改进关联规则算法在医疗监控中的应用  

Application of an Improved Algorithm of Association Rules in Health Monitoring Center

作　　者：田亚凯 陈小惠[1] 

机构地区：[1]南京邮电大学自动化学院,江苏南京210046

出　　处：《计算机技术与发展》2015年第10期183-186,共4页Computer Technology and Development

基　　金：国家自然科学基金资助项目(61104216);江苏省科技支撑计划项目(BE2011843)

摘　　要：为了方便监护人员能够从监控中心的数据库中及时获取病人的生理参数和病情的关系,文中提出一种改进的Apriori算法。该算法充分利用医疗数据的特点,把整条事务当作一个属性,避免了传统Apriori算法反复扫描事务数据库,从而简化了生成频繁项集的过程。为了验证改进Apriori算法的有效性和可行性,文中将此算法与传统的Apriori算法分别应用到监护系统中,对这两种算法的运行结果进行了对比。结果表明,改进Apriori算法在效率上有明显提高,为监护人员针对一些突发性疾病做出及时诊断提供了良好的决策支持。In order to facilitate supervisors to get the relationship between physiological parameters and disease of patients from monitoring center database timely ,put forward a kind of improved Apriori algorithm. The algorithm makes full use of the characteristics of medical data and regards the entire transaction as an attribute, avoiding the operation that traditional Apriori algorithm repeatedly scans the transac- tion database, so that simplifies the process while generating candidate sets. In order to verify the effectiveness and feasibility of the im- proved Apriori algorithm, both the Apriori algorithm and the new algorithm are applied to the monitoring system, also the results of the two algorithms are compared. The results show that the improved Apriori algorithm has obvious improvement in efficiency, providing a good decision support about some sudden illness for the care staff timely.

关 键 词：数据挖掘 关联规则 APRIORI算法 医疗监护 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]