신호 특성을 고려한 가변 상태 개수 HMM을 이용한 심음분류 방법에 대한 고찰
Heart Sound Classification Using Variable Number of States in Hidden Markov Model Considering Characteristics of the Signal
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
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.
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.
참고문헌 (14)
- Leung T, "Acoustic diagnosis of heart diseases", Proceedings of the 3rd international conference on acoustical and vibratory surveillance methods and diagnostic techniques (1998)
- Cathers I, "Neural Network Assisted Cardiac Asculation", Artificial Intelligence in Medicine, 7, pp.53~66 (1995)
- Bhatikar S, "Classifier Based on Artificial Neural Network Approach for Cardiac Auscultation in Pediatrics", Artificial Intelligence in Medicine, 33, pp.251~260 (2005)
- Lippmann R, "An Introduction to Computing with Neural Nets", IEEE ASSP Magazine, 4, pp.4~22 (1987)
- DeGroff C, "Artificial neural network-based method of screening heart murmur in children", Circulation, 103, pp.2711~2716 (2001)
- Gill D, "A Probabilistic Model for Phonocardiograms Segmentation Based on Homomorphic Filtering", 18-th Biennial International EURASIP Conference Biosignal (2006)
- Ricke A, "Automatic segmentation of heart sound signals using hidden Markov models", Computers in Cardiology, 9, pp.953~956 (2005)
- A Classification Approach for the Heart Sound Signals Using Hidden Markov Models, "Chung Y", SSPR, 2006
- Rabiner L, "A segmental k-means training procedure for estimating parameters of hidden Markov models", IEEE Trans. Signal Process ASSP, 38(9), pp.1639~1641 (1990)
- Rabiner L, "A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition", Proceedings of the IEEE, 77(2), pp.257~287 (1989)
- Mason D, "Listening to the Heart. 2nd ed", pp.1~137 (2000), F. A. Davis Company
- Baum L, "A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains", Annals of Mathematical Statistics, 41, pp.164~17 (1970)
- Lee K, "Automatic Speech Recognition", pp.1~207 (1989), Kluwer Academic Publishers
- Kumar, S, "Classification and Detection of Computer Intrusions", PhD, Department of Computer Sciences, pp.1995