Prediction of autoignition temperatures (AITs) for hydrocarbons and compounds containing heteroatoms by the quantitative structure-property relationship

Yeong Suk Kim, Sung Kwang Lee, Jae Hyun Kim, Jung Sup Kim, Kyoung Tai No

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

Regression models that are useful for the explanation and prediction of autoignition temperatures of diverse compounds were provided by a quantitative structure property relationships study (QSPR). Genetic functional approximation was used to find the best multiple linear regression within 72 molecular descriptors. After validation by correlation of the prediction set, nine descriptor models were evaluated in the best model. The nine descriptors were Ial, Ike, radius of gyration, 1χv, SC-2, the Balaban index JX, density, Kappa-3-AM and Jurs-FNSA-2, and information of structure features and their interactions was provide. The result of the best regression model showed that the square of the correlation coefficient (R2) for the autoignition temperature of the 157-member training set was 0.920, and the root mean square error (RMSE) was 25.876. The R2 of AIT for a 43-member prediction set was 0.910, and the RMSE was 28.968.

Original languageEnglish
Pages (from-to)2087-2092
Number of pages6
JournalJournal of the Chemical Society. Perkin Transactions 2
Issue number12
Publication statusPublished - 2002 Dec 1

Fingerprint

Hydrocarbons
Mean square error
Temperature
Linear regression

All Science Journal Classification (ASJC) codes

  • Chemistry(all)

Cite this

@article{08dc48e5353e4eea86cdc1dbfb054915,
title = "Prediction of autoignition temperatures (AITs) for hydrocarbons and compounds containing heteroatoms by the quantitative structure-property relationship",
abstract = "Regression models that are useful for the explanation and prediction of autoignition temperatures of diverse compounds were provided by a quantitative structure property relationships study (QSPR). Genetic functional approximation was used to find the best multiple linear regression within 72 molecular descriptors. After validation by correlation of the prediction set, nine descriptor models were evaluated in the best model. The nine descriptors were Ial, Ike, radius of gyration, 1χv, SC-2, the Balaban index JX, density, Kappa-3-AM and Jurs-FNSA-2, and information of structure features and their interactions was provide. The result of the best regression model showed that the square of the correlation coefficient (R2) for the autoignition temperature of the 157-member training set was 0.920, and the root mean square error (RMSE) was 25.876. The R2 of AIT for a 43-member prediction set was 0.910, and the RMSE was 28.968.",
author = "Kim, {Yeong Suk} and Lee, {Sung Kwang} and Kim, {Jae Hyun} and Kim, {Jung Sup} and No, {Kyoung Tai}",
year = "2002",
month = "12",
day = "1",
language = "English",
pages = "2087--2092",
journal = "Journal of the Chemical Society, Perkin Transactions 2",
issn = "1470-1820",
publisher = "Royal Society of Chemistry",
number = "12",

}

Prediction of autoignition temperatures (AITs) for hydrocarbons and compounds containing heteroatoms by the quantitative structure-property relationship. / Kim, Yeong Suk; Lee, Sung Kwang; Kim, Jae Hyun; Kim, Jung Sup; No, Kyoung Tai.

In: Journal of the Chemical Society. Perkin Transactions 2, No. 12, 01.12.2002, p. 2087-2092.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Prediction of autoignition temperatures (AITs) for hydrocarbons and compounds containing heteroatoms by the quantitative structure-property relationship

AU - Kim, Yeong Suk

AU - Lee, Sung Kwang

AU - Kim, Jae Hyun

AU - Kim, Jung Sup

AU - No, Kyoung Tai

PY - 2002/12/1

Y1 - 2002/12/1

N2 - Regression models that are useful for the explanation and prediction of autoignition temperatures of diverse compounds were provided by a quantitative structure property relationships study (QSPR). Genetic functional approximation was used to find the best multiple linear regression within 72 molecular descriptors. After validation by correlation of the prediction set, nine descriptor models were evaluated in the best model. The nine descriptors were Ial, Ike, radius of gyration, 1χv, SC-2, the Balaban index JX, density, Kappa-3-AM and Jurs-FNSA-2, and information of structure features and their interactions was provide. The result of the best regression model showed that the square of the correlation coefficient (R2) for the autoignition temperature of the 157-member training set was 0.920, and the root mean square error (RMSE) was 25.876. The R2 of AIT for a 43-member prediction set was 0.910, and the RMSE was 28.968.

AB - Regression models that are useful for the explanation and prediction of autoignition temperatures of diverse compounds were provided by a quantitative structure property relationships study (QSPR). Genetic functional approximation was used to find the best multiple linear regression within 72 molecular descriptors. After validation by correlation of the prediction set, nine descriptor models were evaluated in the best model. The nine descriptors were Ial, Ike, radius of gyration, 1χv, SC-2, the Balaban index JX, density, Kappa-3-AM and Jurs-FNSA-2, and information of structure features and their interactions was provide. The result of the best regression model showed that the square of the correlation coefficient (R2) for the autoignition temperature of the 157-member training set was 0.920, and the root mean square error (RMSE) was 25.876. The R2 of AIT for a 43-member prediction set was 0.910, and the RMSE was 28.968.

UR - http://www.scopus.com/inward/record.url?scp=0036934010&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036934010&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0036934010

SP - 2087

EP - 2092

JO - Journal of the Chemical Society, Perkin Transactions 2

JF - Journal of the Chemical Society, Perkin Transactions 2

SN - 1470-1820

IS - 12

ER -