Artificial Neural Network-Genetic Algorithm Approach to Optimize Media Constituents for Enhancing Lipase Production by a Soil Microorganism

Results of lipase production by a soil microorganism, expressed in terms of lipolytic activities of the culture were modeled and optimized using artificial neural network (ANN) and genetic algorithm (GA) techniques, respectively. ANN model, developed based on back propagation algorithm, were highly accurate in predicting the system with coefficient of determination (R ²) value being close to 0.99. Optimization using GA, based on the ANN model developed, resulted in the following values of the media constituents: 9.991 ml/l oil, 0.100 g/l MgSO₄ and 0.009 g/l FeSO₄. And a maximum value of 7.69 U/ml of lipolytic activity at 72 h of culture was obtained using the ANN-GA method, which was found to be 8.8% higher than the maximum values predicted by a statistical regression-based optimization technique-response surface methodology.     

A comparative study of diesel analysis by FTIR, FTNIR and FT-Raman spectroscopy using PLS and artificial neural network analysis

Diesel properties determined by ASTM reference methods as cetane index, density, viscosity, distillation temperatures at 50% (T50) and 85% (T85) recovery, and the total sulfur content (%, w/w) were modeled by FTIR-ATR, FTNIR, and FT-Raman spectroscopy using partial last square regression (PLS) and artificial neural network (ANN) spectral analysis. In the PLS models, 45 diesel samples were used in the training group and the other 45 samples were used in the validation. In the ANN analysis a modular feedforward network was used. Sixty diesel samples were used in the neural network training and other 30 samples were used in the validation. Two different ATR configurations were compared in the FTIR, a conventional (ATR1) and an immersion (ATR2) cell. The ATR1 cell presented the best results, with smaller prediction errors (root mean square error of prediction, RMSEP). The comparison of the three PLS models (FTIR-ATR1, FTNIR, and FT-Raman) shows that reasonable values of R² and RMSEP were obtained by the FTIR-ATR1 and FTNIR models in the evaluation of density, viscosity, and T50. The PLS/FT-Raman models presented reasonable results only for the T50 property. None of the techniques was able to generate suitable PLS calibration models for the determination of sulfur content. The ANN/FT-Raman models presented the best performances, with all models presenting R²-values above 85% some of them with RMSEP values significantly smaller than those obtained with FTIR-ATR and FTNIR. The ANN/FT-Raman and ANN/FTIR-ATR1 models were able to estimate the total sulfur content of diesel with 0.01% (w/w) accuracy.     

Combining convolutional neural networks and in‐line near‐infrared spectroscopy for real‐time monitoring of the chromatographic elution process in commercial production of notoginseng total saponins

The chromatographic elution process is a key step in the production of notoginseng total saponins. Due to quality variability of loading samples and resin capacity decreasing over cycle time, saponins, especially the five main saponins of notoginseng total saponins, need to be monitored in real time during the elution process. In this study, convolutional neural networks, one of the most popular deep learning methods, were used to develop quantitative calibration models based on in‐line near‐infrared spectroscopy for notoginsenoside R₁, ginsenosides Rg₁, Re, Rb₁ and Rd, and their sum concentration, with root mean square error of prediction values of 0.87, 2.76, 0.60, 1.57, 0.28, and 4.99 mg/mL, respectively. Partial least squares calibration models were also developed for model performance comparison. Results show predicted concentration profiles outputted by both the convolutional neural network models and partial least squares models show agreements with the real trends defined by reference measurements, and can be used for elution process monitoring and endpoint determination. To the best of our knowledge, this is the first reported case study of combining convolutional neural networks and in‐line near‐infrared spectroscopy for monitoring of the chromatographic elution process in commercial production of botanical drug products.     

Determination of carbon-bonded sulfur in soils by hydriodic acid reduction and hydrogen peroxide oxidation

A sequential extraction method has been developed for the determination of carbon-bonded sulfur in soils. The soil sample has been sequentially reduced with HI and oxidized with hydrogen peroxide, and finally the residue has been digested with a mixture of nitric acid and perchloric acid. All inorganic sulfur components and ester sulfur has been reduced to H₂S by HI except the unreducible sulfur including pyritic sulfur, carbon-bonded sulfur and a previously unidentified sulfur fraction. Whereas a part of the carbon-bonded sulfur has been dissolved in the HI reducing solution another part of carbon-bonded sulfur was removed by hydrogen peroxide oxidation. The total carbon-bonded sulfur compose for oxic soils of the HI-dissolved sulfur and the H₂O₂-oxidized sulfur. However, because the pyritic sulfur can be completely decomposed by H₂O₂, this form of sulfur should be subtracted from the sum of the two sulfur fractions in case of anoxic soils. Unidentified sulfur components were also detected in the residue after the sequential extraction.     

Prediction of Carbon Dioxide Adsorption via Deep Learning

Porous carbons with different textural properties exhibit great differences in CO₂ adsorption capacity. It is generally known that narrow micropores contribute to higher CO₂ adsorption capacity. However, it is still unclear what role each variable in the textural properties plays in CO₂ adsorption. Herein, a deep neural network is trained as a generative model to direct the relationship between CO₂ adsorption of porous carbons and corresponding textural properties. The trained neural network is further employed as an implicit model to estimate its ability to predict the CO₂ adsorption capacity of unknown porous carbons. Interestingly, the practical CO₂ adsorption amounts are in good agreement with predicted values using surface area, micropore and mesopore volumes as the input values simultaneously. This unprecedented deep learning neural network (DNN) approach, a type of machine learning algorithm, exhibits great potential to predict gas adsorption and guide the development of next‐generation carbons.     

A comparative study concerning chromatographic retention and computed partition coefficients of some precursors of peraza crown ethers

Retention indices for some precursors of peraza crown ethers were determined by reversed phase high-performance thin layer chromatography on RP-18 plates with methanol-water in different volume proportions as mobile phase. The Log P values for the same compounds were calculated using different computer programs: SciQSAR, SciLogP, Chem3D Ultra 8.0, XLOGP (based on atom contributions), Chemaxon and KOWWIN (based on atom/fragment contributions), cLogP (based on fragmental contributions), ALOGPS and IAlogP (based on atom-type electrotopological-state indices and neural network modeling). A comparative study concerning lipophilic parameters (R_M0, b and ϕ0) and computed partition coefficients has been developed. Taking into account the correlation coefficients between determined and calculated Log P values, it seems that R_M0 and b are less suitable than ϕ₀ for estimating lipophilicity of the compounds investigated, and cLogP and ALOGPS provide the best correlations with experimental values.     

A Radioisotope Flow-Circulation Tracer Method for Determination of Sulfur Uptake and Exchange

A combined radioactive flow-circulation tracer method has been developed and applied to a CoMo/Al₂O₃ catalyst for measurement of sulfur uptakes and of catalyst - gas phase sulfur exchange in the H₂S partial pressure range of 2–47 kPa and the temperature range of 373–673 K. Equilibrium between gas-phase and catalyst sulfur species was rapidly achieved. A substantial part of the sulfur uptake was retained as adsorbed (reversible) sulfur species. The exchange of sulfur increased with increase in temperature up to 573 K and in H₂S partial pressure up to 4 kPa.     

Multiobjective optimization of a free radical bulk polymerization reactor using genetic algorithm

A multiobjective optimization technique has been developed for free radical bulk polymerization reactors using genetic algorithm. The polymerization of methyl methacrylate in a batch reactor has been studied as an example. The two objective functions which are minimized are the total reaction time and the polydispersity index of the polymer product. Simultaneously, end‐point constraints are incorporated to attain desired values of the monomer conversion (x_m) and the number average chain length (μ_n). A nondominated sorting genetic algorithm (NSGA) has been adapted to obtain the optimal control variable (temperature) history. It has been shown that the optimal solution converges to a unique point and no Pareto set is obtained. It has been observed that the optimal solution obtained using the NSGA for multiobjective function optimization compares very well with the solution obtained using the simple genetic algorithm (SGA) for a single objective function optimization problem, in which only the total reaction time is minimized and the two end‐point constraints on x_m and μ_n are satisfied.     

Homolytic Decomposition of Sulfonyl Chlorides

The products, kinetic parameters, and activation entropy of thermal decomposition of sulfonyl chloride groups in chlorosulfonated polyethylene (CSPE) have been studied for the first time, and it has been demonstrated that the decomposition mechanism involves simultaneous cleavage of two bonds (carbon–sulfur and sulfur–chlorine) to give an SO₂ molecule and two free radicals, which can be useful in the process of polymer structuring. The radical mechanism has been confirmed by the formation of 2,3-diphenyl-2,3- dimethylbutane on heating CSPE in isopropylbenzene. The simultaneous cleavage of two bonds is supported by the low activation energy and pre-exponential factor in the Arrhenius equation, as well as by negative activation entropy values.     

Potentiometric estimation of sulfide ion using the Fe(III)-EDTA complex

The Fe(III)-EDTA complex reacts with sulfide ion in a fast electron transfer reaction, oxidising the latter to elemental sulfur and getting itself reduced to Fe(II). The reaction has been developed for the quantitative estimation of sulfide ion by titration against the Fe(III)-EDTA complex, measuring the redox potential of the system. Repeated use of a given quantity of the complex solution by the process of regeneration has been demonstrated. The possibility of its practical application in liquid phase oxidation processes of recovering sulfur from H₂S is emphasized.     

Sulfur containing polymers.: Aromatic polydithiocarbonates and polythiocarbonates: synthesis and thermal properties

New polydithiocarbonates and polythiocarbonates were obtained by interfacial polymerization of bis(4-mercaptophenyl)methane, bis(4-mercaptophenyl)ether and bis(4-mercaptophenyl)sulfide with phosgene, bisphenol A bischloroformate and bisphenol A polycarbonate oligomers (-OH/-O-CO-Cl terminated). Polymerization process was carried out under interfacial conditions using a phase-transfer catalyst, as earlier described for the synthesis of polydithiocarbonates and polythiocarbonates from 2,2-bis(4-mercaptophenyl)propane. The structures of the polymers were examined by IR and NMR spectroscopies; their thermal properties were investigated by thermogravimetric analysis and differential scanning calorimetry. In particular, the effect of the substitution of one or both the ethereal oxygen atoms of the carbonate group by sulfur has been analyzed by comparing the T_g values and the ability to crystallize of the sulfur containing polymers with those of the corresponding polycarbonates.     

Simultaneous determination of iron and aluminium by differential kinetic spectrophotometric method and chemometrics

A differential kinetic spectrophotometric method was researched and developed for the simultaneous determination of iron and aluminium in food samples. It was based on the direct reaction kinetics and spectrophotometry of these two metal ions with Chrome Azurol S (CAS) in ethylenediamine-hydrochloric acid buffer (pH 6.3). The results were interpreted with the use of chemometrics. The kinetic runs and the visible spectra of the complex formation reaction were studied between 540 and 750 nm every 30 s over a total period of 285 s. A set of synthetic metal mixture samples was used to build calibrations models. These were based on the spectral and kinetic two-way data matrices, which were processed separately by the radial basis function-artificial neural network (global RBF-ANN) method. The prediction performance of these models was poorer than that from the combined kinetic-spectral three-way array, which was similarly processed by the same method (% relative prediction error (RPE_T) = 5.6). These results demonstrate that improved predictions can be obtained from the data array, which has more information, and that appropriate chemometrics methods can enhance analytical performance of simple techniques such as spectrophotometry.Other chemometrics models were then applied: N-way partial least squares (NPLS), parallel factor analysis (PARAFAC), back propagation-artificial neural network (BP-ANN), single radial basis function-artificial neural network (RBF-ANN), and principal component neural network (PC-RBF-ANN). There was no substantial difference between the methods with the overall %RPE_T range being 5.0-5.8. These two values corresponded to the NPLS and BP-ANN models, respectively. The proposed method was applied for the determination of iron and aluminium in some commercial food samples with satisfactory results.     

Dynamic modelling of milk ultrafiltration by artificial neural network

Artificial neural networks (ANNs) have been used to dynamically model crossflow ultrafiltration of milk. It aims to predict permeate flux, total hydraulic resistance and the milk components rejection (protein, fat, lactose, ash and total solids) as a function of transmembrane pressure and processing time. Dynamic modelling of ultrafiltration performance of colloidal systems (such as milk) is very important for designing of a new process and better understanding of the present process. Such processes show complex non-linear behaviour due to unknown interactions between compounds of a colloidal system, thus the theoretical approaches were not being able to successfully model the process. In this work, emphasis has been focused on intelligent selection of training data, using few training data points and small network. Also it has been tried to test the ANN ability to predict new data that may not be originally available. Two neural network models were constructed to predict the flux/total resistance and rejection during ultrafiltration of milk. The results showed that there is an excellent agreement between the validation data (not used in training) and modelled data, with average errors less than 1%. Also the trained networks are able to accurately capture the non-linear dynamics of milk ultrafiltration even for a new condition that has not been used in the training process.