Time-Frequency Atom Decomposition Based on Seeker Optimization Algorithm

Sparse representation of signals has many important applications in signal processing. However, this issue is well known as a complex and NP problem, which is a key factor to depress the application and progress of sparse decomposition. In this work, seeker optimization algorithm(SOA)- based method is used to search for the best matching atoms in sparse decomposition. For comparision, the conventional matching pursuit (MP) method and two versions of PSO algorithms are also consid- ered in the simulation studies. The simulation results show that the proposed approach is an effective and reliable technique for time-frequency atom decomposition.

[1]  Wang Jian-ying.  Signal Sparse Decomposition Based on MP with AA , 2006 .

[2]  Stéphane Mallat,et al.  Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..

[3]  Shao Jun.  Sparse Decomposition Based on Structural Properties of Atom Dictionary , 2005 .

[4]  Stéphane Mallat,et al.  Matching pursuit of images , 1995, Proceedings., International Conference on Image Processing.

[5]  Bruno Torrésani,et al.  Time-Frequency and Time-Scale Analysis , 1999 .

[6]  Wang Jian-ying.  MP-based Signal Sparse Decomposition by Simulated Annealing , 2009 .

[7]  Chaohua Dai,et al.  Seeker Optimization Algorithm , 2006, 2006 International Conference on Computational Intelligence and Security.

[8]  Philipos C. Loizou,et al.  Voiced/unvoiced speech discrimination in noise using Gabor atomic decomposition , 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..