Publication: Time Sequence Learning for Electrical Impedance Tomography Using Bayesian Spatiotemporal Priors
0
0
Issued Date
2020
Resource Type
File Type
application/pdf
ISSN
189456
Other identifier(s)
2-s2.0-85083076658
Rights Holder(s)
มหาวิทยาลัยศรีนครินทรวิโรฒ
Bibliographic Citation
IEEE Transactions on Instrumentation and Measurement. Vol 69, No.9 (2020), p.6045-6057
Suggested Citation
Liu S., Cao R., Huang Y., Ouypornkochagorn T., Ji J. Time Sequence Learning for Electrical Impedance Tomography Using Bayesian Spatiotemporal Priors. IEEE Transactions on Instrumentation and Measurement. Vol 69, No.9 (2020), p.6045-6057. doi:10.1109/TIM.2020.2972172 Retrieved from: https://hdl.handle.net/20.500.14740/4428
Author(s)
Abstract
As an emerging technology for continuous monitoring of a bounded domain, electrical impedance tomography (EIT) gains increasing popularity in various applications. Despite unprecedented progress, the EIT inverse solvers at the present stage are incompetent to guarantee sufficient fidelity as well as efficient investigation of the internal impedance dynamics. In this context, this article introduces a spatiotemporal structure-aware sparse Bayesian learning (SA-SBL) framework for solving the time-continuous EIT inverse problems. Specifically, in the process of reconstructing the EIT time sequence, both intraframe spatial clustering and interframe temporal continuity are explored and exploited in an unsupervised manner by using the hierarchical Bayesian model and structure-aware priors. A multiple measurement vector model is established to capture the spatiotemporal correlations and describe the underlying multidimensional reconstruction problem. The resultant large-scale inversion is efficiently solved by applying the approximate message passing to the expectation updating. A speedup ratio of ON2/M is achieved compared with original SA-SBL. Simulation results indicate that the proposed algorithm exhibits superior reconstruction performance to the existing methods, where the scores evaluated by the quantitative metrics are improved by at least 17%. The presented algorithm is envisioned to offer broader applicability since it yields improved image quality and recovery efficiency. © 1963-2012 IEEE.
Subject(s)
Bayesian networks
Electric impedance
Electric impedance measurement
Electric impedance tomography
Hierarchical clustering
Image enhancement
Message passing
Electrical impe dance tomography (EIT)
Electrical impedance tomography
Hierarchical Bayesian modeling
Multidimensional reconstruction
Multiple measurement vectors
Sparse Bayesian learning
Spatio-temporal structures
Spatiotemporal correlation
Inverse problems
Electric impedance
Electric impedance measurement
Electric impedance tomography
Hierarchical clustering
Image enhancement
Message passing
Electrical impe dance tomography (EIT)
Electrical impedance tomography
Hierarchical Bayesian modeling
Multidimensional reconstruction
Multiple measurement vectors
Sparse Bayesian learning
Spatio-temporal structures
Spatiotemporal correlation
Inverse problems