The influence of physiological characteristics on blood pressure estimation using only PPG signals

Yang Sen, Stephen P. Morgan, Siu Yeung Cho, Zhang Yaping

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

1 Citation (Scopus)

Abstract

This paper proposed a novel non-invasive, cuff-less and continuous blood pressure monitoring method to investigate the influence of physiological characteristics. The proposed method, based solely on a photoplethysmography (PPG) signal and machine learning models, has been implemented to investigate a database of 191 subjects. Each subject has PPG signals and 5 physiological characteristics recorded. Therefore, there were 32 types of combinations of physiological characteristics that could serve as inputs to the machine learning models, along with features extracted from PPG signals. The mean absolute error and standard deviation were calculated to test the performance of the machine learning models. Simulation results indicated that the more the physiological characteristics were included, the more accurate the blood pressure estimation of the models.

Original languageEnglish
Title of host publication2019 14th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2019
EditorsJuan Wu, Jiali Yin, Zhang Qi
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1694-1700
Number of pages7
ISBN (Electronic)9781728105093
DOIs
Publication statusPublished - Nov 2019
Event14th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2019 - Changsha, China
Duration: 1 Nov 20193 Nov 2019

Publication series

Name2019 14th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2019

Conference

Conference14th IEEE International Conference on Electronic Measurement and Instruments, ICEMI 2019
Country/TerritoryChina
CityChangsha
Period1/11/193/11/19

Keywords

  • blood pressure estimation
  • photoplethysmography (PPG) signal
  • physiological characteristics

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Instrumentation

Fingerprint

Dive into the research topics of 'The influence of physiological characteristics on blood pressure estimation using only PPG signals'. Together they form a unique fingerprint.

Cite this