Electroencephalography (EEG) signal has been playing a crucial role in clinical diagnosis and treatment of neurological diseases. However, it is very challenging to efficiently reconstruct the high-resolution brain image from very few scalp EEG measurements due to high ill-posedness. Recently some efforts have been devoted to developing EEG source reconstruction methods using various forms of regularization, including the ℓ1-norm, the total variation (TV), as well as the fractional-order TV. However, since high-dimensional data are very large, these methods are difficult to implement. In this paper, we propose accelerated methods for EEG source imaging based on the TV regularization and its variants. Since the gradient/fractional-order gradient operators have coordinate friendly structures, we apply the Chambolle-Pock and ARock algorithms, along with diagonal preconditioning. In our algorithms, the coordinates of primal and dual variables are updated in an asynchronously parallel fashion. A variety of experiments show that the proposed algorithms have more rapid convergence than the state-of-the-art methods and have the potential to achieve the real-time temporal resolution.
|Title of host publication||8th International IEEE EMBS Conference on Neural Engineering, NER 2017|
|Number of pages||4|
|State||Published - Aug 10 2017|
|Event||8th International IEEE EMBS Conference on Neural Engineering, NER 2017 - Shanghai, China|
Duration: May 25 2017 → May 28 2017
|Name||International IEEE/EMBS Conference on Neural Engineering, NER|
|Conference||8th International IEEE EMBS Conference on Neural Engineering, NER 2017|
|Period||5/25/17 → 5/28/17|
Bibliographical noteFunding Information:
*This work is supported in part by the California Capital Equity LLC, the Keck foundation, NSF DMS-1317602, NSF ECCS-1462397 and ONR N000141612157.
© 2017 IEEE.
ASJC Scopus subject areas
- Artificial Intelligence
- Mechanical Engineering