Title :
A fast geometric method for blind separation of sparse sources
Author :
Mebel, Ofir ; Avargel, Yekutiel ; Cohen, Israel
Author_Institution :
Dept. of Electr. Eng., Technion - Israel Inst. of Technol., Haifa, Israel
Abstract :
In this paper, we introduce a new geometry-based approach for blind separation of sparse sources modeled by a linear instantaneous mixtures model. The algorithm assumes at least two mixtures of any number of sources, in addition to the sources being sparse in some representation. Formulating the problem as a clustering problem, the unknown mixing matrix is estimated from the transformed data up to the usual indeterminacies. An extraction method is then used for separation of the sources according to transform-space directions induced by the mixing-matrix estimation process, with an optional noise reduction scheme. Because of the geometric nature of the methods, they are extremely fast and are suitable for use in real-time systems. Simulation results demonstrate the effectiveness of the proposed algorithm for different signal-to-noise ratio (SNR) values.
Keywords :
blind source separation; geometry; signal representation; sparse matrices; blind source separation; clustering problem; fast geometric method; linear instantaneous mixtures model; mixing-matrix estimation process; optional noise reduction scheme; real-time systems; sparse representation; Cities and towns; Clustering algorithms; Data mining; Noise reduction; Real time systems; Signal sampling; Signal to noise ratio; Solid modeling; Source separation; Sparse matrices; Blind source separation; clustering; sparse representation;
Conference_Titel :
Electrical and Electronics Engineers in Israel, 2008. IEEEI 2008. IEEE 25th Convention of
Conference_Location :
Eilat
Print_ISBN :
978-1-4244-2481-8
Electronic_ISBN :
978-1-4244-2482-5
DOI :
10.1109/EEEI.2008.4736683
