导航

ACTA AERONAUTICAET ASTRONAUTICA SINICA ›› 2015, Vol. 36 ›› Issue (10): 3393-3400.doi: 10.7527/S1000-6893.2014.0319

• Electronics and Control • Previous Articles     Next Articles

Canonical decomposition approach for underdetermined blind separation of non-disjoint sources

AI Xiaofan, LUO Yongjiang, ZHAO Guoqing   

  1. Key Laboratory of Electronic Information Countermeasure and Simulation Technology, Ministry of Education, Xidian University, Xi'an 710071, China
  • Received:2014-09-22 Revised:2014-11-19 Online:2015-10-15 Published:2014-11-24
  • Supported by:

    Fundamental Research Funds for the Central Universities (K5051302018)

Abstract:

This paper proposes a method of underdetermined blind separation of non-disjoint sources (UBSS) based on fourth-order cumulant (FO) and tensor decomposition. By semi-invariance of high-order cumulant, the FO is presented as statistics of the observed signal as fourth-order tensor; hence the mixed matrix is estimated by tensor decomposition with line search alternating least square. Finally, with the estimated matrix, sources are recovered by minimum mean-squared error-based beamforming. Simulations illustrate the validity of the method and show that the proposed method outperforms the existing methods in performance significantly.

Key words: blind source separation, underdetermined mixtures, non-disjoint source, fourth-order cumulant, tensor canonical decomposition

CLC Number: