The Experts below are selected from a list of 2778 Experts worldwide ranked by ideXlab platform
Dominique Richon - One of the best experts on this subject based on the ideXlab platform.
-
determination of the Normal Boiling Point of chemical compounds using a quantitative structure property relationship strategy application to a very large dataset
Fluid Phase Equilibria, 2013Co-Authors: Farhad Gharagheizi, Dominique Richon, Amir H Mohammadi, Seyyed Alireza Mirkhani, Deresh Ramjugernath, Poorandokht IlanikashkouliAbstract:Abstract In this work, the quantitative structure–property relationship (QSPR) strategy is applied to predict the Normal Boiling Point (NBP) of pure chemical compounds. In order to propose a comprehensive, reliable, and predictive model, a large dataset of 17,768 pure chemical compounds was exploited. The sequential search mathematical method has been observed to be the only viable search method capable for selection of appropriate model parameters (molecular descriptors) with regard to a data set as large as is used in this study. To develop the model, a three-layer feed forward artificial neural network has been optimized using the Levenberg–Marquardt (LM) optimization strategy. Using this dedicated strategy, satisfactory results were obtained and are quantified by the following statistical parameters: average absolute relative deviations of the predicted properties from existing literature values: 3.2%, and squared correlation coefficient: 0.94.
-
Determination of the Normal Boiling Point of chemical compounds using a quantitative structure–property relationship strategy: Application to a very large dataset
Fluid Phase Equilibria, 2013Co-Authors: Farhad Gharagheizi, Amir H Mohammadi, Seyyed Alireza Mirkhani, Poorandokht Ilani-kashkouli, Deresh Ramjugernath, Dominique RichonAbstract:Abstract In this work, the quantitative structure–property relationship (QSPR) strategy is applied to predict the Normal Boiling Point (NBP) of pure chemical compounds. In order to propose a comprehensive, reliable, and predictive model, a large dataset of 17,768 pure chemical compounds was exploited. The sequential search mathematical method has been observed to be the only viable search method capable for selection of appropriate model parameters (molecular descriptors) with regard to a data set as large as is used in this study. To develop the model, a three-layer feed forward artificial neural network has been optimized using the Levenberg–Marquardt (LM) optimization strategy. Using this dedicated strategy, satisfactory results were obtained and are quantified by the following statistical parameters: average absolute relative deviations of the predicted properties from existing literature values: 3.2%, and squared correlation coefficient: 0.94.
-
use of Boiling Point elevation data of aqueous solutions for estimating hydrate stability zone
Industrial & Engineering Chemistry Research, 2007Co-Authors: Amir H Mohammadi, Dominique RichonAbstract:Limited information is available for estimating the hydrate safety margin and controlling gas hydrate formation along pipelines and production facilities. In this work, the possibility of predicting the hydrate safety margin from the Normal Boiling Point of aqueous solution is investigated by developing a predictive method that uses Normal Boiling Point elevation data of aqueous solution in the presence of wide ranges of salt concentrations for determination of hydrate formation region. The developed method considers only the changes in Normal Boiling Point elevation with respect to the Normal Boiling Point of pure water for estimating hydrate stability zone, and therefore there is no need to have the analysis of the solution. As measurement of Normal Boiling Point elevation for the aqueous phase is easier and more accurate than measurement of the hydrate dissociation Point, such a method can reduce experimental costs and efforts. Independent data (not used in developing the correlation) are used to exami...
Peng Bai - One of the best experts on this subject based on the ideXlab platform.
-
prediction of the Normal Boiling Point of oxygen containing organic compounds using quantitative structure property relationship strategy
Fluid Phase Equilibria, 2016Co-Authors: Liangjie Jin, Peng BaiAbstract:Abstract Quantitative structure–property relationship (QSPR) models were applied to predict the Normal Boiling Point (NBP) of oxygen containing organic compounds, including alcohols, phenols, ethers, aldehydes, ketones, carboxylic acids and esters. The total 432 compounds were divided into 3 subsets according to their structure features. For each subset, 8 significant descriptors were selected from the pool of descriptors. Sequentially, the multiple linear regression (MLR) method as well as the non-linear radial basis network (RBN) was used to correlate and predict the NBP of the compounds. RBN model showed higher accuracy with respect to MLR model and Constantinou-Gani (C-G) group contribution method. Comparison with previous QSPR models indicated that the present models could be more general for NBP prediction of organic compounds with certain oxygen containing functional group. In addition, QSPR models for all the 432 compounds were also deduced, and the results confirmed that RBN model performed better in the field of QSPR modeling.
-
Prediction of the Normal Boiling Point of oxygen containing organic compounds using quantitative structure–property relationship strategy
Fluid Phase Equilibria, 2016Co-Authors: Liangjie Jin, Peng BaiAbstract:Abstract Quantitative structure–property relationship (QSPR) models were applied to predict the Normal Boiling Point (NBP) of oxygen containing organic compounds, including alcohols, phenols, ethers, aldehydes, ketones, carboxylic acids and esters. The total 432 compounds were divided into 3 subsets according to their structure features. For each subset, 8 significant descriptors were selected from the pool of descriptors. Sequentially, the multiple linear regression (MLR) method as well as the non-linear radial basis network (RBN) was used to correlate and predict the NBP of the compounds. RBN model showed higher accuracy with respect to MLR model and Constantinou-Gani (C-G) group contribution method. Comparison with previous QSPR models indicated that the present models could be more general for NBP prediction of organic compounds with certain oxygen containing functional group. In addition, QSPR models for all the 432 compounds were also deduced, and the results confirmed that RBN model performed better in the field of QSPR modeling.
-
QSPR study on Normal Boiling Point of acyclic oxygen containing organic compounds by radial basis function artificial neural network
Chemometrics and Intelligent Laboratory Systems, 2016Co-Authors: Liangjie Jin, Peng BaiAbstract:Abstract Radial basis function artificial neural network (RBF-ANN) model was developed to predict the Normal Boiling Point (NBP) of 240 acyclic oxygen containing organic compounds, including alcohols, ethers, aldehydes, ketones, carboxylic acids and esters. The total database was randomly divided into a training set (192), a validation set (24) and a test set (24). 8 significant molecular descriptors, which were used to build the RBF-ANN model, were selected from a pool of descriptors by multi-stepwise regression method. The RBF-ANN model was trained by the Orthogonal Least Squares (OLS) learning algorithm. The biharmonic response surface analysis was used for the optimization of two main tuning parameters in the neural network. The final optimum RBF-ANN model represented by [8- 22 (32) -1] was tested and evaluated by graphic and statistical methods. Y-randomization test and a random split cross validation confirmed the robustness of the RBF-ANN model. The comparison results with the best multiple linear regression function and literature QSPR models showed the superiority of the RBF-ANN model.
Alexandre Varnek - One of the best experts on this subject based on the ideXlab platform.
-
Publicly available models to predict Normal Boiling Point of organic compounds
Thermochimica Acta, 2013Co-Authors: Ioana Oprisiu, Gilles Marcou, Dragos Horvath, Damien Bernard Brunel, Fabien Rivollet, Alexandre VarnekAbstract:Abstract Quantitative structure–property models to predict the Normal Boiling Point ( T b ) of organic compounds were developed using non-linear ASNNs (associative neural networks) as well as multiple linear regression – ISIDA-MLR and SQS (stochastic QSAR sampler). Models were built on a diverse set of 2098 organic compounds with T b varying in the range of 185–491 K. In ISIDA-MLR and ASNN calculations, fragment descriptors were used, whereas fragment, FPTs (fuzzy pharmacophore triplets), and ChemAxon descriptors were employed in SQS models. Prediction quality of the models has been assessed in 5-fold cross validation. Obtained models were implemented in the on-line ISIDA predictor at http://infochim.u-strasbg.fr/webserv/VSEngine.html .
-
Quantitative Structure–Property Relationship (QSPR) Modeling of Normal Boiling Point Temperature and Composition of Binary Azeotropes
Industrial & Engineering Chemistry Research, 2011Co-Authors: Vitaly P. Solov'ev, Ioana Oprisiu, Gilles Marcou, Alexandre VarnekAbstract:Quantitative structure–property relationship (QSPR) modeling of Normal Boiling Point temperature (Taz) and the composition (weight fraction, X1w) of 176 binary azeotropic mixtures was performed using ensemble multiple linear regression analysis and fragment descriptors implemented in ISIDA software. The models have been validated in external 5-fold cross-validations procedure and on an additional test set of 24 azeotropes. The prediction errors (3–4 K for Taz and 10–14 wt % for X1w) are comparable with the noise in experimental data. A simple empirical relationship linking Taz with Boiling Points of two molecular components of azeotrope has been suggested.
-
quantitative structure property relationship qspr modeling of Normal Boiling Point temperature and composition of binary azeotropes
Industrial & Engineering Chemistry Research, 2011Co-Authors: V P Solovev, Ioana Oprisiu, Gilles Marcou, Alexandre VarnekAbstract:Quantitative structure–property relationship (QSPR) modeling of Normal Boiling Point temperature (Taz) and the composition (weight fraction, X1w) of 176 binary azeotropic mixtures was performed using ensemble multiple linear regression analysis and fragment descriptors implemented in ISIDA software. The models have been validated in external 5-fold cross-validations procedure and on an additional test set of 24 azeotropes. The prediction errors (3–4 K for Taz and 10–14 wt % for X1w) are comparable with the noise in experimental data. A simple empirical relationship linking Taz with Boiling Points of two molecular components of azeotrope has been suggested.
Seyyed Alireza Mirkhani - One of the best experts on this subject based on the ideXlab platform.
-
determination of the Normal Boiling Point of chemical compounds using a quantitative structure property relationship strategy application to a very large dataset
Fluid Phase Equilibria, 2013Co-Authors: Farhad Gharagheizi, Dominique Richon, Amir H Mohammadi, Seyyed Alireza Mirkhani, Deresh Ramjugernath, Poorandokht IlanikashkouliAbstract:Abstract In this work, the quantitative structure–property relationship (QSPR) strategy is applied to predict the Normal Boiling Point (NBP) of pure chemical compounds. In order to propose a comprehensive, reliable, and predictive model, a large dataset of 17,768 pure chemical compounds was exploited. The sequential search mathematical method has been observed to be the only viable search method capable for selection of appropriate model parameters (molecular descriptors) with regard to a data set as large as is used in this study. To develop the model, a three-layer feed forward artificial neural network has been optimized using the Levenberg–Marquardt (LM) optimization strategy. Using this dedicated strategy, satisfactory results were obtained and are quantified by the following statistical parameters: average absolute relative deviations of the predicted properties from existing literature values: 3.2%, and squared correlation coefficient: 0.94.
-
Determination of the Normal Boiling Point of chemical compounds using a quantitative structure–property relationship strategy: Application to a very large dataset
Fluid Phase Equilibria, 2013Co-Authors: Farhad Gharagheizi, Amir H Mohammadi, Seyyed Alireza Mirkhani, Poorandokht Ilani-kashkouli, Deresh Ramjugernath, Dominique RichonAbstract:Abstract In this work, the quantitative structure–property relationship (QSPR) strategy is applied to predict the Normal Boiling Point (NBP) of pure chemical compounds. In order to propose a comprehensive, reliable, and predictive model, a large dataset of 17,768 pure chemical compounds was exploited. The sequential search mathematical method has been observed to be the only viable search method capable for selection of appropriate model parameters (molecular descriptors) with regard to a data set as large as is used in this study. To develop the model, a three-layer feed forward artificial neural network has been optimized using the Levenberg–Marquardt (LM) optimization strategy. Using this dedicated strategy, satisfactory results were obtained and are quantified by the following statistical parameters: average absolute relative deviations of the predicted properties from existing literature values: 3.2%, and squared correlation coefficient: 0.94.
Dimitrios P. Tassios - One of the best experts on this subject based on the ideXlab platform.
-
Prediction of vapor pressures and enthalpies of vaporization of organic compounds from the Normal Boiling Point temperature
Fluid Phase Equilibria, 2006Co-Authors: Eleni Panteli, Epaminondas Voutsas, Kostis Magoulas, Dimitrios P. TassiosAbstract:Abstract Recently, our Laboratory proposed a model for the prediction of vapor pressures of organic compounds that requires only the knowledge of the Normal Boiling Point of the compound involved, and a compound specific K f for which generalized expressions for several classes of organic compounds as functions of the Normal Boiling Point and the molecular weight were developed. In this work our model is compared with the one proposed in Lyman's book, which is similar to our model but uses different K f values. The results indicate that our model provides very satisfactory results in the temperature range from the melting up to the Normal Boiling Point and up to the critical, where no hydrogen-bonding is involved. Also, it is proven that the accuracy of our model is much better than that proposed by Lyman, especially for the high molecular weight compounds. Finally, our model is used for the prediction of enthalpies of vaporization at the Normal Boiling Point. Excellent results are obtained that are comparable or better than those obtained with two recommended models in “The Properties of Gases and Liquids” book, where the latter, however, require as input information except from the Normal Boiling Point the critical properties of the compound involved as well.
-
Prediction of vapor pressures of pure compounds from knowledge of the Normal Boiling Point temperature
Fluid Phase Equilibria, 2002Co-Authors: Epaminondas Voutsas, Kostis Magoulas, Maria Lampadariou, Dimitrios P. TassiosAbstract:Abstract A simple method for the prediction of vapor pressures of pure compounds from knowledge of the Normal Boiling Point temperature is presented. Typical errors down to 10−5 bar (1 Pa) are below 20% and are off only by a factor of 2–3 down to 10−9 bar (10−4 Pa), which must be considered very satisfactory considering the simplicity of the method and the uncertainty in the very low vapor pressure data. For higher pressures, up to 5 bar, very satisfactory results are obtained with typical errors below 3% but somewhat higher for alcohols.
-
prediction of Normal Boiling Point temperature of medium high molecular weight compounds
Industrial & Engineering Chemistry Research, 1995Co-Authors: Ioannis N. Tsibanogiannis, Nikolaos S. Kalospiros, Dimitrios P. TassiosAbstract:A simple method for the prediction of the Normal Boiling Point temperatures of medium/high molecular weight compounds is presented requiring as input information the molecular weight and density (at 20°C) only. Excellent results are obtained with an overall average error of 1.7% for the 126 compounds considered. Even if the density is not available, predicted values from a group contribution method can be used
-
Prediction of Normal Boiling Point Temperature of Medium/High Molecular Weight Compounds
Industrial & Engineering Chemistry Research, 1995Co-Authors: Ioannis N. Tsibanogiannis, Nikolaos S. Kalospiros, Dimitrios P. TassiosAbstract:A simple method for the prediction of the Normal Boiling Point temperatures of medium/high molecular weight compounds is presented requiring as input information the molecular weight and density (at 20°C) only. Excellent results are obtained with an overall average error of 1.7% for the 126 compounds considered. Even if the density is not available, predicted values from a group contribution method can be used
