Prediction of Infinite Dilution Activity Coefficients of Halogenated Hydrocarbons in Water Using Classification and Regression Tree Analysis and Adaptive Neuro-Fuzzy Inference Systems

Abstract

A quantitative structure-infinite dilution activity relationship was developed to predict the infinite dilution activity coefficients of halogenated hydrocarbons, γ∞, in water at 298.15 K. A set of 1,497 zero-to three-dimentional descriptors were used for each molecule in the data set. Classification and regression tree (CART) were successfully used as a descriptor selection method. Three descriptors were selected and used as inputs for the adaptive neuro-fuzzy inference system (ANFIS). The root mean square errors for both calibration and prediction sets are 0.48. The results were compared with those obtained from other models. The results showed that CART-ANFIS can be used as a powerful model for prediction of the infinite dilution activity coefficients of halogenated hydrocarbons.