Deakin University
Browse

On blind separability based on the temporal predictability method

Download (347.1 kB)
journal contribution
posted on 2009-01-01, 00:00 authored by S Xie, G Zhou, Zuyuan Yang, Y Fu
This letter discusses blind separability based on temporal predictability (Stone, 2001; Xie, He, & Fu, 2005). Our results show that the sources are separable using the temporal predictability method if and only if they have different temporal structures (i.e., autocorrelations). Consequently, the applicability and limitations of the temporal predictability method are clarified. In addition, instead of using generalized eigendecomposition, we suggest using joint approximate diagonalization algorithms to improve the robustness of the method. A new criterion is presented to evaluate the separation results. Numerical simulations are performed to demonstrate the validity of the theoretical results.

History

Journal

Neural Computation

Volume

21

Pagination

3519 - 3531

Location

Cambridge, MA

Open access

  • Yes

ISSN

0899-7667

Language

eng

Publication classification

C1.1 Refereed article in a scholarly journal

Copyright notice

2009, MIT Press Journals

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC