TY - JOUR
T1 - High-Dimensional Uncertainty Quantification in Electrical Impedance Tomography Forward Problem Based on Deep Neural Network
AU - Zhao, Yingge
AU - Wang, Lingyue
AU - Li, Ying
AU - He, Renjie
AU - Ma, Chonglei
N1 - Funding Information:
This work was supported in part by the Natural Science Foundation of Hebei Province under Grant E2015202050; in part by the Key Science and Technology Project of Henan Province under Grant 222102210147; and in part by the Outstanding Young Teachers Program of Sanquan College, Xinxiang Medical University.
Publisher Copyright:
© 2013 IEEE.
PY - 2023
Y1 - 2023
N2 - In electrical impedance tomography (EIT), the uncertainty of conductivity distribution may cause the uncertainty in the forward calculation and further affect the inverse problem. In this paper, an improved univariate dimension reduction method based on deep neural network (DNN-UDR) is proposed for the high-dimensional uncertainty quantification in EIT forward problem. Firstly, DNN is studied to build a substitute model for EIT forward problem in order to solve the high-dimensional problem. Three normalized circular finite element models are established with random uniform conductivity distribution. Then UDR is used to analyze and quantify the uncertainty in the simulation with the form of probability. Compared with Monte Carlo simulation (MCS), the probability distribution of voltage is fitted, and the quantification indicators such as mean, variance, variation coefficient and covariance, are also consistent. On the other hand, with the increase of parameter dimensions, DNN-UDR accelerates the computations obviously. This indicates that DNN-UDR is effective and has high structural stability, accurate prediction results and high computational efficiency.
AB - In electrical impedance tomography (EIT), the uncertainty of conductivity distribution may cause the uncertainty in the forward calculation and further affect the inverse problem. In this paper, an improved univariate dimension reduction method based on deep neural network (DNN-UDR) is proposed for the high-dimensional uncertainty quantification in EIT forward problem. Firstly, DNN is studied to build a substitute model for EIT forward problem in order to solve the high-dimensional problem. Three normalized circular finite element models are established with random uniform conductivity distribution. Then UDR is used to analyze and quantify the uncertainty in the simulation with the form of probability. Compared with Monte Carlo simulation (MCS), the probability distribution of voltage is fitted, and the quantification indicators such as mean, variance, variation coefficient and covariance, are also consistent. On the other hand, with the increase of parameter dimensions, DNN-UDR accelerates the computations obviously. This indicates that DNN-UDR is effective and has high structural stability, accurate prediction results and high computational efficiency.
KW - Electrical impedance tomography
KW - high-dimensional uncertainty quantification
KW - Monte Carlo simulation
KW - substitute model
UR - http://www.scopus.com/inward/record.url?scp=85161057444&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85161057444&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2023.3281366
DO - 10.1109/ACCESS.2023.3281366
M3 - Article
AN - SCOPUS:85161057444
SN - 2169-3536
VL - 11
SP - 54957
EP - 54967
JO - IEEE Access
JF - IEEE Access
ER -