DocumentCode :
1803519
Title :
Application of Bayesian neural network in electrical impedance tomography
Author :
Lampinen, Jouko ; Vehtari, Aki ; Leinonen, Kimmo
Author_Institution :
Lab. of Comput. Eng., Helsinki Univ. of Technol., Espoo, Finland
Volume :
6
fYear :
1999
fDate :
36342
Firstpage :
3942
Abstract :
In this contribution we present a method for solving the inverse problem in electric impedance tomography with neural networks. The problem of reconstructing the conductivity distribution inside an object from potential measurements on the surface is known to be ill-posed requiring efficient regularization techniques. We demonstrate that a statistical inverse solution, where the mean of the inverse mapping is approximated with a neural network gives promising results. We study the effect of input and output data representation by simulations and conclude that projection to principal axis is feasible data transformation. Also we demonstrate that Bayesian neural networks, which aim to average over all network models weighted by the model´s posterior probability provide the best reconstruction results. With the presented approach estimation of some target variables, such as the void fraction (the ratio of gas and liquid), may be applicable directly without the actual image reconstruction. We also demonstrate that the solutions are very robust against noise in inputs
Keywords :
Bayes methods; electric impedance imaging; image processing; inverse problems; neural nets; statistical analysis; Bayesian neural network; conductivity distribution reconstruction; efficient regularization techniques; electrical impedance tomography; feasible data transformation; inverse problem; posterior probability; potential measurements; principal axis; statistical inverse solution; void fraction; Bayesian methods; Electrodes; Image reconstruction; Intelligent networks; Inverse problems; Neural networks; Noise robustness; Surface impedance; Surface reconstruction; Tomography;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
ISSN :
1098-7576
Print_ISBN :
0-7803-5529-6
Type :
conf
DOI :
10.1109/IJCNN.1999.830787
Filename :
830787
Link To Document :
بازگشت