Search

This paper gives a new method of rough set-based on taste signals identification. Further improve the identification accuracy by dividing regions more appropriate. The simulation data and the latest UCI machine learning taste signal data (Wine Quality) are used to verify the new method, and the new method is compared with other identification algorithms. The results fully show the correctness and effectiveness of the proposed identification method based on rough set.

Least squares support vector machines (LSSVM) has been carried out in order to obtain a statistically meaningful analysis of the extended set of molecules. The combined HF with LSSVM correction approach ???LSSVM/HF??? has been applied to evaluate the transition energies of organic molecules. After LSSVM correction, the RMS deviations of the calculated transition energies reduce from 0.91 to 0.26 eV for HF methods. And, this LSSVM/HF is a excellent method to predict transition energies and extend the reliably and efficiently of calculated transition energies.