2016
DOI: 10.15439/2016f344
|View full text |Cite
|
Sign up to set email alerts
|

Acceleration of image reconstruction in 3D Electrical Capacitance Tomography in heterogeneous, multi-GPU system using sparse matrix computations and Finite Element Method

Abstract: Abstract-3D Electrical Capacitance Tomography provides a lot of challenging computational issues that have been reported in the past by many researchers. Image reconstruction using deterministic methods requires execution of many basic operations of linear algebra. Due to significant sizes of matrices used in ECT for image reconstruction and the fact that best image quality is achieved by using algorithms of which significant part is FEM and which are hard to parallelize or distribute. In order to solve these … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
8
0

Year Published

2018
2018
2020
2020

Publication Types

Select...
4
4

Relationship

2
6

Authors

Journals

citations
Cited by 8 publications
(8 citation statements)
references
References 5 publications
0
8
0
Order By: Relevance
“…Inverse problem is nonlinear and therefore two main groups of image reconstruction algorithms can be distinguished: nonlinear and linear. Non-linear algorithms are more accurate but slower [16]. Linear algorithms use approximate linear model, which is less accurate but simple and useful in engineering praxis.…”
Section: Image Reconstruction In Ectmentioning
confidence: 99%
See 1 more Smart Citation
“…Inverse problem is nonlinear and therefore two main groups of image reconstruction algorithms can be distinguished: nonlinear and linear. Non-linear algorithms are more accurate but slower [16]. Linear algorithms use approximate linear model, which is less accurate but simple and useful in engineering praxis.…”
Section: Image Reconstruction In Ectmentioning
confidence: 99%
“…In dynamic measurements of fast changing media, time of measurement and data processing is equally or even more important parameter than accuracy. Therefore different solutions accelerating these calculation have been reported in the past, especially dealing with parallel computing [11][12][13][14][15], sparse matrices and Finite Elements Method [16], Fourier-based sparse representations [17], neural networks approach [18,19], fuzzy logic [20] or field-programmable gate array (FPGA) implementation [21]. Usually a compromise between accuracy and rapidity of ECT measurement must be taken.…”
Section: Introductionmentioning
confidence: 99%
“…As a result of the earlier performed studies [8] algorithms used in ECT [9]. The earlier developed solution was based on the Xgrid platform, used as a network layer.…”
Section: Design Assumptionsmentioning
confidence: 99%
“…In order to achieve a high quality of 3D image, complex reconstruction algorithms performing many matrix calculations have to be applied. Therefore different solutions accelerating these calculation have been reported in the past by the Authors [8] [14], especially these dealing with sparse matrices and Finite Elements Method [9] as well as neural networks approach [5] [6] and even fuzzy logic [21].…”
Section: Introductionmentioning
confidence: 99%
“…Superior performance was achieved in [20] when the algorithm uses the intrinsic fine parallelism ability of the FPGA. In addition, the substantial functioning of Graphics Processing Units (GPU) for arithmetically exhaustive algorithms drives the implementation of the 3D ECT system [21]. However, their performance is lower than the FPGA since it needs a lot of random off-chip memory access.…”
Section: Introductionmentioning
confidence: 99%