CONSTRUCT DEEP NEURAL NETWORKS BASED ON DIRECT SAMPLING METHODS FOR SOLVING ELECTRICAL IMPEDANCE TOMOGRAPHY

doi:10.1137/20M1367350

	CONSTRUCT DEEP NEURAL NETWORKS BASED ON DIRECT SAMPLING METHODS FOR SOLVING ELECTRICAL IMPEDANCE TOMOGRAPHY
	Guo, Ruchi 1; Jiang, Jiahua2
	2021
发表期刊	SIAM JOURNAL ON SCIENTIFIC COMPUTING (IF:3.0[JCR-2023],3.2[5-Year])
ISSN	1064-8275
EISSN	1095-7197
卷号	43 期号:3 页码:B678-B711
DOI	10.1137/20M1367350
摘要	This work investigates the electrical impedance tomography problem when only limited boundary measurements are available, which is known to be challenging due to the extreme ill-posedness. Based on the direct sampling method (DSM) introduced in [Y. T. Chow, K. Ito, and J. Zou, Inverse Problems, 30 (2016), 095003], we propose deep direct sampling methods (DDSMs) to locate inhomogeneous inclusions in which two types of deep neural networks (DNNs) are constructed to approximate the index function (functional): fully connected neural networks and convolutional neural networks. The proposed DDSMs are easy to be implemented, capable of incorporating multiple Cauchy data pairs to achieve high-quality reconstruction and highly robust with respect to large noise. Additionally, the implementation of DDSMs adopts offine-online decomposition, which helps to reduce a lot of computational costs and makes DDSMs as efficient as the conventional DSM proposed by Chow, Ito, and Zou. The numerical experiments are presented to demonstrate the efficacy and show the potential benefits of combining DNN with DSM.
关键词	deep learning inverse problems direct sampling methods electrical impedance tomography reconstruction algorithm limited boundary data Convolutional neural networks Electric impedance Electric impedance measurement Electric impedance tomography Inverse problems Boundary measurements Computational costs Direct sampling method Electrical impedance tomography Fully connected neural network High quality reconstruction Inhomogeneous inclusions Numerical experiments
URL	查看原文
收录类别	SCIE ; EI
语种	英语
WOS研究方向	Mathematics
WOS类目	Mathematics, Applied
WOS记录号	WOS:000674142500039
出版者	SIAM PUBLICATIONS
EI入藏号	20212410494411
EI主题词	Deep neural networks
EI分类号	701.1 Electricity: Basic Concepts and Phenomena ; 942.2 Electric Variables Measurements
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/127945
专题	信息科学与技术学院数学科学研究所_PI研究组(P)_姜嘉骅组
通讯作者	Guo, Ruchi
作者单位	1.Univ Calif Irvine, Dept Math, Irvine, CA 92697 USA; 2.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai, Peoples R China
推荐引用方式 GB/T 7714	Guo, Ruchi,Jiang, Jiahua. CONSTRUCT DEEP NEURAL NETWORKS BASED ON DIRECT SAMPLING METHODS FOR SOLVING ELECTRICAL IMPEDANCE TOMOGRAPHY[J]. SIAM JOURNAL ON SCIENTIFIC COMPUTING,2021,43(3):B678-B711.
APA	Guo, Ruchi,&Jiang, Jiahua.(2021).CONSTRUCT DEEP NEURAL NETWORKS BASED ON DIRECT SAMPLING METHODS FOR SOLVING ELECTRICAL IMPEDANCE TOMOGRAPHY.SIAM JOURNAL ON SCIENTIFIC COMPUTING,43(3),B678-B711.
MLA	Guo, Ruchi,et al."CONSTRUCT DEEP NEURAL NETWORKS BASED ON DIRECT SAMPLING METHODS FOR SOLVING ELECTRICAL IMPEDANCE TOMOGRAPHY".SIAM JOURNAL ON SCIENTIFIC COMPUTING 43.3(2021):B678-B711.