Continuous_Blood_Pressure_Estimation

关于联系血压监控的ML建模方向。
Continuous Blood Pressure Monitoring[1] 是一篇关于联系血压检测技术的综述。

BP-ML

A non-invasive continuous blood pressure estimation approach based on machine learning.[2]
创新点：使用Machine Learning去评估systolic BP and diastolic BP，主要用到两种模式的数据：
1.pulse transit time(PTT)
2. characteristics of pulse waveform。

关键词：systolic BP (SBP) ，diastolic BP (DBP)，

2.3. Normalization and Dimensionality Reduction of Features

为了提升数据之间的相关性，对所有的输入数据使用线性归一化normalization：

为了消除冗余的特征序列，使用了the mean impact value (MIV)

2.4. Modeling Methods

Traditional models： Multivariate Linear Regression (MLR) models and PTTc-based SVR models.
In the porposed method: Support Vector Regression (SVR) was used to construct the SBP and DBP estimation models.

[1] Stojanova A, Koceski S, Koceska N. Continuous Blood Pressure Monitoring as a Basis for Ambient Assisted Living (AAL) - Review of Methodologies and Devices. J Med Syst. 2019;43(2):24. Published 2019 Jan 2. doi:10.1007/s10916-018-1138-8
[2] Chen, Shuo, et al. “A non-invasive continuous blood pressure estimation approach based on machine learning.“ Sensors 19.11 (2019): 2585.