Approximative inversion of positive matrices with applications to modelling
Proceedings of NATO Advanced Research Workshop on Modelling, robustness and sensitivity reduction in control systems
Multidimensional Systems and Signal Processing
Multidimensional Systems and Signal Processing
Multidimensional Systems and Signal Processing
Multidimensional Systems and Signal Processing
Adaptive bearings vibration modelling for diagnosis
ICAIS'11 Proceedings of the Second international conference on Adaptive and intelligent systems
Dynamic structure of volterra-wiener filter for reference signal cancellation in passive radar
KES'12 Proceedings of the 16th international conference on Knowledge Engineering, Machine Learning and Lattice Computing with Applications
| Hi-index | 0.00 |
The subject of this three-part paper is the multidimensional nonlinear Schur parametrization problem for higher-order (and non-Gaussian) stochastic signals. In the first part of this paper we state the nonlinear orthogonal parametrization problem as a generalization of the linear prediction/innovations filter problem. A unified geometric approach to the problem is introduced in the following three isometrically isomorphic spaces: of random variables (of higher-order stochastic sequences), of multi-indexed matrices, and of multidimensional z-polynomials. The nonlinear orthogonal approximate filters of the Volterra–Wiener class are considered. In the second part [30] of this paper we derive a generalized multidimensional nonlinear Schur parametrization algorithm for higher-order nonstationary stochastic sequences. The third part [33] of the paper is devoted to the complexity reduction problem in the nonlinear case, where a low-complexity Schur parametrization procedure, following from a nonlinear generalization of the staircase matrix extension problem [13], is proposed.