经验模态分解和小波变换的连续血压测量

A Continuous Blood Pressure Measurement Based on Empirical Mode Decomposition and Wavelet Transform

为了解决经验模态分解对容积脉搏波滤波效果不佳、建立准确的血压计算模型。利用经验模态分解和db5小波变换对容积脉搏波滤波后,对支持向量机识别出的不同加速脉搏波采用不同的方法提取特征点来计算脉搏波的传导时间,分别建立血压与脉搏波传导时间的血压计算模型。实验仿真证明容积脉搏波信号经经验模态分解和db5小波变换滤波后,噪声得到了有效的去除,建立的血压模型与水银血压计测出的血压值之间的误差,优于AAMI的推荐标准。提高了提取脉搏波传导时间的准确性,建立的血压计算模型更加可行准确。

To resolve poor filtering effect of volume pulse wave by empirical mode decomposition, an accurate blood pressure calculation model is set up. The pulse wave is extract filtered by empirical mode decomposition and db5 wavelet transform, the feature of different acceleration pulse waves adopting different methods is extracted to calculate the pulse wave transmission time, a blood pressure model and a blood pressure calculation model of pulse wave conduction time are established. Simulation results show that the filter of volume pulse wave by the empirical mode decomposition and db5 is removed efficiently, and the maximum error of the blood pressure value calculated by the blood pressure model and measured by the mercury sphygmomanometer is 7 mmHg which is smaller than AAMI＇s recommendation. The method improves the accuracy of pulse wave transmission time, and the blood pressure estimation model established is more accurate.