• Something wrong with this record ?

Modified ant colony clustering method in long-term electrocardiogram processing

M. Bursa, L. Lhotska

Language English Country United States

Document type Evaluation Study

The paper presents an application of a clustering technique inspired by ant colony metaheuristics. The paper addresses the problem of long-term (Holter) electrocardiogram data processing. Long-term recording produces a huge amount of biomedical data, which must be preprocessed prior to its presentation to the specialist. The paper also discusses relevant aspects improving the robustness, stability and convergence criteria of the method. The method is compared with well known clustering techniques (both classical and nature-inspired), first testing on the known dataset and finally applying them to the real ECG data records from the MIT-BIH database and outperforms the standard methods. Electrocardiogram data clustering can effectively reduce the amount of data presented to the cardiologist: cardiac arrhythmia and significant morphology changes in the ECG can be visually emphasized in a reasonable time. The final evaluation of the ECG recording must still be made by an expert.

000      
00000naa 2200000 a 4500
001      
bmc10026779
003      
CZ-PrNML
005      
20120806110047.0
008      
101019s2007 xxu e eng||
009      
AR
040    __
$a ABA008 $b cze $c ABA008 $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Burša, Miroslav $7 xx0141366
245    10
$a Modified ant colony clustering method in long-term electrocardiogram processing / $c M. Bursa, L. Lhotska
314    __
$a Czech Technical University in Prague, Czech Republic, Dept. of Cybernetics, Gerstner laboratory. bursam@fel.cvut.cz
520    9_
$a The paper presents an application of a clustering technique inspired by ant colony metaheuristics. The paper addresses the problem of long-term (Holter) electrocardiogram data processing. Long-term recording produces a huge amount of biomedical data, which must be preprocessed prior to its presentation to the specialist. The paper also discusses relevant aspects improving the robustness, stability and convergence criteria of the method. The method is compared with well known clustering techniques (both classical and nature-inspired), first testing on the known dataset and finally applying them to the real ECG data records from the MIT-BIH database and outperforms the standard methods. Electrocardiogram data clustering can effectively reduce the amount of data presented to the cardiologist: cardiac arrhythmia and significant morphology changes in the ECG can be visually emphasized in a reasonable time. The final evaluation of the ECG recording must still be made by an expert.
650    _2
$a algoritmy $7 D000465
650    _2
$a zvířata $7 D000818
650    _2
$a Formicidae $x fyziologie $7 D001000
650    _2
$a srdeční arytmie $x diagnóza $x patofyziologie $7 D001145
650    _2
$a chování zvířat $7 D001522
650    _2
$a biomimetika $x metody $7 D032701
650    _2
$a shluková analýza $7 D016000
650    _2
$a diagnóza počítačová $x metody $7 D003936
650    _2
$a elektrokardiografie ambulantní $x metody $7 D015716
650    _2
$a srdeční frekvence $7 D006339
650    _2
$a lidé $7 D006801
650    _2
$a rozpoznávání automatizované $x metody $7 D010363
650    _2
$a reprodukovatelnost výsledků $7 D015203
650    _2
$a senzitivita a specificita $7 D012680
650    _2
$a počítačové zpracování signálu $7 D012815
650    _2
$a financování organizované $7 D005381
655    _2
$a hodnotící studie $7 D023362
700    1_
$a Lhotská, Lenka, $d 1961- $7 ntka173228
773    0_
$t Conf Proc IEEE Eng Med Biol Soc. $w MED00180111 $g (2007), s. 3249-3252 $x 1557-170X
910    __
$a ABA008 $b x $y 7
990    __
$a 20110413105016 $b ABA008
991    __
$a 20120806110133 $b ABA008
999    __
$a ok $b bmc $g 801884 $s 666644
BAS    __
$a 3
BMC    __
$a 2007 $d 3249-3252 $i 1557-170X $m Conference proceedings ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society $n Conf Proc IEEE Eng Med Biol Soc $x MED00180111
LZP    __
$a 2010-B3/vtme

Find record

Citation metrics

Loading data ...

Archiving options

Loading data ...