A spectral estimation algorithm using the householder transform
- 14 Downloads
Householder transform is used to triangularize the data matrix, which is based on the near prediction error equation. It is proved that the sum of squared residuals for each AR order can be obtained by the main diagonal elements of upper triangular matrix, so the column by column procedure can be used to develop a recursive algorithm for AR modeling and spectral estimation. In most cases, the present algorithm yields the same results as the covariance method or modified covariance method does. But in some special cases where the numerical illconditioned problems are so serious that the covariance, method and modified covariance method fail to estimate AR spectrum, the presented algorithm still tends to keep good performance. The typical computational results are presented finally.
Key wordsAR spectral estimation Householder transform AR parameter Recursive algorithm
Unable to display preview. Download preview PDF.
- S. L. Marple, Digital Spectral Analysis with Applications, Prentice-Hall Inc., NJ 1987.Google Scholar
- J. Makhoul,Proc. IEEE,63(1975)4, 561–580.Google Scholar
- Morf. et al.,IEEE Trans. on ASSP,ASSP-25(1977)10, 429–433.Google Scholar
- S. L. Marple,IEEE Trans. on ASSP,ASSP-29(1981)2, 62–73.Google Scholar
- J. A. Cadzow, et al.,Proc. Inst. Elec. Eng., Part F,130(1983)4, 202–210.Google Scholar
- Huang Junqin, Huili Yu, A Recursive Householder Algorithm for Identification and ME/AR Spectral Estimation, Seventh IFAC/IFORS Symposium on Iden. and System Parameter Esti., Vol.2, pp. 1461–1466, July 1985.Google Scholar
- S. H. Leung, W. Y. Horng, Superresolution Autoregressive Spectral Estimation Technique Using Multiple Step Prediction, Proc. IEEE Int. Conf. ASSP, Vol. 1, pp. 101–104, Mar. 1985.Google Scholar