A sliding-exponential window RLS adaptive filtering algorithm: Properties and applications. (English) Zbl 0925.93920

Summary: This paper presents a sliding-exponential window recursive least-squares (SEWRLS) adaptive filtering algorithm, which has the same fast tracking property as the sliding rectangular window RLS (SRWRLS) algorithm, but its tracking accuracy is much higher than that of SRWRLS. The initial convergence and steady-state misadjustment performances of SEWRLS, SRWRLS and exponential window RLS algorithms are analyzed. Simulation results of these algorithms are presented and compared with theoretical ones which show that the simulation results are consistent with the theoretical results. It is also illustrated that SEWRLS algorithm exhibits better numerical stability in a floating point arithmetic than a conventional SRWRLS algorithm. Applications of SEWRLS to system identification and to decision feedback equalization on digital mobile radio channels are also investigated.


93E11 Filtering in stochastic control theory
93E24 Least squares and related methods for stochastic control systems
Full Text: DOI