I. J. of Electrical & Electronics Research
Research Article | 
1-Dimensional Convolutional Neural Network Based Blood Pressure Estimation with Photo plethysmography Signals and Semi-Classical Signal Analysis
Author(s) : Seong-Hyun Kim1 and Eui-Rim Jeong2
Published In : International Journal of Electrical and Electronics Research (IJEER) Volume 10, Issue 2
Publisher : FOREX Publication
Published : 10 June 2022
e-ISSN : 2347-470X
Page(s) : 214-217
Abstract
In this paper, we propose a 1-Dimensional Convolutional Neural Network (1D-CNN) based Blood Pressure (BP) estimation using Photo plethysmography (PPG) signals and their features obtained through Semi-classical Signal Analysis (SCSA). The procedure of the proposed BP estimation technique is as follows. First, PPG signals are divided into each beat. Then, 9 features are obtained through SCSA for the divided beats. In addition, 5 biometric data are used. The Biometrics data include Heart Rate (HR), age, sex, height, and weight. The total 14 features are used for training and validating the 1D-CNN BP estimation model. After testing three types of 1D-CNNs, the model with the most optimal performance is selected. The selected model structure consists of three convolutional layers and one fully connected layer. The performance is measured by Mean Error (ME) ± Standard Deviation (STD) following the Association for the Advancement of Medical Instrumentation (AAMI) standard. According to the results of the test, Systolic Blood Pressure (SBP) is -2.99±14.48 mmHg and Diastolic Blood Pressure (DBP) is 1.16±9.30 mmHg. Using the proposed technique, blood pressure can be easily predicted using PPG obtained with a non-invasive and cuff-less wearable sensor.
Keywords: SCSA, BP, Photo plethysmography, CNN, Non-invasive, Cuff-less
Seong-Hyun Kim, Department of Mobile Convergence and Engineering, Hanbat National University, Daejeon, Republic of Korea; Email: erjeong@hanbat.ac.kr
Eui-Rim Jeong, Department of Artificial Intelligence Software, Hanbat National University, Daejeon, Republic of Korea; Email:erjeong@hanbat.ac.kr
[1] Chang, W. D. “Frequency analysis for recognition of emotional states using Photoplethysmograms,” Journal of Next-generation Convergence Technology Association, vo. 6, no. 1, pp. 26-31, 2022.[Cross Ref]
[2] Filnt, A. C., Conell, C., Ren, X., Banki, N. M., Chan, S. L., Rao, V. A., Melles, R. B. & Bhatt, D. L. “Effect of systolic and diastolic blood pressure on cardiovascular outcomes,” New England Journal of Medicine, vol. 381, no. 3, pp. 243-251, 2019.[Cross Ref]
[3] Forouzanfar, M. H., et al. “Global burden of hypertension and systolic blood pressure of at least 110 to 115 mm Hg,” JAMA, vol. 317 no. 2, pp. 165-18, 2017.[Cross Ref]
[4] Buford, T. W. “Hypertension and aging,” Ageing research reviews, vol. 26, pp. 96-111, 2016. [Cross Ref]
[5] Mills, K. T., Stefanescu, A. & He, Jiang. “The global epidemiology of hypertension,” Nature Reviews Nephrology, vol. 16, no. 4, pp. 223-237, 2020.[Cross Ref]
[6] Low, P. A. & Tomalia, V. A. “Orthostatic hypotension: Mechanisms, Causes, Management,” Journal of the American College of Cardiology, vol. 66, no. 7, pp. 848-860, 2015[Cross Ref]
[7] Rogan, A., Mcgregor, G., Weston, C., Krishnan, N., Higgins, R., Zehnder, D. & Ting, S. M. S. “Exaggerated blood pressure response to dynamic exercise despite chronic refractory hypotension: results of a human case study,” BMC nephrology, vol. 16, no. 1, pp. 1-5, 2015.[Cross Ref]
[8] Sorvoja, H. “Noninvasive blood pressure measurement methods,” Molecular and quantum acoustics, vol. 27, pp. 239-264, 2006.[Cross Ref]
[9] Kim, S. H. & Jeong, E. R. “1-dimentional convolutional neural network based heart rate estimation using Photoplethysmogram signals,” Webology, vol. 19, no. 1, pp. 4571-4580, 2022.[Cross Ref]
[10] Laleg-Kirati, T. M., Crépeau, E. & Sorine, M. “Semi-classical signal analysis,” Mathematics of Control, Signals, and Systems, vol. 25, no. 1, pp. 37-61, 2013.[Cross Ref]
[11] Laleg-Kirati, T. M., Médigue, C., Papelier, Y., Cottin, F., & Van de Louw, A. “Validation of a semi-classical signal analysis method for stroke volume variation assessment: A comparison with the PiCCO Technique,” Annals of biomedical engineering, vol. 38, no. 12, pp. 3618-3629, 2010.[Cross Ref]
[12] Park, E. K., Park, S. H., Hwang, H. S., Park, H. K. & Kim, I. Y. “A study on the estimation of continuous blood pressure using PIT and biometric parameters,” Journal of Biomedical Engineering Research, vol. 27, no. 1, pp. 1-5, 2006.[Cross Ref]
[13] Stergiou, G. S., et al. “A universal standard for the validation of blood pressure measuring devices: Association for the advancement of medical instrumentation/european society of hypertension/international organization for standardization (AAMI/ESH/ISO) collaboration statement,” Hypertension, vol. 71, no. 3, pp. 368-374, 2018.[Cross Ref]
[14] Li, L., Kong, Y. & Sun, J. "A New ECT Image Reconstruction Algorithm Based on Convolutional Neural Network", International Journal of Signal Processing, Image Processing and Pattern Recognition, NADIA, ISSN: 2005-4254 (Print); 2207-970X (Online), vol.9, no.11, November (2016), pp. 221-230, http://dx.doi.org/10.14257/ijsip.2016.9.11.20.[Cross Ref]
Seong-Hyun Kim and Eui-Rim Jeong (2022), 1-Dimensional Convolutional Neural Network Based Blood Pressure Estimation with Photo plethysmography Signals and Semi-Classical Signal Analysis. IJEER 10(2), 214-217. DOI: 10.37391/IJEER.100228.