Efficient Multitask Structure-Aware Sparse Bayesian Learning for Frequency-Difference Electrical Impedance Tomography

Liu, Shengheng; Huang, Yongming; Wu, Haowei; Tan, Chao; Jia, Jiabin

doi:10.1109/tii.2020.2965202

Cited by 100 publications

(51 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multikernel approach could lead us to the simultaneous estimation of the extended (or composite) lead field matrix and the EEG sources in an iterative fashion. Furthermore, spatiotemporal versions of our model based on the MMV model [ 1 , 2 , 19 ] could be devised in order to study EEG microstates [ 42 ] in BCI domain. In addition to the above, borrowing ideas from image superresolution [ 43 ], we could provide brain imaging techniques with increased spatial resolution.…”

Section: Discussionmentioning

confidence: 99%

A Novel Bayesian Approach for EEG Source Localization

Oikonomou

Kompatsiaris

2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

We propose a new method for EEG source localization. An efficient solution to this problem requires choosing an appropriate regularization term in order to constraint the original problem. In our work, we adopt the Bayesian framework to place constraints; hence, the regularization term is closely connected to the prior distribution. More specifically, we propose a new sparse prior for the localization of EEG sources. The proposed prior distribution has sparse properties favoring focal EEG sources. In order to obtain an efficient algorithm, we use the variational Bayesian (VB) framework which provides us with a tractable iterative algorithm of closed-form equations. Additionally, we provide extensions of our method in cases where we observe group structures and spatially extended EEG sources. We have performed experiments using synthetic EEG data and real EEG data from three publicly available datasets. The real EEG data are produced due to the presentation of auditory and visual stimulus. We compare the proposed method with well-known approaches of EEG source localization and the results have shown that our method presents state-of-the-art performance, especially in cases where we expect few activated brain regions. The proposed method can effectively detect EEG sources in various circumstances. Overall, the proposed sparse prior for EEG source localization results in more accurate localization of EEG sources than state-of-the-art approaches.

show abstract

Section: Discussionmentioning

confidence: 99%

A Novel Bayesian Approach for EEG Source Localization

Oikonomou

Kompatsiaris

2020

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…High-quality CT image reconstruction from limited projection data is challenging. Learning based algorithms such as structure-aware sparse Bayesian learning [22] could yield improved performance in reconstructing tomographic images from limited data, since structural prior knowledge is exploited. Enhancing the proposed algorithm in a learning-based framework using prior knowledge will be the topic of future research.…”

Section: International Journal Of Biomedical Imagingmentioning

confidence: 99%

An Algorithm ofl1-Norm andl0-Norm Regularization Algorithm for CT Image Reconstruction from Limited Projection

Feng

Zhu

2020

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

The l1-norm regularization has attracted attention for image reconstruction in computed tomography. The l0-norm of the gradients of an image provides a measure of the sparsity of gradients of the image. In this paper, we present a new combined l1-norm and l0-norm regularization model for image reconstruction from limited projection data in computed tomography. We also propose an algorithm in the algebraic framework to solve the optimization effectively using the nonmonotone alternating direction algorithm with hard thresholding method. Numerical experiments indicate that this new algorithm makes much improvement by involving l0-norm regularization.

show abstract

“…The sparse basis and measurement matrix can be used to control the sampling rate of the light field. Sparse light field recovery is based on the sparse Bayes learning (SBL) algorithm [18], [19]. Finally, we derive a learning machine for light field SBL, which can improve the rendering quality based on a given set of captured multiview images.…”

Section: (S T)mentioning

confidence: 99%

“…These binary data are used as training data vectors. Additionally, four light field sparse bases Ψ s , Ψ t , Ψ u , and Ψ v are given by (13), and four measurement matrices Φ s , Φ t , Φ u , and Φ v of the light field are given by (17) and (18).…”

Section: B Light Field Sbl Learning Machinementioning

confidence: 99%