Authors:
Soheil Mottaghi
1
;
Mohammad Hassan Moradi
2
;
Mahmoud Moghavvemi
3
;
Leyla Roohisefat
1
and
Eshwar C. V. Sagar
1
Affiliations:
1
University of Malaya, Malaysia
;
2
Amirkabir University of Technology, Iran, Islamic Republic of
;
3
University of Malaya and University of Tehran, Malaysia
Keyword(s):
Blood Pressure, Bruce Protocol, Cuffless, Eelectrocardiography, Exercise, Heart Rate, Pulse Arrival Time, Pulse Pletysmography, Neuro-fuzzy, Stress Test.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Cardiovascular Signals
;
Computer Vision, Visualization and Computer Graphics
;
Fuzzy Systems and Signals
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Real-Time Systems
Abstract:
An accurate blood pressure monitoring method during the course of an exercise stress test is paramount. This is due to the fact that the patients are under intense physical pressure, and most of the time, are usually afflicted with cardiovascular problems. Exercise or intense physical activities elevates blood pressures, which renders cuff-based measuring systems highly inaccurate, but convenient for lesser artifacts. Much research has been conducted on The Pulse Arrival Time (PAT), and it was concluded that it is inexplicably linked to blood pressure. In this study, we propose a novel approach using a neuro-fuzzy system (Fuzzy Type I) and Adaptive neuro-fuzzy inference system (ANFIS)for cuffless blood pressure estimation before, during, and after the stress test. Systolic BP and diastolic BP estimation were carried out in this study as well. There are no significant advantages in having lower error rate and/or higher correlation coefficients between the fuzzy systems. However it has
been shown that the results of the non-linear fuzzy estimators possess higher correlation and lower errors than the Least Squared regression introduced in previous studies.
(More)