Nature Inspired Concepts in Long-Term Electrocardiogram Clustering
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F08%3A03151590" target="_blank" >RIV/68407700:21230/08:03151590 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—
Alternative languages
Result language
angličtina
Original language name
Nature Inspired Concepts in Long-Term Electrocardiogram Clustering
Original language description
In this paper we compare and evaluate the use of clustering approaches that use nature inspired concepts. The following methods are considered: Ant Colony inspired Clustering, Ant Colony inspired method for Decision Tree generation, Radial Basis FunctionNeural Networks with different learning algorithms. We compare the nature inspired methods to classical approaches, such as hierarchical clustering and k-means. The best-performing method over the whole dataset has been agglomerative hierarchical clustering (Se=94.3, Sp=74.1), however it is practically unusable as it is memory and computational demanding. Acceptable results (complexity vs. error) have been obtained by the Ant-Colony inspired method for Decision tree generation (Se=93.1, Sp=72.8).
Czech name
Použití přírodou inspirovaných konceptů při shlukování dlouhodobých záznamů EKG
Czech description
V tomto příspěvku jsou porovnávány a vyhodnocovány metody shlukování, které využívají přírodou inspirované koncepty.
Classification
Type
D - Article in proceedings
CEP classification
JC - Computer hardware and software
OECD FORD branch
—
Result continuities
Project
—
Continuities
Z - Vyzkumny zamer (s odkazem do CEZ)
Others
Publication year
2008
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
IFMBE Proceedings
ISBN
978-3-540-89207-6
ISSN
1680-0737
e-ISSN
—
Number of pages
4
Pages from-to
—
Publisher name
Springer
Place of publication
Berlin
Event location
Antwerp
Event date
Nov 23, 2008
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—