SciELO - Scientific Electronic Library Online

 
vol.56 número3CHEMICAL STABILITY OF PREDNISONE ORAL SUSPENSION AND DRUG SUBSTANCEMICROW AVE-ASSISTED SYNTHESIS OF LOW-SILICA/ALUMINA-RATIO ZEOLITES FROM GEOTHERMAL SILICA índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Journal of the Chilean Chemical Society

versión On-line ISSN 0717-9707

Resumen

YU, XINLIANG; WANG, XUEYE  y  CHEN, JIANFANG. SUPPORT VECTOR MACHINE REGRESSION FOR REACTIVITY PARAMETERS OF VINYL MONOMERS. J. Chil. Chem. Soc. [online]. 2011, vol.56, n.3, pp. 746-751. ISSN 0717-9707.  http://dx.doi.org/10.4067/S0717-97072011000300006.

Recently, the support vector machine (SVM), as a novel type of learning machine, has been introduced to solve chemical problems. In this study, å- support vector regression (å-SVR) and v-support vector regression (v-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 CH3CH2C1H2-C2HR3· (C1H2=C2HR3 + CH3CH2· - CH3CH2C1H2-C2HR3·). The optimum å-SVR model of lnQ (C= 9, å =0.05 and ã =0.2) and the optimum v-SVR model of e (C=100, v = 0.5 and ã =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.

Palabras clave : free-radical copolymerizations; Q-e scheme; quantum chemical descriptors; structure-property relations; support vector machine.

        · texto en Inglés     · pdf en Inglés