基于经验模态分解与独立成分分析的心肺复苏伪迹自适应滤除算法

发布时间：2018-03-12 20:39

本文选题：心肺复苏　切入点：经验模态分解　出处：《生物医学工程学杂志》2016年05期 　论文类型：期刊论文

【摘要】：心肺复苏(CPR)过程中实施的胸外按压引起的伪迹会严重降低除颤节律辨识的可靠性。本文提出了一种无需参考信号的CPR伪迹自适应滤除算法。结合经验模态分解(EMD)和独立成分分析(ICA),将真正的心电节律信号从受CPR伪迹干扰的心电信号中分离出来。为评估算法的效果,构建了一个用于除颤节律辨识的反向传播神经网络。采集了1 484例受CPR伪迹干扰的猪的心电信号用于实验。实验结果表明,该算法可以在很大程度上抑制CPR伪迹的影响,从而显著提高CPR过程中除颤节律辨识的准确性。
[Abstract]:The artifact caused by chest compression during cardiopulmonary resuscitation (CPR) will seriously reduce the reliability of defibrillation rhythm identification. In this paper, an adaptive CPR artifact filtering algorithm without reference signal is proposed, which is combined with empirical mode decomposition (EMD). And independent component analysis (ICA) to separate true ECG rhythm signals from ECG signals interfered with by CPR artifacts. A backpropagation neural network for defibrillation rhythm identification was constructed. The ECG signals of 1 484 pigs affected by CPR artifacts were collected for experiment. The experimental results show that the proposed algorithm can suppress the influence of CPR artifacts to a large extent. Therefore, the accuracy of defibrillation rhythm identification in CPR process is improved significantly.
【作者单位】：军事医学科学院卫生装备研究所;
【基金】：国家自然科学基金资助项目(81501551)
【分类号】：R459.7

【相似文献】