Open AccessHidden Markov Model
Author(s) -
Kezia Tumilaar,
Yohanes Langi,
Altien J. Rindengan
Publication year - 2015
Publication title -
d'cartesian: jurnal matematika dan aplikasi/d ' cartesian
Language(s) - English
Resource type - Journals
eISSN - 2685-1083
pISSN - 2302-4224
DOI - 10.35799/dc.4.1.2015.8104
Subject(s) - hidden markov model , forward algorithm , viterbi algorithm , hidden semi markov model , markov model , variable order markov model , markov chain , maximum entropy markov model , markov property , computer science , sequence labeling , sequence (biology) , markov process , decoding methods , algorithm , artificial intelligence , mathematics , machine learning , statistics , task (project management) , management , biology , economics , genetics
Hidden Markov Models (HMM) is a stochastic model and is essentially an extension of Markov Chain. In Hidden Markov Model (HMM) there are two types states: the observable states and the hidden states. The purpose of this research are to understand how hidden Markov model (HMM) and to understand how the solution of three basic problems on Hidden Markov Model (HMM) which consist of evaluation problem, decoding problem and learning problem. The result of the research is hidden Markov model can be defined as . The evaluation problem or to compute probability of the observation sequence given the model P(O|) can solved by Forward-Backward algorithm, the decoding problem or to choose hidden state sequence which is optimal can solved by Viterbi algorithm and learning problem or to estimate hidden Markov model parameter to maximize P(O|) can solved by Baum – Welch algorithm. From description above Hidden Markov Model with state 3 can describe behavior from the case studies. Key words: Decoding Problem, Evaluation Problem, Hidden Markov Model, Learning Problem