Skip to content

Latest commit

 

History

History
12 lines (9 loc) · 903 Bytes

File metadata and controls

12 lines (9 loc) · 903 Bytes

Particle-Filter-Dynamic-Bayesian-network

Scalar random process is given with the model:

Model

where wt and vt are white Gaussian noises with variances 10 and 1.

Process is simulalted for 50 time steps, and for inital state X0 = 0.1 the aposterior distribution p(xt|e1:t) is evaluated using the Particle Filter. Optimal number of particles is found by calculating MSE.

RESULTS

results MSE histogram