ECG Identification System Using Neural Network with Global and Local Features

ECG Identification System Using Neural Network with Global and Local Features

This paper proposes a human identification system via extracted electrocardiogram (ECG) signals. Two hierarchical classification structures based on global shape feature and local statistical feature is used to extract ECG signals. Global shape feature represents the outline information of ECG signa...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International Association for Development of the Information Society 2016
Hauptverfasser: Tseng, Kuo-Kun, Lee, Dachao, Chen, Charles
Format: Report
Sprache:eng
Schlagworte:
Artificial Intelligence
Classification
Identification
Medicine
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title International Association for Development of the Information Society
container_volume
creator Tseng, Kuo-Kun
Lee, Dachao
Chen, Charles
description This paper proposes a human identification system via extracted electrocardiogram (ECG) signals. Two hierarchical classification structures based on global shape feature and local statistical feature is used to extract ECG signals. Global shape feature represents the outline information of ECG signals and local statistical feature extracts the information between signals in time domain. Genetic algorithm based back propagation neural network is used as the specific classifier. Experiment results show that our identification system can achieves an average 97.6% accuracy on a 38 subjects of PTB public ECG database and an average 100% accuracy on an 18 subjects of MIT-BIH public ECG database, which demonstrates the proposed system can reach satisfactory effects. [For full proceedings, see ED571459.]
format Report
fullrecord <record><control><sourceid>eric_GA5</sourceid><recordid>TN_cdi_eric_primary_ED571582</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ericid>ED571582</ericid><sourcerecordid>ED571582</sourcerecordid><originalsourceid>FETCH-eric_primary_ED5715823</originalsourceid><addsrcrecordid>eNrjZPB1dXZX8ExJzSvJTMtMTizJzM9TCK4sLknNVQgtzsxLV_BLLS1KzAFSJeX5RdkK5ZklGQruOflJQLHEvBQFn_xkIMstNbGktCi1mIeBNS0xpziVF0pzM8i4uYY4e-imFmUmxxcUZeYmFlXGu7qYmhuaWhgZE5AGAFMcMsU</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>report</recordtype></control><display><type>report</type><title>ECG Identification System Using Neural Network with Global and Local Features</title><source>ERIC - Full Text Only (Discovery)</source><creator>Tseng, Kuo-Kun ; Lee, Dachao ; Chen, Charles</creator><creatorcontrib>Tseng, Kuo-Kun ; Lee, Dachao ; Chen, Charles</creatorcontrib><description>This paper proposes a human identification system via extracted electrocardiogram (ECG) signals. Two hierarchical classification structures based on global shape feature and local statistical feature is used to extract ECG signals. Global shape feature represents the outline information of ECG signals and local statistical feature extracts the information between signals in time domain. Genetic algorithm based back propagation neural network is used as the specific classifier. Experiment results show that our identification system can achieves an average 97.6% accuracy on a 38 subjects of PTB public ECG database and an average 100% accuracy on an 18 subjects of MIT-BIH public ECG database, which demonstrates the proposed system can reach satisfactory effects. [For full proceedings, see ED571459.]</description><language>eng</language><publisher>International Association for the Development of the Information Society</publisher><subject>Artificial Intelligence ; Classification ; Identification ; Medicine</subject><ispartof>International Association for Development of the Information Society, 2016</ispartof><tpages>8</tpages><format>8</format><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>230,687,776,881,4476</link.rule.ids><linktorsrc>$$Uhttp://eric.ed.gov/ERICWebPortal/detail?accno=ED571582$$EView_record_in_ERIC_Clearinghouse_on_Information_&amp;_Technology$$FView_record_in_$$GERIC_Clearinghouse_on_Information_&amp;_Technology$$Hfree_for_read</linktorsrc><backlink>$$Uhttp://eric.ed.gov/ERICWebPortal/detail?accno=ED571582$$DView record in ERIC$$Hfree_for_read</backlink></links><search><creatorcontrib>Tseng, Kuo-Kun</creatorcontrib><creatorcontrib>Lee, Dachao</creatorcontrib><creatorcontrib>Chen, Charles</creatorcontrib><title>ECG Identification System Using Neural Network with Global and Local Features</title><title>International Association for Development of the Information Society</title><description>This paper proposes a human identification system via extracted electrocardiogram (ECG) signals. Two hierarchical classification structures based on global shape feature and local statistical feature is used to extract ECG signals. Global shape feature represents the outline information of ECG signals and local statistical feature extracts the information between signals in time domain. Genetic algorithm based back propagation neural network is used as the specific classifier. Experiment results show that our identification system can achieves an average 97.6% accuracy on a 38 subjects of PTB public ECG database and an average 100% accuracy on an 18 subjects of MIT-BIH public ECG database, which demonstrates the proposed system can reach satisfactory effects. [For full proceedings, see ED571459.]</description><subject>Artificial Intelligence</subject><subject>Classification</subject><subject>Identification</subject><subject>Medicine</subject><fulltext>true</fulltext><rsrctype>report</rsrctype><creationdate>2016</creationdate><recordtype>report</recordtype><sourceid>GA5</sourceid><recordid>eNrjZPB1dXZX8ExJzSvJTMtMTizJzM9TCK4sLknNVQgtzsxLV_BLLS1KzAFSJeX5RdkK5ZklGQruOflJQLHEvBQFn_xkIMstNbGktCi1mIeBNS0xpziVF0pzM8i4uYY4e-imFmUmxxcUZeYmFlXGu7qYmhuaWhgZE5AGAFMcMsU</recordid><startdate>201612</startdate><enddate>201612</enddate><creator>Tseng, Kuo-Kun</creator><creator>Lee, Dachao</creator><creator>Chen, Charles</creator><general>International Association for the Development of the Information Society</general><scope>ERI</scope><scope>GA5</scope></search><sort><creationdate>201612</creationdate><title>ECG Identification System Using Neural Network with Global and Local Features</title><author>Tseng, Kuo-Kun ; Lee, Dachao ; Chen, Charles</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-eric_primary_ED5715823</frbrgroupid><rsrctype>reports</rsrctype><prefilter>reports</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Artificial Intelligence</topic><topic>Classification</topic><topic>Identification</topic><topic>Medicine</topic><toplevel>online_resources</toplevel><creatorcontrib>Tseng, Kuo-Kun</creatorcontrib><creatorcontrib>Lee, Dachao</creatorcontrib><creatorcontrib>Chen, Charles</creatorcontrib><collection>ERIC</collection><collection>ERIC - Full Text Only (Discovery)</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tseng, Kuo-Kun</au><au>Lee, Dachao</au><au>Chen, Charles</au><format>book</format><genre>unknown</genre><ristype>RPRT</ristype><ericid>ED571582</ericid><atitle>ECG Identification System Using Neural Network with Global and Local Features</atitle><jtitle>International Association for Development of the Information Society</jtitle><date>2016-12</date><risdate>2016</risdate><abstract>This paper proposes a human identification system via extracted electrocardiogram (ECG) signals. Two hierarchical classification structures based on global shape feature and local statistical feature is used to extract ECG signals. Global shape feature represents the outline information of ECG signals and local statistical feature extracts the information between signals in time domain. Genetic algorithm based back propagation neural network is used as the specific classifier. Experiment results show that our identification system can achieves an average 97.6% accuracy on a 38 subjects of PTB public ECG database and an average 100% accuracy on an 18 subjects of MIT-BIH public ECG database, which demonstrates the proposed system can reach satisfactory effects. [For full proceedings, see ED571459.]</abstract><pub>International Association for the Development of the Information Society</pub><tpages>8</tpages><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof International Association for Development of the Information Society, 2016
issn
language eng
recordid cdi_eric_primary_ED571582
source ERIC - Full Text Only (Discovery)
subjects Artificial Intelligence
Classification
Identification
Medicine
title ECG Identification System Using Neural Network with Global and Local Features
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T18%3A56%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-eric_GA5&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=unknown&rft.atitle=ECG%20Identification%20System%20Using%20Neural%20Network%20with%20Global%20and%20Local%20Features&rft.jtitle=International%20Association%20for%20Development%20of%20the%20Information%20Society&rft.au=Tseng,%20Kuo-Kun&rft.date=2016-12&rft_id=info:doi/&rft_dat=%3Ceric_GA5%3EED571582%3C/eric_GA5%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ericid=ED571582&rfr_iscdi=true