The Parallel Research of MP Sparse Decomposition in Grid Environment

Abstract:

Signal sparse representation in signal processing has many important applications, but the calculation amount of sparse decomposition is difficult to spread to realize industrialization because of its enormous calculation amount. At present, most of us make efforts to shorten the time of sparse decomposition calculation and improve the algorithm in order to make sparse decomposition feasible in its actual application. Although we make great achievements, the time cost by these improved algorithms is still difficult to be accepted. With the rapid development of internet in recent years, cloud computing and grid computing improve the computational ability so greatly that it can make a large amount of data calculation possible in reality. We introduce the grid computing into the sparse calculation so as to make its applicability possible in the practice. The thesis is to build a grid frame work. The performance of sparse decomposition is greatly improved by its calculating allocation to each node of grid computing, which makes it possible in its practical application.

• Periodical: Advanced Materials Research (Volume 647)
• Pages: 891-895
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.647.891
• Online since: January 2013
• Authors: Yong Li
• Keywords: Grid, Over-Complete Dictionary, Sparse Representation

References

[1] Ming C, Yong L, Jian Y Z, An improved parallel FFT algorithm and application in Grid Environment. Granular Computing, 2010, 1(1): 111-114.

[2] Yue Q, the graphics processor CUDA programming model applied research. Computer & Digital Engineering, 2008, 36(12): 177-180.

[3] Andrle M, Rebollo N L, Sagianos E, Backward-optimized orthogonal matching pursuit approach. IEEE Signal Processing Letters, 2004, 11(9): 705-708.

DOI: 10.1109/lsp.2004.833503

[4] Yan Q C, Application of grid computation technology on the large scale CFD computation. Acta aerodynamica sinica, 2009, 27(6).

[5] Aharon M, Elad M, Bruckstein A M, The K-SVD: An Algorithm for Designing of Overcomplete Dictionaries for Sparse Representation, IEEE Tarans on Signal Processing, 2006, 54(11): 4311-4322.

DOI: 10.1109/tsp.2006.881199

[6] Foster I, Kesselman C, Making the Global Infrastructure a Reality. The Physiology of the Grid, 2003, (1): 217 - 249.