Implementation of reduce AI-NN model for highly accurate blood pressure measurement

Jerry Lin, Rajeev Kumar Pandey, Paul C.P. Chao*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This study proposes a reduce AI model for the accurate measurement of the blood pressure (BP). In this study varied temporal periods of photoplethysmography (PPG) waveforms is used as the features for the artificial neural networks to estimate blood pressure. A nonlinear Principal component analysis (PCA) method is used herein to remove the redundant features and determine a set of dominant features which is highly correlated to the Blood pressure (BP). The reduce features-set not only helps to minimize the size of the neural network but also improve the measurement accuracy of the systolic blood pressure (SBP) and diastolic blood pressure (DBP). The designed Neural Network has the 5-input layer, 2 hidden layers (32 nodes each) and 2 output nodes for SBP and DBP, respectively. The NN model is trained by the PPG data sets, acquired from the 96 subjects. The testing regression for the SBP and DBP estimation is obtained as 0.81. The resultant errors for the SBP and DBP measurement are 2.00±6.08 mmHg and 1.87±4.09 mmHg, respectively. According to the Advancement of Medical Instrumentation (AAMI) and British Hypertension Society (BHS) standard, the measured error of ±6.08 mmHg is less than 8 mmHg, which shows that the device performance is in grade “A”.

Original languageEnglish
Title of host publicationASME 2020 29th Conference on Information Storage and Processing Systems, ISPS 2020
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791883600
DOIs
StatePublished - 2020
EventASME 2020 29th Conference on Information Storage and Processing Systems, ISPS 2020 - Virtual, Online
Duration: 24 Jun 202025 Jun 2020

Publication series

NameASME 2020 29th Conference on Information Storage and Processing Systems, ISPS 2020

Conference

ConferenceASME 2020 29th Conference on Information Storage and Processing Systems, ISPS 2020
CityVirtual, Online
Period24/06/2025/06/20

Keywords

  • Artificial neural network (ANN)
  • Blood pressure (BP)
  • Photoplethysmography (PPG) signal
  • Principal component analysis (PCA)

Fingerprint Dive into the research topics of 'Implementation of reduce AI-NN model for highly accurate blood pressure measurement'. Together they form a unique fingerprint.

Cite this