论文部分内容阅读
传统脉搏波特征参数测量通常采用回归分析,建立血压模型,其特征参数不固定,影响了某些因子的不可测性,因此该方法在某些情况下受到限制,影响了测量血压值的准确性。而本研究所采用的基于深度学习的血压测量方法是通过构建多隐层的模型和大量训练数据,来学习更有用的特征,从而提升预测血压值的准确性。
The traditional pulse wave characteristic parameter measurement usually adopts the regression analysis to establish the blood pressure model, and its characteristic parameters are not fixed, affecting the unpredictability of some factors, so this method is limited in some cases, affecting the accuracy of measuring the blood pressure value . However, the depth-based blood pressure measurement method used in this study is to learn more useful features by constructing multiple hidden layer models and a large amount of training data to improve the accuracy of the predicted blood pressure values.