BP-HMM 源代码

function [B] = obslike (X,T,n,hmm) % function [B] = obslike (X,T,n,hmm) % % Evaluate likelihood of data given observation model %…

function [hmm] = obsinit (X,hmm,options) % function [hmm] = obsinit (X,hmm,options) % % Initialise observation model in HMM % % …

function [hmm]=hmmtrain(X,T,hmm) % function [hmm]=hmmtrain(X,T,hmm) % % Train Hidden Markov Model using Baum Welch/MAP EM algorit…

function [hmm] = obsupdate (X,T,Gamma,Gammasum,hmm,update) % function [hmm] = obsupdate (X,T,Gamma,Gammasum,hmm,update) % % Upda…

The routines use a common data structure 'hmm' with fields: hmm.obsmodel name of observation model 'Gauss' - Gaussian 'Ga…

function [hmm] = hmminit (X,hmm,covtype,gamma) % function [hmm] = hmminit (X,hmm,covtype,gamma) % % Initialise Gaussian observati…

HMMBOX, version 3.2, William Penny, Imperial College, Feb 1999 Matlab toolbox for Hidden Markov Models (Adapted from Machine Lear…

P=rand(2,4); for i=1:4, P(:,i)=P(:,i)./sum(P(:,i)); end; for i=1:4, P2(:,i)=reshape(P(:,i)*P(:,i)',4,1); end; hmm1.P=P2; hmm1.K=4…

% A demonstration of the HMM software using the 'Likelihood' observation % model. There are K=2 time series where EACH TIME SERIES…

% HMMBOX, version 3.2, William Penny, Imperial College, October 1998 % Matlab toolbox for Hidden Markov Models % % (Adapted from M…