Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Heart Sound Segmentation using Switching Linear Dynamical Models

Abstract: 

Localization of exact positions of the fundamental heart sounds (FHS) is an essential step towards automatic analysis of heart sound phonocardiogram (PCG) recordings, the automatic segmentation allows for data-driven classification of heart pathological events. Current approach using probabilistic models such as hidden Markov models (HMMs) has improved accuracy of heart sound segmentation. In this paper, we propose a switching linear dynamic system (SLDS) of piece-wise stationary auto-regressive (AR) processes for segmenting the heart sounds into four fundamental components with distinct second order structure (auto-correlation). The SLDS is able to capture simultaneously both the continuous state-space in the hidden dynamics in PCG, and the regime switching in the dynamics using a discrete Markov chain. This overcomes limitation of HMMs which is based on a
single-layer of discrete states. Compared to AR processes, the Gaussian mixture densities in HMM do not account for the temporal auto-correlation structure in PCG which has one-to-one correspondence to frequency content a distinctive feature of HS components. We introduce three schemes for model estimation: (1) switching Kalman filter (SKF) model. (2) refinement by switching Kalman filter (SKS), and (3) fusion of SKF and the duration-dependent Viterbi algorithm (SKF-Viterbi). Results on a large PCG dataset of Physionet/Challenge 2016 shows SKF-Viterbi significantly outperforms SKF by improvement of segmentation accuracy from 71% to 84.2%.

up
0 users have voted:

Paper Details

Authors:
Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, Hadri Hu
Submitted On:
10 November 2017 - 10:14am
Short Link:
Type:
Poster
Event:
Paper Code:
HCE-P.1.13 (1413)
Document Year:
2017
Cite

Document Files

poster_1413.pdf

(83 downloads)

Subscribe

[1] Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, Hadri Hu, "Heart Sound Segmentation using Switching Linear Dynamical Models", IEEE SigPort, 2017. [Online]. Available: http://sigport.org/2293. Accessed: May. 25, 2018.
@article{2293-17,
url = {http://sigport.org/2293},
author = {Fuad Noman; Sh-Hussain Salleh; Chee-Ming Ting; Hadri Hu },
publisher = {IEEE SigPort},
title = {Heart Sound Segmentation using Switching Linear Dynamical Models},
year = {2017} }
TY - EJOUR
T1 - Heart Sound Segmentation using Switching Linear Dynamical Models
AU - Fuad Noman; Sh-Hussain Salleh; Chee-Ming Ting; Hadri Hu
PY - 2017
PB - IEEE SigPort
UR - http://sigport.org/2293
ER -
Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, Hadri Hu. (2017). Heart Sound Segmentation using Switching Linear Dynamical Models. IEEE SigPort. http://sigport.org/2293
Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, Hadri Hu, 2017. Heart Sound Segmentation using Switching Linear Dynamical Models. Available at: http://sigport.org/2293.
Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, Hadri Hu. (2017). "Heart Sound Segmentation using Switching Linear Dynamical Models." Web.
1. Fuad Noman, Sh-Hussain Salleh, Chee-Ming Ting, Hadri Hu. Heart Sound Segmentation using Switching Linear Dynamical Models [Internet]. IEEE SigPort; 2017. Available from : http://sigport.org/2293