Measuring blood pressure from photoplethysmograph (PPG) signals is gaining popularity as the PPG devices are inexpensive, convenient to use and much portable. The advent of wearable PPG devices, machine learning and signal processing has motivated in the development of cuffless blood pressure calculation from PPG signals captured from fingertip. The conventional pulse transit time-based method of measuring blood pressure from PPG is inconvenient as it requires electrocardiogram signals and PPG signals or PPG signals captured simultaneously from two different sites of the body. The proposed system uses the PPG signals alone to estimate blood pressure (BP). A signal analysis method called wavelet scattering transform is applied on the preprocessed PPG signals to extract features. Predictor model that estimates BP are derived by training the support vector regression model and long short term memory prediction model. The derived models are evaluated with testing dataset and the results are compared with ground truth values. The results show that the accuracy of the proposed method achieves grade B for the estimation of the diastolic blood pressure and grade C for the mean arterial pressure under the standard British Hypertension Society protocol. On comparing the results of the proposed system with the benchmark machine learning algorithms, it is observed that the proposed model outperforms others by a considerable margin. A comparative analysis with prior studies shows that the results obtained from proposed work are comparable with existing works in the literature.

由于 PPG 设备价格低廉、使用方便且便于携带，因此从光电容积脉搏波 (PPG) 信号测量血压越来越受欢迎。可穿戴 PPG 设备、机器学习和信号处理的出现推动了从指尖捕获的 PPG 信号计算无袖带血压的发展。从 PPG 测量血压的传统基于脉搏传输时间的方法是不方便的，因为它需要心电图信号和 PPG 信号或从身体的两个不同部位同时捕获的 PPG 信号。所提出的系统仅使用 PPG 信号来估计血压 (BP)。将称为小波散射变换的信号分析方法应用于预处理的 PPG 信号以提取特征。估计BP的预测模型是通过训练支持向量回归模型和长短期记忆预测模型得出的。使用测试数据集评估派生模型，并将结果与​​地面实况值进行比较。结果表明，所提出方法的准确性在估计舒张压时达到 B 级，在标准英国高血压协会协议下达到 C 级平均动脉压。将所提出的系统的结果与基准机器学习算法的结果进行比较，可以看出所提出的模型明显优于其他模型。与先前研究的比较分析表明，从拟议工作中获得的结果与文献中的现有工作具有可比性。