Feature extraction for murmur detection based on support vector regression of time-frequency representations

This paper presents a nonlinear approach for time-frequency representations (TFR) data analysis, based on a statistical learning methodology - support vector regression (SVR), that being a nonlinear framework, matches recent findings on the underlying dynamics of cardiac mechanic activity and phonoc...

Full description

Saved in:
Bibliographic Details
Published in:2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2008-01, p.1623-1626
Main Authors: Jaramillo-Garzon, J., Quiceno-Manrique, A., Godino-Llorente, I., Castellanos-Dominguez, C.G.
Format: Article
Language:English
Subjects:
Feature extraction
Kernel
Phonocardiography
Prototypes
Support vector machines
Time-frequency analysis
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 1626
container_issue
container_start_page 1623
container_title 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
container_volume
creator Jaramillo-Garzon, J.
Quiceno-Manrique, A.
Godino-Llorente, I.
Castellanos-Dominguez, C.G.
description This paper presents a nonlinear approach for time-frequency representations (TFR) data analysis, based on a statistical learning methodology - support vector regression (SVR), that being a nonlinear framework, matches recent findings on the underlying dynamics of cardiac mechanic activity and phonocardiographic (PCG) recordings. The proposed methodology aims to model the estimated TFRs, and extract relevant features to perform classification between normal and pathologic PCG recordings (with murmur). Modeling of TFR is done by means of SVR, and the distance between regressions is calculated through dissimilarity measures based on dot product. Finally, a k-nn classifier is used for the classification stage, obtaining a validation performance of 97.85%.
doi_str_mv 10.1109/IEMBS.2008.4649484
format article
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4649484</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4649484</ieee_id><sourcerecordid>4649484</sourcerecordid><originalsourceid>FETCH-LOGICAL-i413t-b6d01adce7e65fc42adac136b09f0ecde9b67c7c00b1976d23cec06458e8d7193</originalsourceid><addsrcrecordid>eNpVkM1OwzAQhM2faFX6AnDJC6R4E_8eoWqhUhEHQOJWOfYGBbVNsB3Uvj2u2gurkWa132gOS8gt0AkA1feL2cvj26SgVE2YYJopdkbGWipgBWOggBfnZAicq5wJ4Bf_GOOXiVHNcqHk54CMQ_imaRgvhaLXZAAaRKGVHJL1HE3sPWa4i97Y2LTbrG59tul9UuYw4vFYmYAuS0vou671MftNIAU9fnkM4RBp6yw2G8xrjz89bu0-wS5B3EZz6Ag35Ko264Djk4_Ix3z2Pn3Ol69Pi-nDMm8YlDGvhKNgnEWJgteWFcYZC6WoqK4pWoe6EtJKS2kFWgpXlBYtFYwrVE6CLkfk7tjbIOKq883G-P3q9MbyD4WYY94</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Feature extraction for murmur detection based on support vector regression of time-frequency representations</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Jaramillo-Garzon, J. ; Quiceno-Manrique, A. ; Godino-Llorente, I. ; Castellanos-Dominguez, C.G.</creator><creatorcontrib>Jaramillo-Garzon, J. ; Quiceno-Manrique, A. ; Godino-Llorente, I. ; Castellanos-Dominguez, C.G.</creatorcontrib><description>This paper presents a nonlinear approach for time-frequency representations (TFR) data analysis, based on a statistical learning methodology - support vector regression (SVR), that being a nonlinear framework, matches recent findings on the underlying dynamics of cardiac mechanic activity and phonocardiographic (PCG) recordings. The proposed methodology aims to model the estimated TFRs, and extract relevant features to perform classification between normal and pathologic PCG recordings (with murmur). Modeling of TFR is done by means of SVR, and the distance between regressions is calculated through dissimilarity measures based on dot product. Finally, a k-nn classifier is used for the classification stage, obtaining a validation performance of 97.85%.</description><identifier>ISSN: 1094-687X</identifier><identifier>ISBN: 9781424418145</identifier><identifier>ISBN: 1424418143</identifier><identifier>EISSN: 1558-4615</identifier><identifier>EISBN: 9781424418152</identifier><identifier>EISBN: 1424418151</identifier><identifier>DOI: 10.1109/IEMBS.2008.4649484</identifier><identifier>PMID: 19162987</identifier><language>eng</language><publisher>IEEE</publisher><subject>Feature extraction ; Kernel ; Phonocardiography ; Prototypes ; Support vector machines ; Time-frequency analysis ; Training</subject><ispartof>2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2008-01, p.1623-1626</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4649484$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4649484$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Jaramillo-Garzon, J.</creatorcontrib><creatorcontrib>Quiceno-Manrique, A.</creatorcontrib><creatorcontrib>Godino-Llorente, I.</creatorcontrib><creatorcontrib>Castellanos-Dominguez, C.G.</creatorcontrib><title>Feature extraction for murmur detection based on support vector regression of time-frequency representations</title><title>2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society</title><addtitle>IEMBS</addtitle><description>This paper presents a nonlinear approach for time-frequency representations (TFR) data analysis, based on a statistical learning methodology - support vector regression (SVR), that being a nonlinear framework, matches recent findings on the underlying dynamics of cardiac mechanic activity and phonocardiographic (PCG) recordings. The proposed methodology aims to model the estimated TFRs, and extract relevant features to perform classification between normal and pathologic PCG recordings (with murmur). Modeling of TFR is done by means of SVR, and the distance between regressions is calculated through dissimilarity measures based on dot product. Finally, a k-nn classifier is used for the classification stage, obtaining a validation performance of 97.85%.</description><subject>Feature extraction</subject><subject>Kernel</subject><subject>Phonocardiography</subject><subject>Prototypes</subject><subject>Support vector machines</subject><subject>Time-frequency analysis</subject><subject>Training</subject><issn>1094-687X</issn><issn>1558-4615</issn><isbn>9781424418145</isbn><isbn>1424418143</isbn><isbn>9781424418152</isbn><isbn>1424418151</isbn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><sourceid>6IE</sourceid><recordid>eNpVkM1OwzAQhM2faFX6AnDJC6R4E_8eoWqhUhEHQOJWOfYGBbVNsB3Uvj2u2gurkWa132gOS8gt0AkA1feL2cvj26SgVE2YYJopdkbGWipgBWOggBfnZAicq5wJ4Bf_GOOXiVHNcqHk54CMQ_imaRgvhaLXZAAaRKGVHJL1HE3sPWa4i97Y2LTbrG59tul9UuYw4vFYmYAuS0vou671MftNIAU9fnkM4RBp6yw2G8xrjz89bu0-wS5B3EZz6Ag35Ko264Djk4_Ix3z2Pn3Ol69Pi-nDMm8YlDGvhKNgnEWJgteWFcYZC6WoqK4pWoe6EtJKS2kFWgpXlBYtFYwrVE6CLkfk7tjbIOKq883G-P3q9MbyD4WYY94</recordid><startdate>20080101</startdate><enddate>20080101</enddate><creator>Jaramillo-Garzon, J.</creator><creator>Quiceno-Manrique, A.</creator><creator>Godino-Llorente, I.</creator><creator>Castellanos-Dominguez, C.G.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20080101</creationdate><title>Feature extraction for murmur detection based on support vector regression of time-frequency representations</title><author>Jaramillo-Garzon, J. ; Quiceno-Manrique, A. ; Godino-Llorente, I. ; Castellanos-Dominguez, C.G.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i413t-b6d01adce7e65fc42adac136b09f0ecde9b67c7c00b1976d23cec06458e8d7193</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Feature extraction</topic><topic>Kernel</topic><topic>Phonocardiography</topic><topic>Prototypes</topic><topic>Support vector machines</topic><topic>Time-frequency analysis</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Jaramillo-Garzon, J.</creatorcontrib><creatorcontrib>Quiceno-Manrique, A.</creatorcontrib><creatorcontrib>Godino-Llorente, I.</creatorcontrib><creatorcontrib>Castellanos-Dominguez, C.G.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection><jtitle>2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Jaramillo-Garzon, J.</au><au>Quiceno-Manrique, A.</au><au>Godino-Llorente, I.</au><au>Castellanos-Dominguez, C.G.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Feature extraction for murmur detection based on support vector regression of time-frequency representations</atitle><jtitle>2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society</jtitle><stitle>IEMBS</stitle><date>2008-01-01</date><risdate>2008</risdate><spage>1623</spage><epage>1626</epage><pages>1623-1626</pages><issn>1094-687X</issn><eissn>1558-4615</eissn><isbn>9781424418145</isbn><isbn>1424418143</isbn><eisbn>9781424418152</eisbn><eisbn>1424418151</eisbn><abstract>This paper presents a nonlinear approach for time-frequency representations (TFR) data analysis, based on a statistical learning methodology - support vector regression (SVR), that being a nonlinear framework, matches recent findings on the underlying dynamics of cardiac mechanic activity and phonocardiographic (PCG) recordings. The proposed methodology aims to model the estimated TFRs, and extract relevant features to perform classification between normal and pathologic PCG recordings (with murmur). Modeling of TFR is done by means of SVR, and the distance between regressions is calculated through dissimilarity measures based on dot product. Finally, a k-nn classifier is used for the classification stage, obtaining a validation performance of 97.85%.</abstract><pub>IEEE</pub><pmid>19162987</pmid><doi>10.1109/IEMBS.2008.4649484</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1094-687X
ispartof 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2008-01, p.1623-1626
issn 1094-687X
1558-4615
language eng
recordid cdi_ieee_primary_4649484
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Feature extraction
Kernel
Phonocardiography
Prototypes
Support vector machines
Time-frequency analysis
Training
title Feature extraction for murmur detection based on support vector regression of time-frequency representations
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-01T12%3A42%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Feature%20extraction%20for%20murmur%20detection%20based%20on%20support%20vector%20regression%20of%20time-frequency%20representations&rft.jtitle=2008%2030th%20Annual%20International%20Conference%20of%20the%20IEEE%20Engineering%20in%20Medicine%20and%20Biology%20Society&rft.au=Jaramillo-Garzon,%20J.&rft.date=2008-01-01&rft.spage=1623&rft.epage=1626&rft.pages=1623-1626&rft.issn=1094-687X&rft.eissn=1558-4615&rft.isbn=9781424418145&rft.isbn_list=1424418143&rft_id=info:doi/10.1109/IEMBS.2008.4649484&rft.eisbn=9781424418152&rft.eisbn_list=1424418151&rft_dat=%3Cieee_6IE%3E4649484%3C/ieee_6IE%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i413t-b6d01adce7e65fc42adac136b09f0ecde9b67c7c00b1976d23cec06458e8d7193%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/19162987&rft_ieee_id=4649484&rfr_iscdi=true