کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
1168955 960613 2008 8 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
Prediction of air-to-blood partition coefficients of volatile organic compounds using genetic algorithm and artificial neural network
موضوعات مرتبط
مهندسی و علوم پایه شیمی شیمی آنالیزی یا شیمی تجزیه
پیش نمایش صفحه اول مقاله
Prediction of air-to-blood partition coefficients of volatile organic compounds using genetic algorithm and artificial neural network
چکیده انگلیسی

An artificial neural network (ANN) was constructed and trained for the prediction of air-to-blood partition coefficients of volatile organic compounds. The inputs of this neural network are theoretically derived descriptors that were chosen by genetic algorithm (GA) and multiple linear regression (MLR) features selection techniques. These descriptors are: R maximal autocorrelation of lag 1 weighted by atomic Sanderson electronegativities (R1E+), electron density on the most negative atom in molecule (EDNA), maximum partial charge for C atom (MXPCC), surface weighted charge partial surface area (WNSA1), fractional charge partial surface area (FNSA2) and atomic charge weighted partial positive surface area (PPSA3). The standard errors of training, test and validation sets for the ANN model are 0.095, 0.148 and 0.120, respectively. Result obtained showed that nonlinear model can simulate the relationship between structural descriptors and the partition coefficients of the molecules in data set accurately.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Analytica Chimica Acta - Volume 619, Issue 2, 7 July 2008, Pages 157–164
نویسندگان
, ,