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

doi:10.16182/j.issn1004731x.joss.19-0154

Abstract

Abstract: 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%.

Key words: Support vector regression model (SVR), Genetic algorithm (GA), Human body characteristics, Blood pressure prediction

CLC Number:

TP274

Fan Haixia, Chen Xiaohui. A Continuous Non-invasive Blood Pressure Prediction Method Based on Improved SVR Learning[J]. Journal of System Simulation, 2020, 32(9): 1686-1692.

References

[1] Junior A D, Murali S, Rincon F, et al.Estimation of blood pressure and pulse transit time using your smartphone[C]. 2015 Euromicro Conference on. IEEE. San Francisco, CA, USA: IEEE, 2015: 173-180.
[2] Yusuf S, Bosch J, Dagenais G, et al.Cholesterol Lowering in Intermediate-Risk Persons without Cardiovascular Disease[J]. Journal of Vascular Surgery (S0741-5214), 2016, 64(3): 827.
[3] Mishra B, Thakkar N.Cuffless blood pressure monitoring using PTT and PWV methods[C]. 2017 International Conference on. IEEE. San Francisco, CA, USA: IEEE, 2017: 395-401.
[4] Thomas S S, Nathan V, Zong C, et al.BioWatch: A noninvasive wrist-based blood pressure monitor that incorporates training techniques for posture and subject variability[J]. IEEE Journal of Biomedical and Health Informatics (S2168-2194), 2016, 20(5): 1291-1300.
[5] Ghosh S, Banerjee A, Ray N, et al.Continuous blood pressure prediction from pulse transit time using ECG and PPG signals[C]. Healthcare Innovation Point-Of-Care Technologies Conference. IEEE. San Francisco, CA, USA: IEEE, 2016: 188-191.
[6] Liu J, Li Y, Ding X R, et al.Effects of Cuff Inflation and Deflation on Pulse Transit Time Measured from ECG and Multi-Wavelength PPG[C]. IEEE Engineering in Medicine and Biology Society, Annual Conference[S.I.]. IEEE, 2015: 5973-5976.
[7] Hsieh Y Y, Wu C D, Lu S S, et al.A linear regression model with dynamic pulse transit time features for noninvasive blood pressure prediction[C]. Biomedical Circuits and Systems Conference (BioCAS), 2016 IEEE. San Francisco, CA, USA:IEEE, 2016: 604-607.
[8] Costas S, Kalantarian H, Nemati E, et al.Building continuous arterial blood pressure prediction models using recurrent networks[C]. Smart Computing (SMARTCOMP), 2016 IEEE International Conference on. IEEE. San Francisco, CA, USA: IEEE, 2016: 1-5.
[9] Wu T H, Grantham K H P, Enid W Y K. Predicting systolic blood pressure using machine learning[C]. Information and Automation for Sustainability (ICIAfS), 2014 7^th International Conference on. IEEE. San Francisco, CA, USA: IEEE, 2014: 1-6.
[10] 刘艳萍, 李杰, 金菲. 基于RNN的脉搏波血压计的研究与实现[J]. 电子技术应用, 2018, 44(6): 76-79, 84.
Liu Yanping, Li Jie, Jin Fei.Research and design of pulse wave sphygmomanometer based on RNN[J]. Application of Electronic Technique, 2018, 44(6): 76-79, 84.
[11] 宋晓洋, 刘立勋. 基于SVM回归的连续血压测量方法[J]. 吉林大学学报(信息科学版), 2016, 34(3): 384-389.
Song Xiaoyang, Liu Lixun, Continuous Blood Pressure Measurement Method Based on SVM Regression[J]. Journal of Jilin University (Information Science Edition), 2016, 34(3): 384-389.
[12] 赵谞博, 赫英迪, 李信政, 等. 基于支持向量回归的人体血压预测方法[J]. 燕山大学学报, 2017, 41(5): 438-443.
Zhao Xubo, He Yingdi,Li Xinzheng, et al.Prediction of human blood pressure based on support vector regression[J]. Journal of Yanshan University, 2017, 41(5): 438-443.
[13] Cheng C H, Shiu H Y.A novel GA-SVR time series model based on selected indicators method for forecasting stock price[C]. Information Science, Electronics and Electrical Engineering (ISEEE), 2014 International Conference on. IEEE. San Francisco, CA, USA: IEEE, 2014, 1: 395-399.
[14] 王晨晖, 张超. 基于主成分分析法和遗传算法优化支持向量机模型的泥石流危险度预测[J]. 河北地质大学学报, 2017, 40(2): 20-24.
Wang Chenhui, Zhang Chao.Debris Flow Risk Prediction Based on PCA-GA-SVM Model[J]. Journal of Hebei GEO University, 2017, 40(2): 20-24.
[15] 张茜, 李彦. 基于支持向量机的船舶机舱火灾温度快速预测[J]. 舰船科学技术, 2018, 40(1): 148-152.
Zhang Xi, Li Yan.Ship engine room fire temperature fast prediction based on support vector machine[J]. Ship Science and Technology, 2018, 40(1): 148-152.