当前位置: X-MOL 学术Sci. China Inf. Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A robust QRS detection and accurate R-peak identification algorithm for wearable ECG sensors
Science China Information Sciences ( IF 7.3 ) Pub Date : 2021-05-08 , DOI: 10.1007/s11432-020-3150-2
Kai Zhao , Yongfu Li , Guoxing Wang , Yu Pu , Yong Lian

This paper presents a robust QRS detection algorithm that is capable of detecting QRS complexes as well as accurately identifying R-peaks. The proposed bilateral threshold scheme combined with QRS watchdog greatly improves the detection accuracy and robustness, resulting in consistent detection performance on 9 available ECG databases. Simulations show that the proposed algorithm achieves good results on the datasets from both QTDB healthy database and MITDB arrhythmia database, i.e. the sensitivity of 99.99% and 99.88%, the precision of 99.98% and 99.88%, and the detection error rate of 0.04% and 0.31%, respectively. Furthermore, it also outperforms many existing algorithms on six other ECG databases, such as NSTDB, TWADB, STDB, SVDB, AFTDB, and FANTASIADB.



中文翻译:

强大的QRS检测和可穿戴式ECG传感器的准确R峰识别算法

本文提出了一种鲁棒的QRS检测算法,该算法能够检测QRS络合物以及准确识别R峰。所提出的双边阈值方案与QRS看门狗相结合,大大提高了检测准确性和鲁棒性,从而在9个可用ECG数据库上实现了一致的检测性能。仿真结果表明,该算法在QTDB健康数据库和MITDB心律失常数据库的数据集上均取得了较好的结果,灵敏度为99.99%和99.88%,精度为99.98%和99.88%,检测错误率为0.04%和分别为0.31%。此外,它还优于其他六个ECG数据库(例如NSTDB,TWADB,STDB,SVDB,AFTDB和FANTASIADB)上的许多现有算法。

更新日期:2021-05-11
down
wechat
bug