Abstract | ||
---|---|---|
In view of the traditional blind source separation methods cannot be applied to separate the mixed signal in single-channel communication, a modified single-channel signals blind separation method using Empirical Mode Decomposition (EMD) and Independent Component Analysis (ICA) is proposed in this paper. In our method, EMD is employed to decompose the preprocessed received signal into some non-overlapping Intrinsic Mode Functions (IMF). In order to construct the input matrix of ICA, optimum IMFs are selected based on their energy in time domain. Finally, ICA is applied to extract and recover the source signal from the received signal. Simulation results show that our method has the same performance with the exiting method, while the system running time has been greatly shortened. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-662-43908-1_10 | Communications in Computer and Information Science |
Keywords | Field | DocType |
Single-channel,Blind source separation,EMD,ICA | Time domain,Pattern recognition,Matrix (mathematics),Communication channel,Independent component analysis,Artificial intelligence,Mixed-signal integrated circuit,Engineering,Blind signal separation,Hilbert–Huang transform | Conference |
Volume | ISSN | Citations |
426 | 1865-0929 | 0 |
PageRank | References | Authors |
0.34 | 3 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jiao Wang | 1 | 17 | 8.27 |
yulin liu | 2 | 0 | 1.01 |
zhichao chao | 3 | 0 | 0.34 |
wei he | 4 | 0 | 0.34 |