Filtered fractals in signal modeling

Filtered versions of fractionally differenced Gaussian noise (FDGN) processes are studied. Fractionally differenced Gaussian noise is a discrete-time equivalent of fractional Brownian motion. Filtered versions of such processes are ideally suited for modeling signals with both short-term and long-term correlation structures. Two iterative algorithms for estimating the parameters of filtered FDGN processes are described.<<ETX>>