 20.8 h for MFT and 10.1 h for MEP. The proposed models afford reasonably accurate interpretation of the experimental data. Based on the results, modelling the kinetics of disappearance of the parent compound by itself does not ensure the best fit of the degradation behaviour of the fungicides.

Improved 1,3-propanediol production with maintained physical conditions and optimized media composition: Validation with statistical and neural approach

Biochemical Engineering Journal

https://doi.org/10.1016/j.bej.2017.07.003

This work is aimed at assessing the use of response surface methodology (RSM) and artificial neural networks (ANNs) for modelling, and predicting, the optimum parameters for 1,3-Propanediol production by Lactobacillus brevis N1E9.3.3 from glycerol and glucose co-fermentation. A preliminary study of physical parameters was conducted using Plackett-Burman design to reduce the number of input variables up to seven; i) beef extract, ii) yeast extract, iii) MgSO4·7H2O, iv) MnSO4·H2O, v) vitamin B12, vi) glycerol and vii) glucose. The traditional RSM models were improved by ANN models between a 54.08% and 12.19% in terms of root mean square error (RMSE). This study suggested that RSM and ANN can be considered as effective tools to model and predict optimum parameters for 1,3-Propanediol production by L. brevis N1E9.3.3.

Prediction of biological sensors appearance with ARIMA models as a tool for Integrated Pest Management protocols.

Annals of Agricultural and Environmental Medicine, 23, 2016, 129-137

DOI: 10.5604/12321966.1196868

Powdery mildew caused by Uncinula necator and Downy mildew produced by Plasmopara viticola are the most common diseases in the North-West Spain vineyards. Knowledge of airborne spore concentrations could be a useful tool in the Integrated Pest Management protocols in order to reduce the number of pesticide treatments, applied only when there is a real risk of infection.The study was carried out in a vineyard of the D. O. Ribeiro, in the North-West Spain, during the grapevine active period 2004-2012. A Hirts-type volumetric spore-trap was used for the aerobiological monitoring.During the study period the annual total U. necator spores amount ranged from the 578 spores registered in 2007 to the 4,145 spores sampled during 2008. The highest annual total P. viticola spores quantity was observed in 2010 (1,548 spores) and the lowest in 2005 (210 spores). In order to forecast the concentration of fungal spores, ARIMA models were elaborated.The most accurate models were an ARIMA (3.1.3) for U. necator and (1.0.3) for P. viticola. The possibility to forecast the spore presence 72 hours in advance open an important horizon for optimizing the organization of the harvest processes in the vineyard.

Fraxinus pollen and allergen concentrations in Ourense (South-western Europe)

Environmental Research, 147, 2016, 241–248

http://dx.doi.org/10.1016/j.envres.2016.02.014

In temperate zones of North-Central Europe the sensitization to ash pollen is a recognized problem, also extended to the Northern areas of the Mediterranean basin. Some observations in Switzerland suggest that ash pollen season could be as important as birch pollen period. The allergenic significance of this pollen has been poorly studied in Southern Europe as the amounts of ash pollen are low. Due to the high degree of family relationship with the olive pollen major allergen (backed by a sequence identity of 88%), the Fraxinus pollen could be a significant cause of early respiratory allergy in sensitized people to olive pollen as consequence of cross-reactivity processes. Ash tree flowers in the Northwestern Spain during the winter months. The atmospheric presence of Ole e 1–like proteins (which could be related with the Fra a 1 presence) can be accurately detected using Ole e 1 antibodies. The correlation analysis showed high Spearman correlation coefficients between pollen content and rainfall (R2=−0.333, p<0.01) or allergen concentration and maximum temperature (R2=−0.271, p<0.01). In addiction CCA analysis showed not significant differences (p<0.05) between the component 1 and 2 variables. PCFA analysis plots showed that the allergen concentrations are related to the presence of the Fraxinus pollen in the air, facilitating the wind speed its submicronic allergen proteins dispersion. In order to forecast the Fraxinus allergy risk periods, two regression equations were developed with Adjusted R2 values around 0.48–0.49. The t-test for dependent samples shows no significant differences between the observed data and the estimated by the equations. The combination of the airborne pollen content and the allergen quantification must be assessed in the epidemiologic study of allergic respiratory diseases.

Approach of different properties of alkylammonium surfactants using artificial intelligence and response surface methodology

Tenside, Surfactants, Detergents

Response surface methodology (RSM) and artificial neural networks (ANNs) architectures to predict the density, speed of sound, kinematic viscosity, and surface tension of aqueous solutions were developed. All models implemented using the root mean square error (RMSE) for training and validation phase were evaluated. The ANN models implemented show good values of R2 (upper than 0.974) and low errors in terms of average percentage deviation (APD) (lower than 2.92%). Nevertheless, RSM models present low APD values for density and speed of sound prediction (lower than 0.31%) and higher APD values around 5.18% for kinematic viscosity and 14.73% for surface tension. The results show that the different individual artificial neural networks implemented are a useful tool to predict the density, speed of sound, kinematic viscosity, and surface tension with reasonably accuracy.

Kinetic modelling of mancozeb hydrolysis and photolysis to ethylenethiourea and other by-products in water

Water Research 102 (2016) 561–571

http://dx.doi.org/10.1016/j.watres.2016.07.006

The aim of this study was to propose kinetic models suitable for reproducing and predicting mancozeb (Mz) conversion to by-products as a function of the operational conditions. The main factors (pH, temperature and light) potentially affecting the mancozeb degradation in aqueous models were studied by a multifactorial screening design. In addition, the response surface methodology (RSM) was applied to evaluate the interactive effects of these factors on ethylenethiourea (ETU) formation. The response surface revealed that the best degradation conditions to minimize mancozeb conversion to ETU were low pH (2), low temperature (25 °C) and darkness. Under these conditions, the percentage of mancozeb remained in the solution at 72 h was approximately 10% of the initial concentration and the percentage of ETU conversion was 5.4%. However, according to the model, in surface waters under typical environmental conditions (pH 8, 25 °C and light) the percentage of mancozeb conversion to ETU would be about 17.5%. The proposed model provides a satisfactory interpretation of the experimental data obtained during the hydrolysis of mancozeb.

Application of transit data analysis and artificial neural network in the prediction of discharge of Lor River, NW Spain

Water Science & Technology (2016)

DOI: 10.2166/wst.2016.002

Transit data analysis and artificial neural networks (ANNs) have proven to be a useful tool for characterizing and modelling non-linear hydrological processes. In this paper, these methods have been used to characterize and to predict the discharge of Lor River (North Western of Spain), one, two and three days ahead. Transit data analyses have showed a coefficient of correlation of 0.53 for a lag between precipitation and discharge of one day. By other hand, temperature and discharge has a coefficient of correlation negative (−0.43) for a delay of 19 day. The ANNs developed provide a good result for the validation period, with R2 between 0.92 and 0.80. Furthermore, these prediction models have been tested with discharge data from a period of 16 years later. Results of this testing period also show a good correlation with a R2 between 0.91 and 0.64. Overall, results indicate that ANNs are a good tool to predict river discharge with a small number of input variables.

Influence Prediction of Alkylamines Upon Electrical Percolation of AOT-based Microemulsions Using Artificial Neural Networks

Tenside Surfactants Detergents, 52, 473-476 (2015)

doi: 10.3139/113.110399

Simulations for the electrical percolation of AOT/iC8/H2O w/o microemulsions added with alkylamines have been carried out by means of multilayer perceptron. Five variables have been elected as inputs: amine concentration, molecular weight, log P, hydrocarbon chain length (as number of carbons), and pKa. As a result, a neural model consisting in five input neurons, two middle layers (with fifteen and ten neurons respectively) and one output neuron was chosen because of its better performance, with a RMSE of 0.54 °C for the prediction set, with R2 = 0.9976.

Identification of Relevant Phytochemical Constituents for Characterization and Authentication of Tomatoes by General Linear Model Linked to Automatic Interaction Detection (GLM-AID) and Artificial Neural Network Models (ANNs)

PLOS ONE

DOI: 10.1371/journal.pone.0128566

There are a large number of tomato cultivars with a wide range of morphological, chemical, nutritional and sensorial characteristics. Many factors are known to affect the nutrient content of tomato cultivars. A complete understanding of the effect of these factors would require an exhaustive experimental design, multidisciplinary scientific approach and a suitable statistical method. Some multivariate analytical techniques such as Principal Component Analysis (PCA) or Factor Analysis (FA) have been widely applied in order to search for patterns in the behaviour and reduce the dimensionality of a data set by a new set of uncorrelated latent variables. However, in some cases it is not useful to replace the original variables with these latent variables. In this study, Automatic Interaction Detection (AID) algorithm and Artificial Neural Network (ANN) models were applied as alternative to the PCA, AF and other multivariate analytical techniques in order to identify the relevant phytochemical constituents for characterization and authentication of tomatoes. To prove the feasibility of AID algorithm and ANN models to achieve the purpose of this study, both methods were applied on a data set with twenty five chemical parameters analysed on 167 tomato samples from Tenerife (Spain). Each tomato sample was defined by three factors: cultivar, agricultural practice and harvest date. General Linear Model linked to AID (GLM-AID) tree-structured was organized into 3 levels according to the number of factors. p-Coumaric acid was the compound the allowed to distinguish the tomato samples according to the day of harvest. More than one chemical parameter was necessary to distinguish among different agricultural practices and among the tomato cultivars. Several ANN models, with 25 and 10 input variables, for the prediction of cultivar, agricultural practice and harvest date, were developed. Finally, the models with 10 input variables were chosen with fit’s goodness between 44 and 100%. The lowest fits were for the cultivar classification, this low percentage suggests that other kind of chemical parameter should be used to identify tomato cultivars.

Linear Polyethers as Additives for AOT-Based Microemulsions: Prediction of Percolation Temperature Changes Using Artificial Neural Networks

Tenside Surfactants Detergents: 52 (2015) 264-270.
doi: 10.3139/113.110374

 

Predictive models based on artificial neural networks have been developed for the percolation threshold of AOT based microemulsions with addition of either glymes or polyethylene glycols. Models have been built according to the multilayer perceptron architecture, with five input variables (concentration, molecular mass, log P, number of C and O of the additive). Best model for glymes has a topology of five input neurons, five neurons in a single hidden layer and one output neuron. Polyethylene glycol model's architecture consists in five input neurons, three hidden layers with eight neurons in both first two and five in the last, and a neuron in the last output layer. All of them have a good predictive power according to several quality parameters.

Read More

A model to forecast the risk periods of Plantago pollen allergy by using the ANN methodology

Aerobiologia (2015) 31:201–211

DOI 10.1007/s10453-014-9357-z

Some biological particles present in the atmosphere, such as pollen grains, give rise to human health problems, allergies, and infections. In view of the recognized special allergenic ability of Plantago pollen grains, a model based on an artificial neural network (ANN) was developed in this work in order to forecast the Plantago airborne pollen concentration. The proposed model uses data from Plantago pollen and the main meteorological variables recorded during 16 years (1993–2008) in the city of Ourense (north- west Spain). Its accuracy was tested during the years 2009 and 2010 with a prediction horizon of 2 days in advance. The model was applied in the atmosphere of the city of Ourense (Spain). Obtained results show that ANN model provides good results against other classical mathematical methodologies, which do not convergence so well. The forecasted pollen concen- trations here are applied to allergology because they allow taking into account preventive measures in risk pollinosis suffers population.

A model to forecast the risk periods of Plantago pollen allergy by using the ANN methodology

Aerobiología (2015)

DOI: 10.1007/s10453-014-9357-z

Some biological particles present in the atmosphere, such as pollen grains, give rise to human health problems, allergies, and infections. In view of the recognized special allergenic ability of Plantago pollen grains, a model based on an artificial neural network (ANN) was developed in this work in order to forecast the Plantago airborne pollen concentration. The proposed model uses data from Plantago pollen and the main meteorological variables recorded during 16 years (1993–2008) in the city of Ourense (northwest Spain). Its accuracy was tested during the years 2009 and 2010 with a prediction horizon of 2 days in advance. The model was applied in the atmosphere of the city of Ourense (Spain). Obtained results show that ANN model provides good results against other classical mathematical methodologies, which do not convergence so well. The forecasted pollen concentrations here are applied to allergology because they allow taking into account preventive measures in risk pollinosis suffers population.

An axisymmetric model for the analysis of dynamic surface tension

RSC Adv., 2015, 5, 7921–7931 

A quantitative treatment of dynamic surface tension data has been carried out with different mathematical approaches taking into account a diffusion-controlled mechanism. The classical model has been modified in order to achieve a better description of the experimental conditions by considering a finite diffusion domain. The domain has been fixed keeping the restriction that the surfactant concentration in this region should remain constant after the adsorption at the air–water interface, in such a way that the number of surfactant unimers is 30 times the number adsorbed at the interface. The finite diffusion restriction has been used both in 1D and axisymmetric models, the latter one being the most accurate and needing a smaller diffusion domain since it considers surfactant adsorption at a sphere resembling the physical experiments. A distorted sphere geometry taking into account the Laplace–Young equation has also been studied.