MARHMM /

Filename Size Date modified Message
4.7 KB
11.2 KB
1.7 KB
33.7 KB
40.4 KB
8.4 KB
16.9 KB

%This program runs Autoregressive (ARHMM) and Mixture ARHMM (MARHHM).

%In ARHMM, we have 5 inputs (data,level,a,pi,iteration) and three outputs [trans,emission,LOGP]

%data=Given observation sequence labellebd in numerics %level= Observation takes differnt values which will be denoted by level %a=transition probability matrix %pi=initial probability vector %iteration = number of iterations

%Open the ARHMM in matlab. %In command of Matlab program, please copy and paste the following entries:
data=dlmread('real25.txt'); %data=dlmread('real50.txt'); %data=dlmread('real100.txt'); %data=dlmread('real240.txt');

level= [1 2 3]; a=[0.4,0.4,0.2;0.7,0.2,0.1;0.2,0.5,0.3] pi=[0.3;0.4;0.3] iteration=500;

%Then copy and paste:

[trans,emission,LOGP]=ARHMM(data,level,a,pi,iteration)

%in command.

%Then you are asked to enter the dependent matrix b(:,:,i) which defiens as P(Ot|st,O(t-1)=i). %please copy and paste the following matrix in front of b and then enter:

[0.5,0.2,0.3;0.4,0.1,0.5;0.2,0.7,0.1]

%the same as previous step copy and paste the following matrix and enter

[0.5,0.2,0.3;0.4,0.1,0.5;0.2,0.7,0.1]

%and finally copy and paste the following matrix and enter

[0.3,0.2,0.5;0.7,0.2,0.1;0.1,0.4,0.5]


%In MARHMM we have 7 inputes (data,level,a,pi,iteration,alfa1,alfa2) in which alfa1,alfa2 are initial values of mixture coefficients. %Please define the following equations in command: alfa1=.5; alfa2= .5;

%Then copy and Paste the

[trans,emission,pi,trans2,emission2,pi2,LOGP,ALFA1,ALFA2]=MARHMM(data,level,a,pi,iteration,alfa1,alfa2)

%in the Matlab Command.