J Korean Soc Med Inform.  2008 Jun;14(2):179-187.

Heart Sound Classification Using Variable Number of States in Hidden Markov Model Considering Characteristics of the Signal

• Chung YJ

Abstract

Hidden Markov model (HMM) is known to be one of the most powerful methods in the acoustic modeling of heart sound signals. Conventionally, we usually use a fixed number of states for each HMM. However, due to the various types of the heart sound signals, it seems that more accurate acoustic modeling is possible by varying the number of states in the HMM depending on the signal types to be modeled. In this paper, we propose to assign different number of states to the HMM for better acoustic modeling and consequently, improving the classification performance of the heart sound signals. Compared with when fixing the number of states, the proposed approach has shown some performance improvement in the classification experiments on various types of heart sound signals.

Keyword

Classification; Hidden Markov Model; Heart Sounds Signals

MeSH Terms

Acoustics
Heart
Heart Sounds