Fast algorithms for optimal FIR filter and smoother of discrete-time state-space models
Automatica (Journal of IFAC)
Digital Signal Processing
Temporally correlated source separation based on variational Kalman smoother
Digital Signal Processing
A new FIR filter for state estimation and its application
Journal of Computer Science and Technology
Optimal horizons for a one-parameter family of unbiased FIR filters
Digital Signal Processing
Short-time Fourier analysis via optimal harmonic FIR filters
IEEE Transactions on Signal Processing
Brief A receding horizon unbiased FIR filter for discrete-time state space models
Automatica (Journal of IFAC)
Fixed-memory recursive filters (Corresp.)
IEEE Transactions on Information Theory
A Kalman-like algorithm with no requirements for noise and initial conditions
NEHIPISIC'11 Proceeding of 10th WSEAS international conference on electronics, hardware, wireless and optical communications, and 10th WSEAS international conference on signal processing, robotics and automation, and 3rd WSEAS international conference on nanotechnology, and 2nd WSEAS international conference on Plasma-fusion-nuclear physics
FIR filtering of state-space models in non-Gaussian environment with uncertainties
TELE-INFO'11/MINO'11/SIP'11 Proceedings of the 10th WSEAS international conference on Telecommunications and informatics and microelectronics, nanoelectronics, optoelectronics, and WSEAS international conference on Signal processing
Hi-index | 0.00 |
To overcome the resulting problems of existing finite impulse response (FIR) structure filters, this paper proposes an alternative FIR filter for state estimation in discrete-time systems, which is derived from the well-known Kalman filter with recursive infinite impulse response (IIR) structure. The proposed FIR filter obtains a posteriori knowledge about the window initial condition from the most recent finite observations, while existing FIR filters handle this task arbitrarily or heuristically. The gain matrix for the proposed FIR filter incorporates a posteriori knowledge about the window initial condition during its design and is shown to be time-invariant. The proposed FIR filter is shown to have good inherent properties such as unbiasedness and deadbeat. Through extensive computer simulations, the proposed FIR filter can be shown to be comparable with the Kalman filter for the nominal system and better than that for the temporarily uncertain system.