A Forward backward Correlation-based Projection Approximation for Subspace Tracking 


Vol. 33,  No. 4, pp. 131-135, Apr.  2008


PDF
  Abstract

In this paper, we propose a forward/backward correlation-based subspace estimation technique, which is called forward/backward correlation-based projection approximation subspace tracking (FB-COPAST). The FB-COPAST utilizes the forward and backward correlation matrix in projection approximation approach to develop the subspace tracking algorithm. With the projection approximation, the RLS-based FB-COPAST is presented. The RLS-based FB-COPAST algorithm has the better performance than the recently developed COPAST method. From the simulation results, we can confirm the proposed FB-COPAST outperforms the COPAST as well as the conventional PAST in the estimation accuracy by about 5dB in steady state.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

J. Lim and Y. Pyeon, "A Forward backward Correlation-based Projection Approximation for Subspace Tracking," The Journal of Korean Institute of Communications and Information Sciences, vol. 33, no. 4, pp. 131-135, 2008. DOI: .

[ACM Style]

Jun-Seok Lim and Yong-Kug Pyeon. 2008. A Forward backward Correlation-based Projection Approximation for Subspace Tracking. The Journal of Korean Institute of Communications and Information Sciences, 33, 4, (2008), 131-135. DOI: .

[KICS Style]

Jun-Seok Lim and Yong-Kug Pyeon, "A Forward backward Correlation-based Projection Approximation for Subspace Tracking," The Journal of Korean Institute of Communications and Information Sciences, vol. 33, no. 4, pp. 131-135, 4. 2008.

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880