摘要
几千年来,中医药领域的无数临床实践与理论研究积累了很多对哮喘病的治疗方剂,已有的基于距离的聚类算法在对哮喘方剂数据的聚类上不太有效。根据哮喘药方数据集高维稀疏性的特点提出一种基于最大频繁项集的层次聚类算法,此算法在哮喘方剂的聚类上取得了较好的效果。基于现有中药数据,设计并实现一个中药方剂数据挖掘平台,该平台将中药数据检索功能和中药数据挖掘功能集成起来,带来了极大的便利。
People have accumulate a large number of formulae by numerous clinical practices and TCM (Traditional Chinese Medicine) theory research on asthma in the past thousands of years. Most of clus- ter algorithms based on distance has bad performance on formulae's dataset. This paper a new hierarchical cluster algorithm based on largest frequent itemset which much better performance on bronchial asthma dataset,and a data mining platform based on the existing TCM data is designed and implemented by integrating TCM data retrieval functions with data mining functions,which brings great convenience.
出处
《广西师范大学学报(自然科学版)》
CAS
北大核心
2009年第3期105-108,共4页
Journal of Guangxi Normal University:Natural Science Edition
基金
国家自然科学基金资助项目(60875038
60721002
60503021)
江苏省高新技术计划(BG2007038)
关键词
频繁项集
相似度
层次聚类
方剂
frequent itemset similarity cluster formulae