Title: Acquisition, representation of characteristics of prescription samples of Chinese medicine and experiments on knowledge mining

Authors: Gao Quanquan, Liu Xiaofeng, Ren Tingge, Sun Yan, Zhang Fan, Chen Yongyi

Addresses: Academy of Math & Systems Science, Chinese Academy of Science, Beijing, 100190, China. ' Beijing University of Chinese Medicine, Beijing, 100029, China. ' Beijing University of Chinese Medicine, Beijing, 100029, China. ' Beijing University of Chinese Medicine, Beijing, 100029, China. ' Beijing University of Chinese Medicine, Beijing, 100029, China. ' Training Center, China Metrorological Administration, Beijing, 100190, China

Abstract: In this paper, firstly, we introduce a feasible method formalising the calculation of information of prescription of Chinese medicine, and discuss quantified representation of attribute characteristics in prescription samples. Based on aforesaid method and representation, prescription samples are classified by pattern recognition system on the basis of SVM. The acquired results are satisfactory, which are also consistent with or close to the general cognition of principal theory of Chinese medicine. Our experience has shown that machine learning method is a feasible solution to mine thinking mode of Chinese medicine experts when they write prescriptions. This method of pattern recognition can be applied in many research fields of Chinese medicine.

Keywords: Chinese medicine; prescription samples; attribute characteristics; characteristics acquisition; SVM; support vector machines; pattern recognition; machine learning; knowledge mining; medical prescriptions.

DOI: 10.1504/IJGCRSIS.2011.041456

International Journal of Granular Computing, Rough Sets and Intelligent Systems, 2011 Vol.2 No.1, pp.1 - 9

Received: 08 Nov 2010
Accepted: 08 Nov 2010

Published online: 28 Feb 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article