A Research to Retention Index of Saturated Alcohols Based on RBF Neural Network

A model of the relationship between the structure of alcohols and their chromatographic retention index has been set by Randic branch index, but the error forecasted was big in many situations because of the complexity and nonlinearity of structure-activity relationship, and it has a high request to the sample selection. A model based on radial basis function (RBF) neural network for determining the relations between the structure of alcohols and their chromatographic retention indices has been set in this paper. The forecasting results are good when it makes use of the RBF neural network to carry out the forecasting, the correlation coefficient has reached 1.000. Therefore, the model is a more satisfactory method for prediction of chromatographic retention indices of organic compounds.