[Prediction and estimation on molar response values of alkane using molecular subgraph].
Lists
Only you see this
Abstract
A new method based on topographical subgraph of alkanes is proposed and used for molar response values of alkanes. A novel coding, which derived from the numbers of molecular subgraph, is used to characterize molecular structure of alkanes. It showed that there is a very good correlation between the coding and molar response values. The results of multiple linear regression are as follows. Molar response values (SM) on FID: SM = 89.579 - 56.579x1 - 40.579x2 - 18.191x 3 - 2.677x4 + 11.818x5 + 25.690x6 + 40.421x7 + 54.421x8 + 13.926x9 + 15.524x10 + 13.923x11 + 13.857x12 + 30.079x13 + 30.403x14 + 32.677x15 + 29.030x16, N = 50, r = 0.9983, S = 1.9342; Molar response values (SM) on TCD: SM = 139.799 - 62.251x2 - 49.214x3 - 31.244x4 - 15.992x5 + 0x6 + 13.201x7 + 27.201x8 + 11.152x9 + 9.225x10 + 8.427x11 + 10.041x12 + 22.452x13 + 14.977x14 + 22.318x16, N = 32, r = 0.9963, S = 1.7668. Where r, S and N are regression coefficient, residual standard deviation and data number, respectively. Having tested the modeling by using back-propagation neural network (BPNN) and leave-one-out method, we got the correlation coefficient of cross validation, 0.989.
BibTeX
@inproceedings{chen1999prediction,
author = {Guanhua Chen and Zhang Li},
title = {{[Prediction and estimation on molar response values of alkane using molecular subgraph].}},
booktitle = {PubMed},
year = {1999},
}Loading related content...