Efficient Markov chain Monte Carlo sampling for electrical impedance tomography
Journal Title: Computer Assisted Methods in Engineering and Science - Year 2014, Vol 21, Issue 3
Abstract
This paper studies electrical impedance tomography (EIT) using Bayesian inference [1]. The resulting posterior distribution is sampled by Markov chain Monte Carlo (MCMC) [2]. This paper studies a toy model of EIT as the one presented in [3], and focuses on efficient MCMC sampling for this model. First, this paper analyses the computation of forward map of EIT which is the bottleneck of each MCMC update. The forward map is computed by the finite element method [4]. Here its exact computation was conducted up to five times more efficient, by updating the Cholesky factor of the stiffness matrix [5]. Since the forward map computation takes up nearly all the CPU time in each MCMC update, the overall efficiency of MCMC algorithms can be improved almost to the same amount. The forward map can also be computed approximately by local linearisation, and this approximate computation is much more efficient than the exact one. Without loss of efficiency, this approximate computation is more accurate here, after a log transformation is introduced into the local linearisation process. Later on, this improvement of accuracy will play an important role when the approximate computation of forward map will be employed for devising efficient MCMC algorithms. Second, the paper presents two novel MCMC algorithms for sampling the posterior distribution in the toy model of EIT. The two algorithms are made within the 'multiple prior update' [6] and 'the delayed-acceptance Metropolis-Hastings' [7] schemes respectively. Both of them have MCMC proposals that are made of localized updates, so that the forward map computation in each MCMC update can be made efficient by updating the Cholesky factor of the stiffness matrix. Both algorithms' performances are compared to that of the standard single-site Metropolis [8], which is considered hard to surpass [3]. The algorithm of 'multiple prior update' is found to be six times more efficient, while 'the delayed-acceptance Metropolis-Hastings' with single-site update is at least twice more efficient.
Authors and Affiliations
Erfang Ma
Keywords
Related Articles
- EP ID EP73497
- DOI -
- Views 197
- Downloads 0
Identification in multiscale thermoelastic problems
The paper deals with the identification in multiscale analysis of structures under thermal and mechanical loads. A two-scale model of porous materials is examined. Direct thermoelastic analyses with representative volume...
Optimization of functionally gradient materials in valve design under cyclic thermal and mechanical loading
The robust and simple optimization method of functionally graded material (FGM) for combined cyclic thermal and mechanical loading with application to valve design is proposed. The optimization procedure starts from the...
Neural networks in the advisory system for repairs of industrial concrete floors
An advisory system for repairs of industrial concrete floors is a supporting tool for making material and technological decisions in the sphere of problems of recurrent character. The presented advisory system has the ch...
On inverse form finding for orthotropic plasticity
Inverse form finding aims to determine the optimum blank design of a workpiece whereby the desired spatial configuration that is obtained after a forming process, the boundary conditions and the applied loads are known....
Neural modelling of compactibility characteristics of cohesionless soil. (Received in the final form July 30, 2010)
Compaction is the method of in-situ soil modification to improve its engineering properties. Two key compactibility parameters are: the maximum dry density ρd max and the corresponding optimum water content wopt. They ar...