检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]浙江科技学院信息与电子工程学院,浙江杭州310012
出 处:《航天医学与医学工程》2013年第2期125-130,共6页Space Medicine & Medical Engineering
基 金:浙江省自然科学基金(Y1100219)
摘 要:目的研究一种心肌梗死(MI)12导高频心电信号(ECG)全局特征提取方法,以实现阶段性MIECG自动分类识别。方法收集PTB诊断数据库中的健康状态ECG,早期MI ECG,急性期MI ECG,恢复期MI ECG进行研究。提出一种基于联合能量百分比(EP)搜索的二维线性判别法(2D-LDA)对12导高频ECG进行融合特征提取,并进行基于线性分类器的分类。结果各类别分别获得了90.28%~99.24%的分类精度,与常规PCA和LDA法相比,平均分类精度提高了7%~9.7%。结论文中的方法能从12导高频ECG中提取数量较小且分类效果理想的全局心电特征。Objective To discriminate electrocardiogram (ECG) signals automatically in different myocardial infarction (MI) stages, a new technique that extracts the global features from 12-lead high frequency ECG is studied. Methods The data for analysis was collected from PTB clinical diagnostic database including health control (HC), MI in early stage (MIES), MI in acute stage (MIAS) and MI in recover stage (MIRS). Two- dimensional linear discrimination analysis (2D-LDA) was introduced to extract the global features from 12- lead high frequency ECG signals. The joint energy percentage (EP) search method was used to determine the feature projecting vectors during 2D-LDA. The classification was performed using linear classifiers. Results An average classification accuracy of 90.28% to 99.24% could be achieved for the different classes, and the overall classification accuracy could be increased by 7 to 9.7 percentages compared with that of the conven tional PCA and LDA method. Conclusion The classifiable global features with relatively lower dimensionality could be extracted from 12-lead high frequency ECGs using the proposed method.
分 类 号:R540.4[医药卫生—心血管疾病]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.249