Authors:
Marcel Młyńczak
1
and
Gerard Cybulski
1
;
2
Affiliations:
1
Warsaw University of Technology, Poland
;
2
Polish Academy of Sciences, Poland
Keyword(s):
Ambulatory Monitoring, Impedance Pneumography, Calibration, Neural Networks.
Abstract:
Impedance pneumography (IP) is mainly used as a noninvasive method to measure respiratory rate, tidal
volume or minute ventilation. It could also register flow-related signals, after differentiation, from spirometrybased
forced vital capacity maneuvers or ambulatory-based signals reflecting flow values during natural activity.
The aim of this paper is to assess the possibility of improving the accuracy of flow parameters calculated
by IP, by using nonlinear neural network correction (as opposed to simple linear calibration), and to evaluate
the impact of various calibration procedures and neural network configurations. Ten students carried out fixed
static breathing sequences, for both calibration and testing. A reference pneumotachometer and the Pneumonitor
2 were used. The validation of calculating peak and mean flow value during each inspiration and expiration
was considered. A mean accuracy of 80% was achieved for a separate neural network with two hidden layers
with 10 neurons i
n each layer, trained individually for each subject and body position, using the data from the
longest, fixed calibration procedure. Simple linear modeling achieved only 72.5%.
(More)