Optimization of extraction of linarin from Flos chrysanthemi indici by response surface methodology and artificial neural network

The extraction of linarin from Flos chrysanthemi indici by ethanol was investigated. Two modeling techniques, response surface methodology and artificial neural network, were adopted to optimize the process parameters, such as, ethanol concentration, extraction period, extraction frequency, and solvent to material ratio. We showed that both methods provided good predictions, but artificial neural network provided a better and more accurate result. The optimum process parameters include, ethanol concentration of 74%, extraction period of 2 h, extraction three times, solvent to material ratio of 12 mL/g. The experiment yield of linarin was 90.5% that deviated less than 1.6% from that obtained by predicted result.     

Microfibrillated cellulose/cellulose acetate composites: Effect of surface treatment

Microfibrillated cellulose (MFC), which consists of a web‐like array of cellulose fibrils having a diameter in the range of 10–100 nm, was incorporated into a cellulose acetate (CA) matrix to form a totally biobased structural composite. Untreated and a 3‐aminopropyltriethoxysilane (APS) surface treated MFC was combined with a CA matrix by film casting from an acetone suspension. The effectiveness of the surface treatment was determined by infrared spectroscopy and X‐ray photoelectron spectroscopy. The Young's moduli of APS treated MFC composite films increase with increasing MFC content from 1.9 GPa for the CA to 4.1 GPa at 7.5 wt % of MFC, which is more than doubled. The tensile strength of the composite film increases to a maximum of 63.5 MPa at 2.5 wt % compared to the CA which has a value of 38 MPa. The thermal stability of composites with treated MFC is also better than the untreated MFC. © 2009 Wiley Periodicals, Inc. J Polym Sci Part B: Polym Phys 48: 153–161, 2010     

Prediction of programmed-temperature retention values of naphthas by artificial neural networks

It is proposed for the first time a method of prediction of the programmed-temperature retention times of components of naphthas in capillary gas chromatography using artificial neural networks. People are used to predict the programmed-temperature retention time using many formulas such as the integral formula, which requires that four parameters must be determined by calculation or experiments. However the results obtained by the formula are not so good to meet the demand of industry. In order to predict retention time accurately and conveniently, artificial neural networks using five-fold cross-validation and leave-20%-out methods have been applied. Only two parameters: density and isothermal retention index were used as input vectors. The average RMS error for predicted values of five different networks was 0.18, whereas the RMS error of predictions by the integral formula was 0.69. Obviously, the predictions by neural networks were much better than predictions by the formula, and neural networks need fewer parameters than the formula. So neural networks can successfully and conveniently solve the problem of predictions of programmed-temperature retention times, and provide useful data for analysis of naphthas in petrochemical industry.     

The study for optimization of chromatographic condition by means of artificial neural networks

In this paper, the optimization of gas chromatographic experimental parameters is investigated using a three layer feed-forward neural network with the back-propagating. The design, development, and testing of the neural network are described in detail. The chosen structure is 4-6-2 system with a learning rate eta of 0.6 and a momentum constant mu of 0.4. The results of several simulations are very satisfactory. Network results are compared with the results obtained by the orthogonal method.     

人工神经网络预测煤炭成浆浓度的研究

考虑煤炭的多种理化特性建立了成浆浓度的神经网络预测模型,对其数据预处理方法、学习率和中间层节点数等进行了深入讨论。水分、挥发分、分析基碳、灰分和氧等五个因子对于煤炭成浆性的预测起到主导作用。五因子、七因子和八因子神经网络模型对煤炭成浆浓度的预测误差分别为：0.53%、0.50%和0.74%,而现有回归分析方程的误差为1.15%,故神经网络模型比回归分析方程有更好的预测能力,尤以七因子模型最佳。     

Urea enzymatic hydrolysis reaction: optimization by response surface methodology based on potentiometric measurements

The enzymatic hydrolysis reaction of urea by urease is optimized in this work by the chemometric response surface methodology (RSM), based on an initial rate potentiometric measurement using an NH(4)(+) ion-selective electrode (ISE). In this investigation, the ranges of critical variables determined by a preliminary "one at a time" (OVAT) procedure were used as input for the subsequent RSM chemometric analysis. The RSM quadratic response was found to be quite appropriate for modeling and optimization of the hydrolysis reaction as illustrated by the relatively high value of the determination coefficient (R(2)=90.1%), along with the satisfactory results obtained by the analysis of variance (ANOVA). All the evaluated analytical characteristics of the optimized method such as: the linear calibration curve, the upper and lower detection limits, the within-day precisions at low and at high levels, the assay recovery in pool serum media, along with the activation kinetic parameters, were also reported. Further, in order to check the quality of the optimization and the validity of the model, the assay of urea, both in aqueous laboratory and human serum samples, were performed. It has to be noted that the kinetic initial rate measurement method used in this work, permitted to overcome the general problem of NH(4)(+) ISE low selectivity against Na(+) and K(+) interfering ions in real samples.     

Statistical analysis and optimization of photodegradation efficiency of methyl orange from aqueous solution using cellulose/zinc oxide hybrid aerogel by response surface methodology (RSM)

The photodegradation efficiency of cellulose-X/zinc oxide-Y (CA-X/ZnO-Y) aerogels was studied to degrade methyl orange (MO) as an organic dye pollutant from an aqueous solution under UV light irradiation. In this study, the initial pH of the solution (3, 7, and 11), the photocatalyst dosage (3, 6, and 9 g L^-1), the initial concentration of solution MO (10, 20, and 30 ppm), and the concentration of cellulose in CA-X/ZnO-Y hybrid aerogel (3, 6, and 9 wt%) were selected as four variable parameters, whereas the photoderadation performance was selected as the response. Moreover, the response surface methodology (RSM) analysis was carried out to investigate the influence of four various experimental factors at different times on the degradation of MO. The adequacy result of the proposed models displays that total of the proposed models can predict the photodegradation efficiency of MO by CA-x/ZnO-y aerogel. The optimization results of the process showed that pH = 3 and concentration of MO = 10 ppm, photocatalyst dosage (9 g L^-1), and MCC concentration (9 g) are the optimal level of the studied parameters. Also, the results showed that desirability of 0.96 confirms the acceptance and applicability of the model where the RSM model is a helpful technique for the optimum conditions design.     

Bioinspired crystallization of CaCO3 coatings on electrospun cellulose acetate fiber scaffolds and corresponding CaCO3 microtube networks

This article describes the mineralization behavior of CaCO(3) crystals on electrospun cellulose acetate (CA) fibers by using poly(acrylic acid) (PAA) as a crystal growth modifier and further templating synthesis of CaCO(3) microtubes. Calcite film coatings composed of nanoneedles can form on the surfaces of CA fibers while maintaining the fibrous and macroporous structures if the concentration of PAA is in a suitable range. In the presence of a suitable concentration of PAA, the acidic PAA molecules will first adsorb onto the surface of CA fibers by the interaction between the OH moieties of CA and the carboxylic groups of PAA, and then the redundant carboxylic groups of PAA can ionically bind Ca(2+) ions on the surfaces of CA fibers, resulting in the local supersaturation of Ca(2+) ions on and near the fiber surface, which can induce the nucleation of CaCO(3) on the CA fibers instead of in bulk solution. Calcite microtube networks on the macroscale can be prepared by the removal of CA fibers after the CA@CaCO(3) composite is treated with acetone. When the CA fiber scaffold is immersed in CaCl(2) solution with an extended incubation time, the first deposited calcite coatings can act as secondary substrate, leading to the formation of smaller calcite mesocrystal fibers. The present work proves that inorganic crystal growth can occur even at an organic interface without the need for commensurability between the lattices of the organic and inorganic counterparts.     

Prediction of n-octanol/water partition coefficients from PHYSPROP database using artificial neural networks and E-state indices

A new method, ALOGPS v 2.0 (http://www.lnh.unil.ch/~itetko/logp/), for the assessment of n-octanol/water partition coefficient, log P, was developed on the basis of neural network ensemble analysis of 12 908 organic compounds available from PHYSPROP database of Syracuse Research Corporation. The atom and bond-type E-state indices as well as the number of hydrogen and non-hydrogen atoms were used to represent the molecular structures. A preliminary selection of indices was performed by multiple linear regression analysis, and 75 input parameters were chosen. Some of the parameters combined several atom-type or bond-type indices with similar physicochemical properties. The neural network ensemble training was performed by efficient partition algorithm developed by the authors. The ensemble contained 50 neural networks, and each neural network had 10 neurons in one hidden layer. The prediction ability of the developed approach was estimated using both leave-one-out (LOO) technique and training/test protocol. In case of interseries predictions, i.e., when molecules in the test and in the training subsets were selected by chance from the same set of compounds, both approaches provided similar results. ALOGPS performance was significantly better than the results obtained by other tested methods. For a subset of 12 777 molecules the LOO results, namely correlation coefficient r(2)= 0.95, root mean squared error, RMSE = 0.39, and an absolute mean error, MAE = 0.29, were calculated. For two cross-series predictions, i.e., when molecules in the training and in the test sets belong to different series of compounds, all analyzed methods performed less efficiently. The decrease in the performance could be explained by a different diversity of molecules in the training and in the test sets. However, even for such difficult cases the ALOGPS method provided better prediction ability than the other tested methods. We have shown that the diversity of the training sets rather than the design of the methods is the main factor determining their prediction ability for new data. A comparative performance of the methods as well as a dependence on the number of non-hydrogen atoms in a molecule is also presented.     

Optimization of Portulaca oleracea L. extract using response surface methodology and artificial neural network and characterization of bioactive compound by high-resolution mass spectroscopy

The well-known medicinal plant Portulaca oleracea L. (PO) is used as a traditional medicine and culinary herb to treat various diseases. Fatty acids, essential oils, and flavonoids were extracted from PO seeds and leaves using ultrasonic, microwave, and supercritical fluid extraction with RSM techniques. However, investigations on the secondary metabolites and antioxidant capabilities of the aerial part of PO (APO) are scarce. In order to extract polyphenols and antioxidants from APO as effectively as possible, this study used heat reflux extraction (HRE), response surface methodology (RSM), and artificial neural network (ANN) modeling. It also used high-resolution mass spectrometry to identify the APO secondary metabolite. A central-composite design (CCD) was used to establish the ideal ethanol content, extraction time, and extraction temperature to extract the highest polyphenolic compounds and antioxidant activity from APO. According to RSM, the highest amount of TPC (8.23 ± 1.06 mgGAE/g), TFC (43.12 ± 1.15 mgCAE/g), DPPH-scavenging activity (43.01 ± 1.25 % of inhibition) and FRAP (35.98 ± 0.19 µM ascorbic acid equivalent) were obtained at 60.0 % ethanol, 90.2 % time, and 50 °C. Statistical metrics such as the coefficient of determination (R²), root-mean-square error (RMSE), absolute average deviation (AAD), and standard error of prediction (SEP) revealed the ANN's superiority. Ninety-one (91) secondary metabolites, including phenolic, flavonoids, alkaloids, fatty acids, and terpenoids, were discovered using high-resolution mass spectrometry. In addition, 21 new phytoconstituents were identified for the first time in this plant. The results revealed a significant concentration of phytoconstituents, making it an excellent contender for the pharmaceutical and food industries.     

Prediction of the radioactivity in Hazar Lake (Sivrice, Turkey) by artificial neural networks

Summary This paper presents an Artificial Neural Network (ANN) model for determining the total radioactivity in Hazar Lake (Sivrice, Turkey). In order to cope with complex calculations and experiments required for the determination of total radioctivity. The proposed ANN system employs the individual training strategy with fixed-weight and supervised models. The simulation demonstrate the feasibility of the neural based model. Compared to the classical methods, the proposed ANN-based model makes the processes much easier.     

Process optimization of vapor phase pyridine synthesis using response surface methodology

The vapor phase pyridine synthesis from acetaldehyde, formaldehyde and ammonia over HZSM-5 catalyst was studied. The process parameters like temperature, aldehyde ratio, and Si/Al ratio in HZSM-5 was investigated and the process conditions were optimized using surface response methodology (RSM) based on Box-Behnken design. The influence of process parameters investigated using analysis of variance (ANOVA), to identify the significant parameters. The optimum conditions for high yield of pyridine were identified to be a reaction temperature 400°C, aldehyde ratio 1: 1 and Si/Al ratio 106.7. A maximum of 55% yield of pyridine formed under the optimum experimental conditions. The proposed model equation using RSM has shown good agreement with the experimental data, with a correlation coefficient R ² = 0.99.     

Flow injection analysis of fluoride: optimization of experimental conditions and non-linear calibration using artificial neural networks

This paper deals with the application of artificial neural networks (ANNs) to two common problems in spectroscopy: optimization of experimental conditions and non-linear calibration of the result, with particular reference to the determination of fluoride by flow injection analysis (FIA). The FIA system was based on the formation of a blue ternary complex between zirconium(IV), p-methyldibromoarsenazo and F- with the maximum absorption wavelength at 635 nm. First, optimization in terms of sensitivity and sampling rate was carried out by using jointly a central composite design and ANNs, and a neural network with a 3-7-1 structure was confirmed to be able to provide the maximum performance. Second, the relationship between the concentration of fluoride and its absorbance was modeled by ANNs. In this process, cross-validation and leave-k-out were used. The results showed that good prediction was attained in the 1-4-1 neural net. The trained networks proved to be very powerful in both applications. The proposed method was successfully applied to the determination of free fluoride in tea and toothpaste with recoveries between 96 and 101%.     

Prediction of electrophoretic mobilities of alkyl- and alkenylpyridines in capillary electrophoresis using artificial neural networks

A gas chromatographic method to determine thymol, eucalyptol (cineole), menthol and camphor residues in honey and beeswax is proposed. To isolate the compounds, three methods involving liquid-liquid extraction with methylene chloride, distillation, or solid-phase extraction on octadecylsilica cartridges can be used. The GC separation is carried out on a 60 m x 0.53 mm Stabilwax DA capillary column, using a flame ionization detector. The method is applied to the analysis of natural honey and also honey and beeswax samples from beehives treated with the above compounds.     

Prediction of electrophoretic mobilities of sulfonamides in capillary zone electrophoresis using artificial neural networks

Artificial neural networks (ANNs) were successfully developed for the modeling and prediction of electrophoretic mobility of a series of sulfonamides in capillary zone electrophoresis. The cross-validation method was used to evaluate the prediction ability of the generated networks. The mobility of sulfonamides as positively charged species at low pH and negatively charged species at high pH was investigated. The results obtained using neural networks were compared with the experimental values as well as with those obtained using the multiple linear regression (MLR) technique. Comparison of the results shows the superiority of the neural network models over the regression models.     

Process optimization of preparing spherical titania colloids with uniform distribution using artificial neural networks

Optimal operating variables for preparing submicron uniform titania colloids were estimated using the artificial neural networks (ANN) modeling and the process optimization algorithms. Titania colloids were synthesized by a sol–gel method using mixture recipes of titanium tetraisopropoxide (TTIP), NH₃, and H₂O with ethanol/acetonitrile under temperature-controlled conditions. Different sets of the operating variables, such as [NH₃], [H₂O], and reaction temperature, were selected within an operating range to carry out Design of Experiment to evaluate the prepared particle size (PS) and the particle size distribution (PSD) data. The relationship between the operating variables and PS and PSD of the prepared samples can be constructed by an ANN modeling approach. The built ANN model was then used to predict PS and PSD values corresponding to the operating variables. The optimal operating conditions to fabricate different PS values with narrow PSD were determined by the ANN model with the optimization method. Meanwhile, the monodispersed colloids between 150 and 400 nm were fabricated using the determined optimal operating conditions.     

Fabrication and characterization of zein-based nanofibrous scaffolds by an electrospinning method

Electrospun zein membranes were prepared using DMF as solvent. By changing the solution concentration, the electrospinning voltage and the distance between the spinneret and collector, nanofibrous meshes without bead defects could be obtained. In order to improve the mechanical strength of the hydrated zein meshes, core-shell-structured nanofibrous membranes with PCL as the core material and zein forming the shell were prepared by coaxial electrospinning. The core-shell structure of the composite fibers was confirmed by SEM characterization of the fibers, either extracted with chloroform to remove the inner PCL, or elongated to expose their cross-section. The composition and average diameter of the composite fibers could be modulated by the feed rate of the inner PCL solution. It was found that the core-shell fibrous membranes have similar wettability to the electrospun zein mesh. The presence of PCL in the fibers could significantly improve the mechanical properties of the zein membrane.