Artificial bee colony-based extraction of non-taxonomic relation between symptom and syndrome in TCM records
by Feng Yuan; Shouqiang Chen; Hong Liu; Liang Xu
International Journal of Computing Science and Mathematics (IJCSM), Vol. 6, No. 6, 2015

Abstract: Research the extraction of non-taxonomic relation between symptom and syndrome in Traditional Chinese Medicine (TCM) records. In the present study, a niche-based artificial bee colony (ABC) algorithm is proposed to address a variety of problems (e.g., low efficiency, slow convergence rate, miss-reporting and etc.) of conventional rule-oriented extraction of non-taxonomic relation. By combing the vast merging/evolution diversity of niche technique and rapid non-taxonomic relation extraction of ABC algorithm, the proposed algorithm was able to resolve the problems of local optimum and rules redundancy. In addition, confirmatory experiment is performed on TCM medical record corpus; the results show that, when compared with the conventional relationship rule mining algorithm, the novel algorithm featured significant improvements in both the individual diversity and the efficiency of extracting effective rules, and thus excavating the results which can be used as references for extraction of non-taxonomic relation between symptom and syndrome in TCM medical records.

Online publication date: Sun, 13-Dec-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computing Science and Mathematics (IJCSM):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com