Real-time human chest imaging exploiting electrical impedance tomography (EIT) data is addressed in this work. Robust estimations of the lungs conductivity, directly related to their air/liquid content, are obtained by formulating the arising inverse problem within the learning-by-examples (LBE) framework. The partial least squares (PLS) algorithm is exploited to reduce the dimensionality of the feature space, while an adaptive sampling strategy is exploited to build an optimal training set of input/output pairs used to build a computationally efficient surrogate model of the inverse operator. Selected numerical results are shown to assess the effectiveness and the potentialities of the proposed LBE strategy.
Human chest imaging by real-time processing of electrical impedance data tomography / Gottardi, G.; Poli, L.. - STAMPA. - (2018), pp. 1-7. (Intervento presentato al convegno 8th International Conference on New Computational Methods for Inverse Problems (NCMIP 2018) tenutosi a Paris-Saclay nel 25th May 2018).
Human chest imaging by real-time processing of electrical impedance data tomography
G. Gottardi;L. Poli
2018-01-01
Abstract
Real-time human chest imaging exploiting electrical impedance tomography (EIT) data is addressed in this work. Robust estimations of the lungs conductivity, directly related to their air/liquid content, are obtained by formulating the arising inverse problem within the learning-by-examples (LBE) framework. The partial least squares (PLS) algorithm is exploited to reduce the dimensionality of the feature space, while an adaptive sampling strategy is exploited to build an optimal training set of input/output pairs used to build a computationally efficient surrogate model of the inverse operator. Selected numerical results are shown to assess the effectiveness and the potentialities of the proposed LBE strategy.File | Dimensione | Formato | |
---|---|---|---|
Human chest imaging by real-time processing of electrical impedance data tomography.pdf
Solo gestori archivio
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
8.75 MB
Formato
Adobe PDF
|
8.75 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione