Anomaly Location Detection with Electrical Impedance Tomography Using Multilayer Perceptrons

Timo Huuhtanen; Alex Jung

doi:10.1109/MLSP49062.2020.9231818

Anomaly Location Detection with Electrical Impedance Tomography Using Multilayer Perceptrons

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

5 Citations (Scopus)

148 Downloads (Pure)

Abstract

Electrical impedance tomography (EIT) does imaging by solving a nonlinear ill-posed inverse problem. Recently, there has been an increasing interest in solving this problem with artificial neural networks. However, a systematic understanding of the optimal neural network architecture for this problem is still lacking. This paper compares the performance of different multilayer perceptron algorithms for detecting the location of an anomaly on a sensing surface by solving the EIT inverse problem. We generate synthetic data with varying anomaly sizes/locations and compare a wide range of multilayer perceptron algorithms by simulations. Our results indicate that increasing the dimensions of the perceptron improves performance, but this improvement saturates soon. The best performance is achieved when using the multilayer perceptron for regression and Gaussian noise addition as the regularization method.

Original language	English
Title of host publication	Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020
Publisher	IEEE
Pages	1-6
Number of pages	6
ISBN (Electronic)	9781728166629
DOIs	https://doi.org/10.1109/MLSP49062.2020.9231818
Publication status	Published - 23 Sept 2020
MoE publication type	A4 Conference publication
Event	IEEE International Workshop on Machine Learning for Signal Processing - Aalto University, Espoo, Finland Duration: 21 Sept 2020 → 24 Sept 2020 Conference number: 30 https://ieeemlsp.cc

Publication series

Name	Machine Learning for Signal Processing
Publisher	IEEE
ISSN (Electronic)	1551-2541

Workshop

Workshop	IEEE International Workshop on Machine Learning for Signal Processing
Abbreviated title	MLSP
Country/Territory	Finland
City	Espoo
Period	21/09/2020 → 24/09/2020
Internet address	https://ieeemlsp.cc

Keywords

electrical impedance tomography (EIT)
multilayer perceptrons
anomaly detection

Access to Document

10.1109/MLSP49062.2020.9231818

SCI_Huuhtanen_Anomaly.PID6535975Accepted author manuscript, 524 KB

Cite this

@inproceedings{3b7498ef177d4fb08bd526df5da63e87,

title = "Anomaly Location Detection with Electrical Impedance Tomography Using Multilayer Perceptrons",

abstract = "Electrical impedance tomography (EIT) does imaging by solving a nonlinear ill-posed inverse problem. Recently, there has been an increasing interest in solving this problem with artificial neural networks. However, a systematic understanding of the optimal neural network architecture for this problem is still lacking. This paper compares the performance of different multilayer perceptron algorithms for detecting the location of an anomaly on a sensing surface by solving the EIT inverse problem. We generate synthetic data with varying anomaly sizes/locations and compare a wide range of multilayer perceptron algorithms by simulations. Our results indicate that increasing the dimensions of the perceptron improves performance, but this improvement saturates soon. The best performance is achieved when using the multilayer perceptron for regression and Gaussian noise addition as the regularization method.",

keywords = "electrical impedance tomography (EIT), multilayer perceptrons, anomaly detection",

author = "Timo Huuhtanen and Alex Jung",

year = "2020",

month = sep,

day = "23",

doi = "10.1109/MLSP49062.2020.9231818",

language = "English",

series = "Machine Learning for Signal Processing",

publisher = "IEEE",

pages = "1--6",

booktitle = "Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020",

address = "United States",

note = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP ; Conference date: 21-09-2020 Through 24-09-2020",

url = "https://ieeemlsp.cc",

}

Huuhtanen, T & Jung, A 2020, Anomaly Location Detection with Electrical Impedance Tomography Using Multilayer Perceptrons. in Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020., 9231818, Machine Learning for Signal Processing, IEEE, pp. 1-6, IEEE International Workshop on Machine Learning for Signal Processing, Espoo, Finland, 21/09/2020. https://doi.org/10.1109/MLSP49062.2020.9231818

Anomaly Location Detection with Electrical Impedance Tomography Using Multilayer Perceptrons. / Huuhtanen, Timo ; Jung, Alex.
Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020. IEEE, 2020. p. 1-6 9231818 (Machine Learning for Signal Processing).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Anomaly Location Detection with Electrical Impedance Tomography Using Multilayer Perceptrons

AU - Huuhtanen, Timo

AU - Jung, Alex

N1 - Conference code: 30

PY - 2020/9/23

Y1 - 2020/9/23

N2 - Electrical impedance tomography (EIT) does imaging by solving a nonlinear ill-posed inverse problem. Recently, there has been an increasing interest in solving this problem with artificial neural networks. However, a systematic understanding of the optimal neural network architecture for this problem is still lacking. This paper compares the performance of different multilayer perceptron algorithms for detecting the location of an anomaly on a sensing surface by solving the EIT inverse problem. We generate synthetic data with varying anomaly sizes/locations and compare a wide range of multilayer perceptron algorithms by simulations. Our results indicate that increasing the dimensions of the perceptron improves performance, but this improvement saturates soon. The best performance is achieved when using the multilayer perceptron for regression and Gaussian noise addition as the regularization method.

AB - Electrical impedance tomography (EIT) does imaging by solving a nonlinear ill-posed inverse problem. Recently, there has been an increasing interest in solving this problem with artificial neural networks. However, a systematic understanding of the optimal neural network architecture for this problem is still lacking. This paper compares the performance of different multilayer perceptron algorithms for detecting the location of an anomaly on a sensing surface by solving the EIT inverse problem. We generate synthetic data with varying anomaly sizes/locations and compare a wide range of multilayer perceptron algorithms by simulations. Our results indicate that increasing the dimensions of the perceptron improves performance, but this improvement saturates soon. The best performance is achieved when using the multilayer perceptron for regression and Gaussian noise addition as the regularization method.

KW - electrical impedance tomography (EIT)

KW - multilayer perceptrons

KW - anomaly detection

UR - https://www.scopus.com/pages/publications/85096496259

U2 - 10.1109/MLSP49062.2020.9231818

DO - 10.1109/MLSP49062.2020.9231818

M3 - Conference article in proceedings

T3 - Machine Learning for Signal Processing

SP - 1

EP - 6

BT - Proceedings of the 2020 IEEE 30th International Workshop on Machine Learning for Signal Processing, MLSP 2020

PB - IEEE

T2 - IEEE International Workshop on Machine Learning for Signal Processing

Y2 - 21 September 2020 through 24 September 2020

ER -

Anomaly Location Detection with Electrical Impedance Tomography Using Multilayer Perceptrons

Abstract

Publication series

Workshop

Keywords

Access to Document

Other files and links

Fingerprint

Cite this