Nature Inspired Clustering Methods in The Electrocardiogram Interpretation Process in Cardiology

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F10%3A00170436" target="_blank" >RIV/68407700:21230/10:00170436 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Nature Inspired Clustering Methods in The Electrocardiogram Interpretation Process in Cardiology

Popis výsledku v původním jazyce

The paper focuses on the field of artificial intelligence techniques and their use in biomedical data processing. It concentrates on the clustering techniques inspired by various ant colonies and other nature concepts. The paper evaluates the use of thefollowing nature inspired methods: Ant Colony inspired Clustering, Ant Colony inspired method for Decision Tree generation, Radial Basis Function Neural Networks with different learning algorithms and compare them to classical approaches, such as k-meansand hierarchical clustering. The methods have been evaluated using the annotated MIT-BIH database. Use of the Dynamic Time Warping measure improved Sensitivity about 0.7 % and Specificity about 0.9 % when compared to classical feature extraction. Thebest-performing method is the agglomerative hierarchical clustering (Se=94.3, Sp=74.1), however it is practically unusable as it is memory and computational demanding.

Název v anglickém jazyce

Nature Inspired Clustering Methods in The Electrocardiogram Interpretation Process in Cardiology

Popis výsledku anglicky

The paper focuses on the field of artificial intelligence techniques and their use in biomedical data processing. It concentrates on the clustering techniques inspired by various ant colonies and other nature concepts. The paper evaluates the use of thefollowing nature inspired methods: Ant Colony inspired Clustering, Ant Colony inspired method for Decision Tree generation, Radial Basis Function Neural Networks with different learning algorithms and compare them to classical approaches, such as k-meansand hierarchical clustering. The methods have been evaluated using the annotated MIT-BIH database. Use of the Dynamic Time Warping measure improved Sensitivity about 0.7 % and Specificity about 0.9 % when compared to classical feature extraction. Thebest-performing method is the agglomerative hierarchical clustering (Se=94.3, Sp=74.1), however it is practically unusable as it is memory and computational demanding.

Druh

D - Stať ve sborníku

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

Z - Vyzkumny zamer (s odkazem do CEZ)

Rok uplatnění

2010

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Analysis of Biomedical Signals and Images, BIOSIGNAL 2010, Proceedings

ISBN

978-80-214-4106-4

ISSN

1211-412X

e-ISSN

—

Počet stran výsledku

5

Strana od-do

—

Název nakladatele

Brno University of Technology

Místo vydání

Brno

Místo konání akce

Brno

Datum konání akce

27. 6. 2010

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—