穿戴式心电信号伪差识别算法的研究及应用  

Research and Application of Artifact Identification Methodfor Wearable ECG Devices

作　　者：上官卫华 李烨[2] 吴敏[1] SHANGGUAN Weihua;LI Ye;WU Min(School of Software Engineering,University of Science and Technology of China,Hefei,Anhui 230026,China;Institute of Biomedical and Health Engineering,Shenzhen Institutes of Advanced Technology,Chinese Academy of Sciences,Shenzhen,Guangdong 518055,China)

机构地区：[1]中国科学技术大学软件学院,安徽合肥230026 [2]中国科学院深圳先进技术研究院生物医学信息技术研究中心,广东深圳518055

出　　处：《北京理工大学学报》2021年第6期665-670,共6页Transactions of Beijing Institute of Technology

基　　金：国家科技重大专项(2013ZX03005013-005)。

摘　　要：针对穿戴式心电监测设备普遍存在的运动和设备伪差问题,提出了基于心电幅度突变度和突变分布连通性、变换后心电极大极小值对凌乱度,以及异常心搏特征等设计的伪差识别组合算法.通过在心电自动分析三个关键环节嵌入组合算法实现伪差识别,并选择了3种设备4种数据样本进行算法验证.结果表明,组合算法伪差识别灵敏度可达98.35%,可将QRS检出正确率提高3.08%,且并未增加心电自动分析运算时长,算法不依赖特定硬件设备,可应用到各类穿戴式设备的心电数据分析中,具有普适且高效的特点.The electrocardiogram(ECG)signals from wearable ECG monitoring equipment usually contain movement and device artifact.In this paper,a combined artifact recognition algorithm was developed based on the mutation degree of ECG amplitude and the connectivity of mutation distribution,the disorder degree of transformed ECG maximum and minimum values,and abnormal cardiac beat characteristics,etc.Embedding three key links in ECG automatic analysis,the combined artifact recognition algorithm was carried out,and selecting four kinds of data samples from three kinds of equipment,the algorithm was verified.Test results show that the combined artifact recognition algorithm can provide an artifact recognition sensitivity up to 98.35%,and improve QRS detection accuracy by 3.08%,at the same time,make the ECG automatic analysis operation time no increase and no rely on specific hardware equipment.The combined artifact recognition algorithm can be applied to ECG data analysis of various wearable devices universally and efficiently.

关 键 词：穿戴式心电采集 心电伪差 突变点 凌乱度 

分 类 号：TN911.7[电子电信—通信与信息系统]