Wavelet Neural Network and Its Application to the Inclusion of -Cyclodextrin with Benzene Derivatives

A wavelet neural network (WNN) was constituted and applied to the inclusion complexation of β-cyclodextrin with mono- and 1,4-disubstituted benzenes. The association constant (Ka) values have been calculated by the WNN from substituent molar refraction (Rm), hydrophobic constant (π), and Hammett constant (σ) of the guest compounds as input parameters. The excellent prediction results with a correlation coefficient of 0.992 and standard deviation of 0.089 suggested that β-CD inclusion complexation is mainly driven by van der Waals force, hydrophobic interaction, and electronic effects.