远程健康监护系统监护信息预报方法  

Predicting method of monitoring information in telemonitoring system

作　　者：蒋贤海[1] 谢存禧[2] 

机构地区：[1]广东水利电力职业技术学院,广州501635 [2]华南理工大学机械与汽车工程学院,广州510640

出　　处：《北京生物医学工程》2013年第4期387-391,共5页Beijing Biomedical Engineering

基　　金：粤港关键领域重点突破项目(20090101-1)资助

摘　　要：目的针对远程健康监护系统中系统预报未来的监护信息数值问题,提出一种基于粒子群优化算法(particle swarm optimization,PSO)的监护信息预报方法。方法采用PSO算法确定预报模型参数,应用最小二乘支持向量机(1east square support vector machine,LS-SVM)对未来监护信息数值进行预报。文中构建了监护信息的LS-SVM预报模型,给出了模型参数确定方法。最后,选择PhysioNet标准数据库中的数据,应用该方法进行了实验。结果实验结果表明该监护信息预报方法是有效的。结论基于PSO算法的远程健康监护系统可较好地预测未来的监护信息值,并能较准确地预报监护对象的健康状态。Objective According to the problem of predicting future monitoring information in tele-health monitoring system,the predicting method of monitoring information is proposed based on particle swarm optimization （PSO）. Methods The parameters of predicting model are given based on PSO in this method,and the least square support vector machine （LS-SVM） is adopted to predict monitoring information. Then,the prediction model of monitoring information based on LS-SVM is constructed,and the method of confirming parameters in the model is proposed. Finally,an experiment is carried out with PhysioNet database. Results The experimental results verify the effectiveness of this predicting method for monitoring information. Conclusions A new method based on PSO can be used to predict future monitoring information in tele-health monitoring system,and the health state of the monitored object can be forecasted accurately.

关 键 词：监护信息 PSO 最小二乘支持向量机 预报 

分 类 号：R318.04[医药卫生—生物医学工程]