Characterisation of Arteriovenous Fistula’s sound recordings using principal component analysis
(2009) Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2009 p.5661-5664- Abstract
- In this study, a signal analysis framework based
on the Karhunen-Loève expansion and k-means clustering
algorithm is proposed for the characterisation of arteriovenous
(AV) fistula’s sound recordings. The Karhunen-Loève (KL) coefficients
corresponding to the directions of maximum variance
were used as classification features, which were clustered applying
k-means algorithm. The results showed that one natural
cluster was found for similar AV fistula’s state recordings. On
the other hand, when stenotic and non-stenotic AV fistula’s
recordings were processed together, the two most significant
KL coefficients contain important information that can be... (More) - In this study, a signal analysis framework based
on the Karhunen-Loève expansion and k-means clustering
algorithm is proposed for the characterisation of arteriovenous
(AV) fistula’s sound recordings. The Karhunen-Loève (KL) coefficients
corresponding to the directions of maximum variance
were used as classification features, which were clustered applying
k-means algorithm. The results showed that one natural
cluster was found for similar AV fistula’s state recordings. On
the other hand, when stenotic and non-stenotic AV fistula’s
recordings were processed together, the two most significant
KL coefficients contain important information that can be used
for classification or discrimination between these AV fistula’s
states. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/1668963
- author
- Munguia Mena, Marco LU ; Vasquez Obando, Pablo LU and Mandersson, Bengt LU
- organization
- publishing date
- 2009
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- Principal Component Analysis, Signal Classification, Arteriovenous Fistula
- host publication
- [Host publication title missing]
- pages
- 4 pages
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2009
- conference location
- Minneapolis, Minnesota, United States
- conference dates
- 2009-09-03 - 2009-09-06
- external identifiers
-
- pmid:19964410
- scopus:84903867180
- ISSN
- 1557-170X
- DOI
- 10.1109/IEMBS.2009.5333770
- language
- English
- LU publication?
- yes
- id
- 66517f17-733a-476f-bae2-f2e5c6c099c7 (old id 1668963)
- date added to LUP
- 2016-04-01 15:02:36
- date last changed
- 2022-01-28 03:48:39
@inproceedings{66517f17-733a-476f-bae2-f2e5c6c099c7,
abstract = {{In this study, a signal analysis framework based<br/><br>
on the Karhunen-Loève expansion and k-means clustering<br/><br>
algorithm is proposed for the characterisation of arteriovenous<br/><br>
(AV) fistula’s sound recordings. The Karhunen-Loève (KL) coefficients<br/><br>
corresponding to the directions of maximum variance<br/><br>
were used as classification features, which were clustered applying<br/><br>
k-means algorithm. The results showed that one natural<br/><br>
cluster was found for similar AV fistula’s state recordings. On<br/><br>
the other hand, when stenotic and non-stenotic AV fistula’s<br/><br>
recordings were processed together, the two most significant<br/><br>
KL coefficients contain important information that can be used<br/><br>
for classification or discrimination between these AV fistula’s<br/><br>
states.}},
author = {{Munguia Mena, Marco and Vasquez Obando, Pablo and Mandersson, Bengt}},
booktitle = {{[Host publication title missing]}},
issn = {{1557-170X}},
keywords = {{Principal Component Analysis; Signal Classification; Arteriovenous Fistula}},
language = {{eng}},
pages = {{5661--5664}},
publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
title = {{Characterisation of Arteriovenous Fistula’s sound recordings using principal component analysis}},
url = {{http://dx.doi.org/10.1109/IEMBS.2009.5333770}},
doi = {{10.1109/IEMBS.2009.5333770}},
year = {{2009}},
}