A new time domain convolutive BSS of heart and lung sounds

Makkiabadi, B, Jarchi, D, Sanei, S, Makkiabadi, B and Jarchi, D (2012) A new time domain convolutive BSS of heart and lung sounds In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2012), 2012-03-25 - 2012-03-30, Kyoto, Japan.

	Text 3.pdf Restricted to Repository staff only Available under License : See the attached licence file. Download (494kB)
	Text (licence) SRI_deposit_agreement.pdf Restricted to Repository staff only Download (33kB)

Abstract

In this paper the objective is to separate nonstationary heart and lung sounds from their convolutive mixtures in time domain. In order to separate the sources an orthogonal source model and a gradient based optimization have been used to best model the mixing system and best estimate the parameters respectively. Having diagonal or quasi diagonal covariance matrices for different source segments and also having independent profiles/envelops for different sources (which implies nonstationarity of the sources) are the requirements for our convolutive method. We applied the method to synthetically mixed real heart and lung sound signals. Compared to the other methods, the results show the high capability of the method for separating nonstationary heart and lung sound signals. © 2012 IEEE.

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Divisions :	Surrey research (other units)
Authors :	Makkiabadi, B, Jarchi, D, Sanei, S, Makkiabadi, B and Jarchi, D
Date :	2012
DOI :	10.1109/ICASSP.2012.6287956
Contributors :	Contribution Name Email ORCID http://www.loc.gov/loc.terms/relators/PBL IEEE,
Depositing User :	Symplectic Elements
Date Deposited :	28 Mar 2017 14:13
Last Modified :	23 Jan 2020 12:55
URI:	http://epubs.surrey.ac.uk/id/eprint/742473

Actions (login required)

View Item

Downloads