Heart sound segmentation by hidden Markov models
Heart sound segmentation by hidden Markov models
The segmentation of phonocardiogram (PCG) signals is the first step in the automatic diagnosis based on heart sounds. The majority of attempts to segment PCG signals depend on a reference provided by simultaneous electrocardiogram recordings. The algorithm proposed in this paper is based on the analysis of the PCG signal only and does not require an ECG reference signal. In this paper we propose the tracking of the log spectral components that vary slowly with frequency (the low-time components). That is Cepstral analysis is used to provide the features selected to represent the heart sounds. The algorithm utilises a hidden Markov Model to identify the S1 and S2 components of the heart sound, which delimit the systolic and diastolic cycles. The parameters of a simple hidden Markov model with single Gaussian distribution for continuous observations are learned from a training set of heart sounds. Once the parameters of the model are obtained PCG signals from different sets are used to test the segmentation procedure.
19
Romero-Vivas, E.
45f6c974-0cdd-4f69-a6af-b887a68af16c
White, P.R.
2dd2477b-5aa9-42e2-9d19-0806d994eaba
2002
Romero-Vivas, E.
45f6c974-0cdd-4f69-a6af-b887a68af16c
White, P.R.
2dd2477b-5aa9-42e2-9d19-0806d994eaba
Romero-Vivas, E. and White, P.R.
(2002)
Heart sound segmentation by hidden Markov models.
IEE Seminar Digest: Medical Applications of Signal Processing, 110, .
(doi:10.1049/ic:20020297).
Abstract
The segmentation of phonocardiogram (PCG) signals is the first step in the automatic diagnosis based on heart sounds. The majority of attempts to segment PCG signals depend on a reference provided by simultaneous electrocardiogram recordings. The algorithm proposed in this paper is based on the analysis of the PCG signal only and does not require an ECG reference signal. In this paper we propose the tracking of the log spectral components that vary slowly with frequency (the low-time components). That is Cepstral analysis is used to provide the features selected to represent the heart sounds. The algorithm utilises a hidden Markov Model to identify the S1 and S2 components of the heart sound, which delimit the systolic and diastolic cycles. The parameters of a simple hidden Markov model with single Gaussian distribution for continuous observations are learned from a training set of heart sounds. Once the parameters of the model are obtained PCG signals from different sets are used to test the segmentation procedure.
This record has no associated files available for download.
More information
Published date: 2002
Additional Information:
London, UK, 7 October 2000
Identifiers
Local EPrints ID: 10923
URI: http://eprints.soton.ac.uk/id/eprint/10923
PURE UUID: ca413691-efa4-426d-990c-b7e6031086f2
Catalogue record
Date deposited: 09 Feb 2006
Last modified: 11 Jul 2024 01:33
Export record
Altmetrics
Contributors
Author:
E. Romero-Vivas
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
