![](bg8.png)
and depths, allows better coverage of possible
flow changes in test signals.
• Neural networks trained individually for every
body position of a particular subject seem to pro-
vide better results than ones trained with a global
set.
• We obtained 80% accuracy with the best combi-
nation (separate model based on a neural network
with two hidden layers of 10 neurons each, trained
individually on the data from 3rd calibration pro-
cedure), versus 72.5% for simple linear modeling.
ACKNOWLEDGMENTS
This study was supported by the research programs of
institutions the authors are affiliated with.
REFERENCES
Ansari, S., Ward, K., and Najarian, K. (2016). Motion Ar-
tifact Suppression in Impedance Pneumography Sig-
nal for Portable Monitoring of Respiration: an Adap-
tive Approach. IEEE J. Biomed. Heal. Informatics,
11(4):1–1.
Baemani, M. J., Monadjemi, A., and Moallem, P. (2008).
Detection of respiratory abnormalities using artifi-
cial neural networks. Journal of Computer Science,
4(8):663–667.
Gracia, J., Seppa, V. P., and Viik, J. (2015). Regional
impedance pneumography heterogeneity during air-
way opening pressure chirp oscillations. Int. J. Bio-
electromagn., 17(1):42–51.
Houtveen, J. H., Groot, P. F. C., and De Geus, E. J. C.
(2006). Validation of the thoracic impedance derived
respiratory signal using multilevel analysis. Int. J.
Psychophysiol., 59(2):97–106.
Jafari, S., Arabalibeik, H., and Agin, K. (2010). Classifica-
tion of normal and abnormal respiration patterns us-
ing flow volume curve and neural network. In Health
Informatics and Bioinformatics (HIBIT), 2010 5th In-
ternational Symposium On, pages 110–113. IEEE.
Koivumaki, T., Vauhkonen, M., Kuikka, J. T., and Haku-
linen, M. a. (2012). Bioimpedance-based measure-
ment method for simultaneous acquisition of respi-
ratory and cardiac gating signals. Physiol. Meas.,
33(8):1323–1334.
Lai, C.-L., Lee, J.-S., and Chen, J.-C. (2015). A curve fit-
ting approach using ann for converting ct number to
linear attenuation coefficient for ct-based pet attenu-
ation correction. IEEE Transactions on Nuclear Sci-
ence, 62(1):164–170.
Lee, S. J., Motai, Y., Weiss, E., and Sun, S. S. (2012). Ir-
regular breathing classification from multiple patient
datasets using neural networks. IEEE Transactions on
Information Technology in Biomedicine, 16(6):1253–
1264.
Leonhardt, S. and Lachmann, B. (2012). Electrical
impedance tomography: The holy grail of ventila-
tion and perfusion monitoring? Intensive Care Med.,
38:1917–1929.
Li, Y., Pan Fua, Z. L., Lia, X., and Lina, Z. (2015). Biax-
ial angle sensor calibration method based on artificial
neural network. Chemical Engineering, 46:361–366.
Mathworks (2016). Fit Data with a Neural Net-
work. https://www.mathworks.com/help/nnet/gs/fit-
data-with-a-neural-network.html. [Online; accessed
07-October-2016].
Min, M. and Paavle, T. (2013). Improved extraction of in-
formation in bioimpedance measurements. In J. Phys.
Conf. Ser., volume 434, pages 0120291–4.
Mły
´
nczak, M., Niewiadomski, W.,
˙
Zyli
´
nski, M., and Cybul-
ski, G. (2015a). Assessment of calibration methods
on impedance pneumography accuracy. Biomed. Eng.
/ Biomed. Tech.
Mły
´
nczak, M., Niewiadomski, W.,
˙
Zyli
´
nski, M., and Cybul-
ski, G. (2015b). Verification of the Respiratory Param-
eters Derived from Impedance Pnumography during
Normal and Deep Breathing in Three Body Postures.
In IFMBE Proc., volume 45, pages 162–165.
Monteiro, R. L. S., Carneiro, T. K. G., Fontoura, J. R. A.,
Da Silva, V. L., Moret, M. A., and De Barros Pereira,
H. B. (2016). A model for improving the learning
curves of artificial neural networks. PLoS One, 11(2).
Ojarand, J., Annus, P., and Min, M. (2013). Optimisation of
multisine waveform for bio-impedance spectroscopy.
In J. Phys. Conf. Ser., volume 434, pages 0120301–4.
Poupard, L., Mathieu, M., Sart
`
ene, R., and Goldman, M.
(2008). Use of thoracic impedance sensors to screen
for sleep-disordered breathing in patients with cardio-
vascular disease. Physiol. Meas., 29(2):255–267.
Roebuck, A., Monasterio, V., Gederi, E., Osipov, M., Behar,
J., Malhotra, A., Penzel, T., and Clifford, G. (2013). A
review of signals used in sleep analysis. Physiological
measurement, 35(1):R1.
Seppa, V. P., Hyttinen, J., Uitto, M., Chrapek, W., and
Viik, J. (2013a). Novel electrode configuration for
highly linear impedance pneumography. Biomed. Eng.
/ Biomed. Tech., 58(1):35–38.
Seppa, V.-P., Hyttinen, J., and Viik, J. (2011). A method
for suppressing cardiogenic oscillations in impedance
pneumography. Physiol. Meas., 32(3):337–345.
Seppa, V.-P., Pelkonen, A. S., Kotaniemi-Syrjanen, A.,
Makela, M. J., Viik, J., and Malmberg, L. P. (2013b).
Tidal breathing flow measurement in awake young
children by using impedance pneumography. J. Appl.
Physiol., 115(11):1725–31.
Seppa, V.-P., Pelkonen, A. S., Kotaniemi-Syrjanen, A.,
Viik, J., Makela, M. J., and Malmberg, L. P. (2016).
Tidal flow variability measured by impedance pneu-
mography relates to childhood asthma risk. Eur.
Respir. J., pages 1–10.
Seppa, V.-P., Viik, J., and Hyttinen, J. (2010). Assessment
of pulmonary flow using impedance pneumography.
IEEE Trans. Biomed. Eng., 57(9):2277–2285.
Flow Parameters Derived from Impedance Pneumography after Nonlinear Calibration based on Neural Networks
77