THE RELATIONSHIP BETWEEN AR-MODELING BISPECTRAL ESTIMATION AND THE THEORY OF LINEAR PREDICTION

被引:7
作者
GALLEGO, A
CARRION, MC
RUIZ, DP
MEDOURI, A
机构
[1] Department of Applied Physics, Faculty of Sciences, University of Granada
关键词
BISPECTRUM; AUTOREGRESSIVE MODELING; LINEAR PREDICTION;
D O I
10.1016/0165-1684(94)90006-X
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
In this paper, a relationship between bispectrum estimation by means of autoregressive modelling and the theory of linear prediction is presented. It is demonstrated that the 'third-order recursion' equations for a causal and an anticausal model can be derived via minimization of a set of forward- and backward-prediction squared errors, respectively.
引用
收藏
页码:381 / 388
页数:8
相关论文
共 12 条
[11]  
Raghuveer, Nikias, Bispectrum estimation: A parametric approach, IEEE Trans. Acoust. Speech Signal Process, 33 ASSP, 5, pp. 1213-1230, (1985)
[12]  
Raghuveer, Nikias, Bispectrum estimation via AR modeling, Signal Processing, 10, 1, pp. 35-48, (1986)