Authors:
A. Nassef
1
;
M. Mahfouf
1
;
C-H. Ting
2
;
E. Elsamahy
1
;
D. A. Linkens
1
and
M. Denaï
3
Affiliations:
1
University of Sheffield, United Kingdom
;
2
National Chiayi University, Taiwan
;
3
The University of Sheffield, United Kingdom
Keyword(s):
Modeling, Signal Processing, Biomedical Systems, Fuzzy Systems, Genetic Algorithms.
Related
Ontology
Subjects/Areas/Topics:
Biomedical Engineering
;
Biomedical Signal Processing
;
Physiological Processes and Bio-Signal Modeling, Non-Linear Dynamics
Abstract:
This paper investigates the influence of physical stress on the physiological parameters of the cardiovascular system (CVS). The work aims at estimating the physiological variables such as the Heart Rate (HR), Blood Pressure (BP), Total Peripheral Resistance (TPR) and respiration in a subject underging physical workload. The core of the model was based on the model architecture previously developed by Luczak and his co-workers. Luczak's model was first reconstructed and the original published figure plots were used to identify some of the missing parameters via Genetic Algorithms (GA). The model was then modified using real experimental data extracted from healthy subjects who underwent two-session experiments of cyclic-loading based physical stress. Neuro-Fuzzy models were elicited via the data in order to describe the non-linear components of the model. The model response has also been significantly improved by including a dynamics-based component represented by 'time' as an extra
input. The final model, as well as being of a ‘hybrid’ nature, was found to generalize better, to be more amenable to expansions and to also lead to better predictions.
(More)