Machine Learning
Advances in kernel methods: support vector learning
Advances in kernel methods: support vector learning
An introduction to support Vector Machines: and other kernel-based learning methods
An introduction to support Vector Machines: and other kernel-based learning methods
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
| Hi-index | 0.00 |
Identifying and explaining the property of Chinese Materia Medica (CMM) is an important and urgent mission in recent CMM researches. In the present work, we built a combination system for predicting the cold/hot property of CMM based on chemical material basis. A novel strategy, weight center treatment, was used to solve the problem that the chemical description was unable to be applied to CMM. As the results of prediction, the accuracy of 83.3% and 81.0% for the training and the test set, respectively, indicates that this system is a useful tool to predict the property of unidentified folk herbs and foreign herbs. It will characterize these herbs with traditional Chinese medicine properties so as to design new CMM formulas for better therapeutics. Moreover, we found some interesting explanation about the property of CMM based on chemical information by using the selected descriptors. It will give new insight into the CMM property from the standpoint of chemistry.