摘要
基于特征提取和多模板匹配的心律失常检测算法通过样本数据库创建模板库,对模板库进行特征提取以创建特征库,同时建立索引与模板库关联,然后使用特征库中的模板与待检测心电信号进行粗匹配运算,当粗匹配的相关系数大于预设阀值后,再利用索引加载相关模板进行细匹配运算。使用MIT-BIH数据库的数据验证基于特征提取和多模板匹配的心律失常检测算法的效果理想。
The paper introduces an arrhythmia detection algorithm based on feature extraction and multiple template matching.The algorithm creates the template database from the sample database.In order to create the feature database,the algorithm extracts the features of the template database and creates the indexes associated with the corresponding template database.Then,templates of the feature database and the Electrocardiography（ECG） are used to be inspected to execute the rough matching algorithm.If the cross-correlation of the rough matching is bigger than the predefined threshold,the indexes are used to load the corresponding template and execute the fine matching algorithm.The experimental results,verified by using MIT-BIH database,show the algorithm can guarantee the detection accuracy.
出处
《广西科学院学报》
2012年第1期7-10,共4页
Journal of Guangxi Academy of Sciences
关键词
检测系统
算法
特征提取
相关系数
多模板匹配
detecting system
algorithm
feature database
cross-correlation
multiple template matching
