Abstract
A moving-average filter is used to generate input signals for system identification. This has enabled the development of an efficient numeric algorithm and also some sufficiency results for a stationary point of the filter parameters. These sufficiency results give simple design equations for the design of identification experiments with an output-power constraint. A theoretical result for autoregressive systems is also given and used to interpret the numeric examples.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have