A mesh-refinement method based on artificial neural networks for electrical impedance tomography

Sebastien Martin; T.m. Choi

doi:10.1109/CEFC.2016.7816171

A mesh-refinement method based on artificial neural networks for electrical impedance tomography

Sebastien Martin, T.m. Choi

Institute of Biomedical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Inverse boundary problem are usually solved with a finite element model, with either limited accuracy or huge computation resources. Using a fine mesh results in a computationally demanding task, but when the region of interest is known, when one can easily locally refine the model, aiming for greater local accuracy. In this paper, a novel approach uses artificial neural network to estimate the location of the region of interest and refine this region before solving the inverse problem. The idea is illustrated by solving the electrical impedance tomography inverse problem. Result shows that the proposed method increases the accuracy without significantly affecting the computation resources necessary to solve the inverse problem.

Original language	English
Title of host publication	IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509010325
DOIs	https://doi.org/10.1109/CEFC.2016.7816171
State	Published - 12 Jan 2017
Event	17th Biennial IEEE Conference on Electromagnetic Field Computation, IEEE CEFC 2016 - Miami, United States Duration: 13 Nov 2016 → 16 Nov 2016

Publication series

Name	IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation

Conference

Conference	17th Biennial IEEE Conference on Electromagnetic Field Computation, IEEE CEFC 2016
Country/Territory	United States
City	Miami
Period	13/11/16 → 16/11/16

Keywords

Adaptive Mesh Refinement
Artificial Neural Network
Electrical Impedance Tomography
Finite Element Method

Access to Document

10.1109/CEFC.2016.7816171

Cite this

Martin, S., & Choi, T. M. (2017). A mesh-refinement method based on artificial neural networks for electrical impedance tomography. In IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation [7816171] (IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CEFC.2016.7816171

@inproceedings{df4bba59ccfd4d8f9eb1f9fcc5d9fd5b,

title = "A mesh-refinement method based on artificial neural networks for electrical impedance tomography",

abstract = "Inverse boundary problem are usually solved with a finite element model, with either limited accuracy or huge computation resources. Using a fine mesh results in a computationally demanding task, but when the region of interest is known, when one can easily locally refine the model, aiming for greater local accuracy. In this paper, a novel approach uses artificial neural network to estimate the location of the region of interest and refine this region before solving the inverse problem. The idea is illustrated by solving the electrical impedance tomography inverse problem. Result shows that the proposed method increases the accuracy without significantly affecting the computation resources necessary to solve the inverse problem.",

keywords = "Adaptive Mesh Refinement, Artificial Neural Network, Electrical Impedance Tomography, Finite Element Method",

author = "Sebastien Martin and T.m. Choi",

year = "2017",

month = jan,

day = "12",

doi = "10.1109/CEFC.2016.7816171",

language = "English",

series = "IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation",

address = "United States",

note = "17th Biennial IEEE Conference on Electromagnetic Field Computation, IEEE CEFC 2016 ; Conference date: 13-11-2016 Through 16-11-2016",

}

Martin, S & Choi, TM 2017, A mesh-refinement method based on artificial neural networks for electrical impedance tomography. in IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation., 7816171, IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation, Institute of Electrical and Electronics Engineers Inc., 17th Biennial IEEE Conference on Electromagnetic Field Computation, IEEE CEFC 2016, Miami, United States, 13/11/16. https://doi.org/10.1109/CEFC.2016.7816171

A mesh-refinement method based on artificial neural networks for electrical impedance tomography. / Martin, Sebastien; Choi, T.m.
IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation. Institute of Electrical and Electronics Engineers Inc., 2017. 7816171 (IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A mesh-refinement method based on artificial neural networks for electrical impedance tomography

AU - Martin, Sebastien

AU - Choi, T.m.

PY - 2017/1/12

Y1 - 2017/1/12

N2 - Inverse boundary problem are usually solved with a finite element model, with either limited accuracy or huge computation resources. Using a fine mesh results in a computationally demanding task, but when the region of interest is known, when one can easily locally refine the model, aiming for greater local accuracy. In this paper, a novel approach uses artificial neural network to estimate the location of the region of interest and refine this region before solving the inverse problem. The idea is illustrated by solving the electrical impedance tomography inverse problem. Result shows that the proposed method increases the accuracy without significantly affecting the computation resources necessary to solve the inverse problem.

AB - Inverse boundary problem are usually solved with a finite element model, with either limited accuracy or huge computation resources. Using a fine mesh results in a computationally demanding task, but when the region of interest is known, when one can easily locally refine the model, aiming for greater local accuracy. In this paper, a novel approach uses artificial neural network to estimate the location of the region of interest and refine this region before solving the inverse problem. The idea is illustrated by solving the electrical impedance tomography inverse problem. Result shows that the proposed method increases the accuracy without significantly affecting the computation resources necessary to solve the inverse problem.

KW - Adaptive Mesh Refinement

KW - Artificial Neural Network

KW - Electrical Impedance Tomography

KW - Finite Element Method

UR - http://www.scopus.com/inward/record.url?scp=85012000551&partnerID=8YFLogxK

U2 - 10.1109/CEFC.2016.7816171

DO - 10.1109/CEFC.2016.7816171

M3 - Conference contribution

AN - SCOPUS:85012000551

T3 - IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation

BT - IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th Biennial IEEE Conference on Electromagnetic Field Computation, IEEE CEFC 2016

Y2 - 13 November 2016 through 16 November 2016

ER -

Martin S, Choi TM. A mesh-refinement method based on artificial neural networks for electrical impedance tomography. In IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation. Institute of Electrical and Electronics Engineers Inc. 2017. 7816171. (IEEE CEFC 2016 - 17th Biennial Conference on Electromagnetic Field Computation). doi: 10.1109/CEFC.2016.7816171

A mesh-refinement method based on artificial neural networks for electrical impedance tomography

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this