| 1. |
- Tsakonas, Efthymios, et al.
(författare)
-
Optimal Particle Filters for Tracking a Time- Varying Harmonic or Chirp Signal
- 2008
-
Ingår i: IEEE Transactions on Signal Processing. - : IEEE. - 1053-587X .- 1941-0476. ; 56:10, s. 4598-4610
-
Tidskriftsartikel (refereegranskat)abstract
- We consider the problem of tracking the time-varying (TV) parameters of a harmonic or chirp signal using particle filtering (PF) tools. Similar to previous PF approaches to TV spectral analysis, we assume that the model parameters (complex amplitude, frequency, and frequency rate in the chirp case) evolve according to a Gaussian AR(1) model; but we concentrate on the important special case of a single TVharmonic or chirp.We show that the optimal importance function that minimizes the variance of the particle weights can be computed in closed form, and develop procedures to draw samples from it. We further employ Rao–Blackwellization to come up with reduced-complexity versions of the optimal filters. The end result is custom PF solutions that are considerably more efficient than generic ones, and can be used in a broad range of important applications that involve a single TV harmonic or chirp signal, e.g., TV Doppler estimation in communications, and radar.
|
|
| 2. |
|
|
| 3. |
- Valyrakis, Alexandros, et al.
(författare)
-
Stochastic Modeling and Particle Filtering Algorithms for Tracking a Frequency-Hopped Signal
- 2009
-
Ingår i: IEEE Transactions on Signal Processing. - : IEEE. - 1053-587X .- 1941-0476. ; 57:8, s. 3108-3118
-
Tidskriftsartikel (refereegranskat)abstract
- The problem of tracking a frequency-hopped signal without knowledge of its hopping pattern is considered. The problem is of interest in military communications, where, in addition to frequency, hop timing can also be randomly shifted to guard against unauthorized reception and jamming. A conceptually simple nonlinear and non-Gaussian stochastic state-space model is proposed to capture the randomness in carrier frequency and hop timing. This model is well-suited for the application of particle filtering tools: it is possible to compute the optimal (weight variance-minimizing) importance function in closed-form. A convenient mixture representation of the latter is employed together with Rao-Blackwellization to derive a very simple optimal sampling procedure. This is representative of the state-of-art in terms of systematic design of particle filters. A heuristic design approach is also developed, using the mode of the spectrogram to localize hop particles. Performance is assessed in a range of experiments using both simulated and measured data. Interestingly, the results indicate that the heuristic design approach can outperform the systematic one, and both are robust to model assumptions.
|
|
