We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
PARAFAC-Based Blind Identification of Underdetermined Mixtures Using Gaussian Mixture Model.
- Authors
Gu, Fanglin; Zhang, Hang; Wang, Wenwu; Zhu, Desheng
- Abstract
This paper presents a novel algorithm, named GMM-PARAFAC, for blind identification of underdetermined instantaneous linear mixtures. The GMM-PARAFAC algorithm uses Gaussian mixture model (GMM) to model non-Gaussianity of the independent sources. We show that the distribution of the observations can also be modeled by a GMM, and derive a maximum-likelihood function with regard to the mixing matrix by estimating the GMM parameters of the observations via the expectation-maximization algorithm. In order to reduce the computation complexity, the mixing matrix is estimated by maximizing a tight upper bound of the likelihood instead of the log-likelihood itself. The maximum of the tight upper bound is obtained by decomposition of a three-way tensor which is obtained by stacking the covariance matrices of the GMM of the observations. Simulation results validate the superiority of the GMM-PARAFAC algorithm.
- Subjects
GAUSSIAN mixture models; BLIND channel identification (Telecommunications); IDEAL independent sources (Electric circuits); COMPUTATIONAL complexity; COVARIANCE matrices; DECOMPOSITION method
- Publication
Circuits, Systems & Signal Processing, 2014, Vol 33, Issue 6, p1841
- ISSN
0278-081X
- Publication type
Article
- DOI
10.1007/s00034-013-9719-8