Modeling the Glass Transition Temperature of Polymers via Multipole Moments Using Support Vector Regression

被引：3

作者：

Pei, J. F. ^{[1
]}

Cai, C. Z. ^{[1
]}

Zhu, X. J. ^{[1
]}

Wang, G. L. ^{[1
]}

Yan, B. ^{[1
]}

机构：

[1] Chongqing Univ, Dept Appl Phys, Chongqing 400044, Peoples R China

来源：

FUTURE MATERIAL RESEARCH AND INDUSTRY APPLICATION, PTS 1 AND 2 | 2012年 / 455-456卷

关键词：

Glass transition temperature; polymer; mulitpole moments; support vector regression; regression analysis; STRUCTURE-PROPERTY RELATIONSHIP; NEURAL-NETWORK PREDICTION; CLASSIFICATION; PROTEIN;

D O I：

10.4028/www.scientific.net/AMR.455-456.430

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

This study introduces support vector regression (SVR) approach to model the relationship between the glass transition temperature (Tg) and multipole moments for polymers. SVR was trained and tested via 60 samples by using two quantum chemical descriptors including the molecular traceless quadrupole moment Theta and the molecular average hexadecapole moment Phi. The prediction performance of SVR was compared with that of reported quantitative structure property relationship (QSPR) model. The results show that the mean absolute error (MAE), mean absolute percentage error (MAPE) and root mean square error (RMSE) of training samples and test samples achieved by SVR model, are smaller than those achieved by the QSPR model, respectively. This investigation reveals that SVR-based modeling is a practically useful tool in prediction of the glass transition temperature of polymers.

引用

页码：430 / 435

页数：6

共 21 条

[1]

Bicerano J., 1996, PREDICTION POLYM PRO, V2nd

[2] Predicting the Superconducting Transition Temperature Tc of BiPbSrCaCuOF Superconductors by Using Support Vector Regression [J].

Cai, C. Z. ;

Zhu, X. J. ;

Wen, Y. F. ;

Pei, J. F. ;

Wang, G. L. ;

Zhuang, W. P. .

JOURNAL OF SUPERCONDUCTIVITY AND NOVEL MAGNETISM, 2010, 23 (05) :737-740

[3] Support vector machine classification of physical and biological datasets [J].

Cai, CZ ;

Wang, WL ;

Chen, YZ .

INTERNATIONAL JOURNAL OF MODERN PHYSICS C, 2003, 14 (05) :575-585

[4] Protein function classification via support vector machine approach [J].

Cai, CZ ;

Wang, WL ;

Sun, LZ ;

Chen, YZ .

MATHEMATICAL BIOSCIENCES, 2003, 185 (02) :111-122

[5] SVM-Prot: web-based support vector machine software for functional classification of a protein from its primary sequence [J].

Cai, CZ ;

Han, LY ;

Ji, ZL ;

Chen, X ;

Chen, YZ .

NUCLEIC ACIDS RESEARCH, 2003, 31 (13) :3692-3697

[6]

Camelio P, 1997, J POLYM SCI POL CHEM, V35, P2579, DOI 10.1002/(SICI)1099-0518(19970930)35:13<2579::AID-POLA5>3.0.CO

[7]

2-M

[8]

Dai JF, 2003, ACTA POLYM SIN, P343

[9] Recursive neural networks prediction of glass transition temperature from monomer structure: an application to acrylic and methacrylic polymers [J].

Duce, Celia ;

Micheli, Alessio ;

Solaro, Roberto ;

Starita, Antonina ;

Tine, Maria Rosaria .

JOURNAL OF MATHEMATICAL CHEMISTRY, 2009, 46 (03) :729-755

[10] NEURAL-NETWORK PREDICTION OF GLASS-TRANSITION TEMPERATURES FROM MONOMER STRUCTURE [J].

JOYCE, SJ ;

OSGUTHORPE, DJ ;

PADGETT, JA ;

PRICE, GJ .

JOURNAL OF THE CHEMICAL SOCIETY-FARADAY TRANSACTIONS, 1995, 91 (16) :2491-2496

← 1 2 3 →