一种连续无创血压预测的改进向量机学习方法

因不同人体生理特征的差异性,影响了基于光电容积脉搏波（PPG）和心电信号（ECG）的连续无创血压测量精度,提出一种基于优化的支持向量机模型预测血压的方法。该方法将PPG、ECG及人体特征进行处理并组成特征矩阵,通过水银血压计测得实时血压值,运用主成分分析法和遗传算法改进的支持向量机学习模型对特征矩阵和实时血压值进行回归训练,从而建立最优血压预测模型。实验证明,优化改进支持向量回归血压预测方法比传统支持向量机学习法准确度提升了10%~15%。

A Continuous Non-invasive Blood Pressure Prediction Method Based on Improved SVR Learning

Aiming at the accuracy of continuous non-invasmive monitoring of blood pressure by photoelectric method based on the photoplethysmography (PPG) signal and the electrocardiography (ECG) signal, is influenced by the differences of human characteristics, a blood pressure prediction method based on principal component analysis (PCA) and genetic algorithm (GA) to optimize machine learning model is proposed. The method processes the PPG signal, ECG signal and human body features to form a feature matrix, and uses an improved SVR learning model to perform regression training on the feature matrix and the real-time blood pressure value measured by the mercury sphygmomanometer. The GA is used to optimize the parameters to establish an optimal blood pressure prediction model. The experimental results show that, compared with the traditional SVR, the proposed method could improve the predictive accuracy by 10%-15%.