COW: a co-evolving memetic wrapper for herb-herb interaction analysis in TCM informatics

Authors:
Dion Detterer;Paul Kwan
Affiliations:
School of Science and Technology, University of New England, Armidale, NSW, Australia;School of Science and Technology, University of New England, Armidale, NSW, Australia
Venue:
PAKDD'11 Proceedings of the 15th international conference on New Frontiers in Applied Data Mining
Year:
2011

Citing 7
Cited 0

Overcoming the Myopia of Inductive Learning Algorithms with RELIEFF

Applied Intelligence
Adaptive Selection Methods for Genetic Algorithms

Proceedings of the 1st International Conference on Genetic Algorithms
An introduction to variable and feature selection

The Journal of Machine Learning Research
Development of traditional Chinese medicine clinical data warehouse for medical knowledge discovery and decision support

Artificial Intelligence in Medicine
Novel two-stage analytic approach in extraction of strong herb-herb interactions in TCM clinical treatment of insomnia

ICMB'10 Proceedings of the Second international conference on Medical Biometrics
Coevolving Memetic Algorithms: A Review and Progress Report

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Wrapper–Filter Feature Selection Algorithm Using a Memetic Framework

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditional Chinese Medicine (TCM) relies heavily on interactions between herbs within prescribed formulae. However, given the combinatorial explosion due to the vast number of herbs available for treatment, the study of herb-herb interactions by pure human analysis is impractical, with computeraided analysis computationally expensive. Thus feature selection is crucial as a pre-processing step prior to herb-herb interaction analysis. In accord with this goal, a new feature selection algorithm known as a Co-evolving Memetic Wrapper (COW) is proposed: COW takes advantage of recent developments in genetic algorithms (GAs) and memetic algorithms (MAs), evolving appropriate feature subsets for a given domain. As part of preliminary research, COW is demonstrated to be effective in selecting herbs in the TCM insomnia datatset. Finally, possible future applications of COW are examined, both within TCM research and in broader data mining contexts.