A stochastic realization approach to reduced-order hierarchical estimation
Uday B. Desai, Sayfollah Kiaei · 1985
A hierarchical estimation algorithm is developed using the stochastic realization approach. The key feature of the algorithm is that the local processors compute oblique projections as opposed to orthogonal projections. Then using the interaction between appropriately defined past and future residuals the new reduced-order hierarchical estimation algorithm is obtained.