SUPPORT VECTOR MACHINE REGRESSION FOR REACTIVITY PARAMETERS OF VINYL MONOMERS
Xinliang Yu, Xueye Wang, JIANFANG CHEN · Journal of the Chilean Chemical Society · 2011
Recently, the support vector machine (SVM), as a novel type of learning machine, has been introduced to solve chemical problems.In this study, ε-support vector regression (ε-SVR) and ν-support vector regression (ν-SVR) were, respectively, used to construct quantitative structure-property relationship (QSPR) models of Q and e parameters in the Q-e scheme, which is remarkably useful in the interpretation of the reactivity of a monomer in free-radical copolymerizations.The quantum chemical descriptors used to developed the SVR models were calculated from styrene and radicals with structures CH 3 CH 2 C 1 H 2 -C 2 HR 3 • (C 1 H 2 =C 2 HR 3 + CH 3 CH 2 • → CH 3 CH 2 C 1 H 2 -C 2 HR 3 •).The optimum ε-SVR model of lnQ (C= 9, ε =0.05 and γ =0.2) and the optimum ν-SVR model of e (C=100, ν = 0.5 and γ =0.4) produced low root mean square (rms) errors for prediction sets: 0.318 and 0.266, respectively.Thus, applying SVR to predict parameters Q and e is successful.