COMPUTATIONAL ASPECTS FOR RECURSIVE FRISCH SCHEME SYSTEM IDENTIFICATION

The implementation of a recursive algorithm for the estimation of parameters of a linear single-input single-output errors-in-variables system is re-considered. The objective is to reduce the computational complexity in order to reduce the computation time per recursion, which, in turn, will allow a wider applicability of the recursive algorithm. The technique of stationary iterative methods for least squares is utilised, in order to reduce the complexity from cubic to quadratic order with respect to the model parameters to be estimated. A numerical simulation underpins the theoretically obtained results.