Current time in Korea 10:33 Apr 25 (Thu) Year 2024 KCS KCS Publications
KCS Publications
My Journal  Log In  Register
HOME > Search > Browsing(BKCS) > Archives

Bulletin of the Korean Chemical Society (BKCS)

ISSN 0253-2964(Print)
ISSN 1229-5949(Online)
Volume 28, Number 9
BKCSDE 28(9)
September 20, 2007 
 
Title
 Artificial Neural Network Prediction of Normalized Polarity Parameter for Various Solvents with Diverse Chemical Structures
Author
 Aziz Habibi-Yangjeh
Keywords
 Quantitative-structure property relationship, Normalized polarity parameter, Artificial neural networks, Theoretical descriptors
Abstract
 Artificial neural networks (ANNs) are successfully developed for the modeling and prediction of normalized polarity parameter (ETN) of 216 various solvents with diverse chemical structures using a quantitative-structure property relationship. ANN with architecture 5-9-1 is generated using five molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The most positive charge of a hydrogen atom (q+), total charge in molecule (qt), molecular volume of solvent (Vm), dipole moment (μ) and polarizability term (πI) are input descriptors and its output is ETN. It is found that properly selected and trained neural network with 192 solvents could fairly represent the dependence of normalized polarity parameter on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network is applied for prediction of the ETN values of 24 solvents in the prediction set, which are not used in the optimization procedure. Correlation coefficient (R) and root mean square error (RMSE) of 0.903 and 0.0887 for prediction set by MLR model should be compared with the values of 0.985 and 0.0375 by ANN model. These improvements are due to the fact that the ETN of solvents shows non-linear correlations with the molecular descriptors.
Page
 1472 - 1476
Full Text
 PDF

How to access to the WOL for The Bulletin of the Korean Chemical Society ?

The Bulletin of the Korean Chemical Society will be co-published with Wiley-VCH from 2015 towards. The online version of the Journal will thus be available on Wiley Online Library, Wiley(-VCH)'s global online platform.

KCS members can get a free online access to the Bulletin of the Korean Chemical Society in WOL.

Close