Mercurial > hg > camir-aes2014
annotate toolboxes/FullBNT-1.0.7/HMM/mc_sample.m @ 0:e9a9cd732c1e tip
first hg version after svn
| author | wolffd |
|---|---|
| date | Tue, 10 Feb 2015 15:05:51 +0000 |
| parents | |
| children |
| rev | line source |
|---|---|
| wolffd@0 | 1 function S = mc_sample(prior, trans, len, numex) |
| wolffd@0 | 2 % SAMPLE_MC Generate random sequences from a Markov chain. |
| wolffd@0 | 3 % STATE = SAMPLE_MC(PRIOR, TRANS, LEN) generates a sequence of length LEN. |
| wolffd@0 | 4 % |
| wolffd@0 | 5 % STATE = SAMPLE_MC(PRIOR, TRANS, LEN, N) generates N rows each of length LEN. |
| wolffd@0 | 6 |
| wolffd@0 | 7 if nargin==3 |
| wolffd@0 | 8 numex = 1; |
| wolffd@0 | 9 end |
| wolffd@0 | 10 |
| wolffd@0 | 11 S = zeros(numex,len); |
| wolffd@0 | 12 for i=1:numex |
| wolffd@0 | 13 S(i, 1) = sample_discrete(prior); |
| wolffd@0 | 14 for t=2:len |
| wolffd@0 | 15 S(i, t) = sample_discrete(trans(S(i,t-1),:)); |
| wolffd@0 | 16 end |
| wolffd@0 | 17 end |