论文部分内容阅读
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。
Artifact caused by chest compression during cardiopulmonary resuscitation (CPR) can severely reduce the reliability of defibrillation rhythm recognition. In this paper, we propose a CPR artifact adaptive filtering algorithm without reference signal. Combined with empirical mode decomposition (EMD) and independent component analysis (ICA), the true ECG rhythm signal is separated from the ECG signal interfered with by CPR artifacts. To evaluate the effectiveness of the algorithm, a backpropagation neural network for the identification of defibrillation rhythm was constructed. ECGs of 1 484 pigs interfered with by CPR artifacts were collected for experiments. The experimental results show that this algorithm can largely suppress the impact of CPR artifacts, and thus significantly improve the accuracy of the CPR process identification of the rhythm of defibrillation.