Table 5 Simulation results for Example 1: Mean and standard deviations of the RMSE for three different estimators of xn,2, namely, O2, the posterior mean based on SIR and the posterior mean based on TS
From: A weighted likelihood criteria for learning importance densities in particle filtering
Exp. no. | (Q,R) | R/Q | RMSE for xn,2 | |||||
|---|---|---|---|---|---|---|---|---|
| Â | Â | Â | O 2 | SIR | TS | |||
| Â | Â | Â | Mean | SD | Mean | SD | Mean | SD |
1 | (0.1,0.1) | 1.0 | 0.0986 | 0.0088 | 0.0646 | 0.0315 | 0.0395 | 0.0089 |
2 | (0.2,0.1) | 0.5 | 0.0947 | 0.0129 | 0.1242 | 0.0607 | 0.0516 | 0.0086 |
3 | (0.4,0.1) | 0.25 | 0.1069 | 0.0168 | 0.1781 | 0.0750 | 0.0689 | 0.0107 |
4 | (0.8,0.1) | 0.125 | 0.1009 | 0.0138 | 0.4562 | 0.3604 | 0.0819 | 0.0182 |
5 | (1.0,0.1) | 0.100 | 0.1030 | 0.0114 | 0.5090 | 0.3914 | 0.1136 | 0.0500 |
6 | (0.1,1.0) | 10.0 | 0.9943 | 0.0934 | 0.2452 | 0.1371 | 0.1920 | 0.0753 |
7 | (0.4,1.0) | 2.5 | 0.9926 | 0.1125 | 0.4424 | 0.1824 | 0.2905 | 0.0888 |