计算机科学
人工智能
工件(错误)
阈值
噪音(视频)
降噪
模式识别(心理学)
希尔伯特-黄变换
信号(编程语言)
计算机视觉
滤波器(信号处理)
图像(数学)
程序设计语言
作者
Xiaoyun Xie,Hui Liu,Minglei Shu,Qing Zhu,Anpeng Huang,Xiangpu Kong,Yinglong Wang
标识
DOI:10.1016/j.future.2020.10.024
摘要
Electrocardiogram (ECG) acquired by wearable devices is increasingly used for healthcare applications. However, the ECG signals are severely corrupted by various noises (e.g. baseline wander and motion artifacts) in daily activities, resulting in unreliable or wrong detection of heart problems and hindering the automatic ECG analysis. Because of the overlap of different kinds of noises in the time and frequency domains, noise removal is a difficult task for ambulatory ECG signals. Especially, motion artifacts with variable frequencies and amplitudes pose a great challenge to ECG denoising. To address this problem, we propose a multi-stage ECG denoising framework concentrating on the detection of motion artifact based on domain knowledge. In the framework, motion artifact candidates are first located by noise-adaptive thresholding. Then we use multiple metrics combined with decision rules to find actual motion artifacts and suppress them by local scaling and morphological filtering. The complete ensemble empirical mode decomposition (CEEMD) and wavelet transform are employed to remove baseline wander and high-frequency noise, respectively. The proposed method is evaluated on the MIT-BIH arrhythmia database, the TELE database, and the Sport database. The results on the MIT-BIH database show that the proposed method achieved statistically significant improvement of signal-to-noise ratio (SNR) ranging from 7% to 25% compared with other approaches. The results also demonstrate that the proposed method effectively suppressed QRS-like motion artifacts and hence decreased false positives generated by the QRS detector, which is important for clinical diagnosis.
科研通智能强力驱动
Strongly Powered by AbleSci AI