Research on Assistant Diagnostic Method of TCM Based on Multi Classifier Integration

DOI

10.2991/amms-17.2017.83How to use a DOI?

Keywords

TCM diagnosis; weighted bipartite graph; ProSVM; classifier integration

Abstract

TCM diagnosis is difficult because of the variety of syndromes and the lack of uniform norms. The traditional Chinese medicine auxiliary diagnosis and treatment system refers to the computer aided system which uses computer modeling technology to assist TCM doctors in recording diseases, prompt diagnosis, assisting prescriptions, and performing some telemedicine and teaching. In this paper, hypertension is taken as an example to study the auxiliary diagnosis of TCM, Based on the classification of symptoms and syndrome elements, a method of TCM assistant diagnosis based on multi classifier ensemble is proposed. This paper studies four classification algorithms: Naive Bayes, Weighted bipartite graph, SVM and ProSVM. To take full advantages of the diversity of different algorithms, a intelligent diagnosis procedure is proposed which could provide technical support for hypertension diagnosis. The effect of the integration was better than that of single classifier, with the average precision increased by 10% to 20%.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yonghong Xie
AU  - Yuyang Yan
AU  - Jianyuan Li
AU  - Dezheng Zhang
PY  - 2017/11
DA  - 2017/11
TI  - Research on Assistant Diagnostic Method of TCM Based on Multi Classifier Integration
BT  - Proceedings of the 2017 International Conference on Applied Mathematics, Modeling and Simulation (AMMS 2017)
PB  - Atlantis Press
SP  - 371
EP  - 376
SN  - 1951-6851
UR  - https://doi.org/10.2991/amms-17.2017.83
DO  - 10.2991/amms-17.2017.83
ID  - Xie2017/11
ER  -