Mercurial > hg > camir-aes2014
comparison toolboxes/FullBNT-1.0.7/bnt/inference/dynamic/@stable_ho_inf_engine/test_ho_inf_enginge.m @ 0:e9a9cd732c1e tip
first hg version after svn
author | wolffd |
---|---|
date | Tue, 10 Feb 2015 15:05:51 +0000 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:e9a9cd732c1e |
---|---|
1 function [engine,engine2] = test_ho_inf_enginge(order,T) | |
2 | |
3 assert(order >= 1) | |
4 % Model a SISO system, i. e. all node are one-dimensional | |
5 % The nodes are numbered as follows | |
6 % u(t) = 1 input | |
7 % y(t) = 2 model output | |
8 % z(t) = 3 noise | |
9 % q(t) = 4 observed output = noise + model output | |
10 | |
11 ns = [1 1 1 1]; | |
12 | |
13 % Model a linear system, i.e. there are no discrete nodes | |
14 dn = []; | |
15 | |
16 % Modeling of connections within a time slice | |
17 intra = zeros(4); | |
18 intra(2,4) = 1; % Connection y(t) -> q(t) | |
19 intra(3,4) = 1; % Connection z(t) -> q(t) | |
20 | |
21 % Connections to the next time slice | |
22 inter = zeros(4,4,order); | |
23 inter(1,2,1) = 1; % u(t) -> y(t+1); | |
24 inter(2,2,1) = 1; %y(t) -> y(t+1); | |
25 inter(3,3,1) = 1; %z(t) -> z(t+1); | |
26 | |
27 if order >= 2 | |
28 inter(1,2,2) = 1; % u(t) -> y(t+2); | |
29 inter(2,2,2) = 1; % y(t) -> y(t+2); | |
30 end | |
31 | |
32 for i = 3: order | |
33 inter(:,:,i) = inter(:,:,i-1); %u(t) -> y(t+i) y(t) -> y(t) +i | |
34 end; | |
35 | |
36 | |
37 % Compution of a higer order Markov Model | |
38 bnet = mk_higher_order_dbn(intra,inter,ns,'discrete',dn); | |
39 bnet2 = mk_dbn(intra,inter(:,:,1),ns,'discrete',dn) | |
40 | |
41 | |
42 %Calculation of the number of nodes with different parameters | |
43 %There is one input and one output nodes 2 | |
44 %There are two different disturbance node 2 | |
45 %There are order +1 nodes for y 1 + order | |
46 numOfNodes = 5 + order; | |
47 | |
48 % First input node | |
49 bnet.CPD{1} = gaussian_CPD(bnet,1,'mean',0); | |
50 bnet2.CPD{1} = gaussian_CPD(bnet,1,'mean',0); | |
51 % Modeled output | |
52 bnet.CPD{2} = gaussian_CPD(bnet,2,'mean',0); | |
53 bnet2.CPD{2} = gaussian_CPD(bnet,2,'mean',0); | |
54 %Disturbance | |
55 bnet.CPD{3} = gaussian_CPD(bnet,3,'mean',0); | |
56 bnet2.CPD{3} = gaussian_CPD(bnet,3,'mean',0); | |
57 | |
58 %Qutput | |
59 bnet.CPD{4} = gaussian_CPD(bnet,4,'mean',0); | |
60 bnet2.CPD{4} = gaussian_CPD(bnet,4,'mean',0); | |
61 | |
62 | |
63 %Output node in the second time-slice | |
64 %Remember that node number 6 is an example for | |
65 %the fifth equivalence class | |
66 bnet.CPD{5} = gaussian_CPD(bnet,6,'mean',0); | |
67 bnet2.CPD{5} = gaussian_CPD(bnet,6,'mean',0); | |
68 | |
69 %Disturbance node in the second time slice | |
70 bnet.CPD{6} = gaussian_CPD(bnet,7,'mean',0); | |
71 bnet2.CPD{6} = gaussian_CPD(bnet,7,'mean',0); | |
72 | |
73 % Modeling of the remaining nodes for y | |
74 for i = 7:numOfNodes | |
75 bnet.CPD{i} = gaussian_CPD(bnet,(i - 6)*4 + 7,'mean',0); | |
76 end | |
77 | |
78 % Generation of the inference engine | |
79 engine = dv_unrolled_dbn_inf_engine(bnet,T); | |
80 engine2 = jtree_unrolled_dbn_inf_engine(bnet,T); | |
81 | |
82 | |
83 | |
84 | |
85 | |
86 | |
87 |