Population based ant colony optimization for reconstructing ECG signals

Yih Chun Cheng; Tom Hartmann; Pei Yun Tsai; Martin Middendorf

doi:10.1007/s12065-016-0139-0

Population based ant colony optimization for reconstructing ECG signals

Yih Chun Cheng, Tom Hartmann, Pei Yun Tsai, Martin Middendorf

Department of Electrical Engineering

Research output: Contribution to journal › Article › peer-review

4 Scopus citations

Abstract

A population based ant colony optimization algorithm (PACO) for the reconstruction of electrocardiogram (ECG) signals is proposed. Specifically, the PACO finds a subset of nonzero positions of a sparse wavelet domain ECG signal vector that is used for the reconstruction of the signal. A time window is used by the proposed PACO for fixing certain decisions of the ants during the run of the algorithm. The optimization behaviour of the PACO is compared with various algorithms from the literature for ECG signal reconstruction, and with two random search heuristics. Experimental results are presented for ECG signals from the MIT-BIT Arrhythmia database. The influence of several algorithmic parameters and of a local search procedure is evaluated. The results show that the proposed PACO algorithm reconstructs ECG signals with high accuracy.

Original language	English
Pages (from-to)	55-66
Number of pages	12
Journal	Evolutionary Intelligence
Volume	9
Issue number	3
DOIs	https://doi.org/10.1007/s12065-016-0139-0
State	Published - 1 Sep 2016

Keywords

ECG signals
Population based ACO
Signal reconstruction
Subset selection problem

Access to Document

10.1007/s12065-016-0139-0

Cite this

@article{d6b087b5631c4b229a36c47d7894cf81,

title = "Population based ant colony optimization for reconstructing ECG signals",

abstract = "A population based ant colony optimization algorithm (PACO) for the reconstruction of electrocardiogram (ECG) signals is proposed. Specifically, the PACO finds a subset of nonzero positions of a sparse wavelet domain ECG signal vector that is used for the reconstruction of the signal. A time window is used by the proposed PACO for fixing certain decisions of the ants during the run of the algorithm. The optimization behaviour of the PACO is compared with various algorithms from the literature for ECG signal reconstruction, and with two random search heuristics. Experimental results are presented for ECG signals from the MIT-BIT Arrhythmia database. The influence of several algorithmic parameters and of a local search procedure is evaluated. The results show that the proposed PACO algorithm reconstructs ECG signals with high accuracy.",

keywords = "ECG signals, Population based ACO, Signal reconstruction, Subset selection problem",

author = "Cheng, {Yih Chun} and Tom Hartmann and Tsai, {Pei Yun} and Martin Middendorf",

note = "Publisher Copyright: {\textcopyright} 2016, Springer-Verlag Berlin Heidelberg.",

year = "2016",

month = sep,

day = "1",

doi = "10.1007/s12065-016-0139-0",

language = "???core.languages.en_GB???",

volume = "9",

pages = "55--66",

journal = "Evolutionary Intelligence",

issn = "1864-5909",

number = "3",

}

TY - JOUR

T1 - Population based ant colony optimization for reconstructing ECG signals

AU - Cheng, Yih Chun

AU - Hartmann, Tom

AU - Tsai, Pei Yun

AU - Middendorf, Martin

PY - 2016/9/1

Y1 - 2016/9/1

N2 - A population based ant colony optimization algorithm (PACO) for the reconstruction of electrocardiogram (ECG) signals is proposed. Specifically, the PACO finds a subset of nonzero positions of a sparse wavelet domain ECG signal vector that is used for the reconstruction of the signal. A time window is used by the proposed PACO for fixing certain decisions of the ants during the run of the algorithm. The optimization behaviour of the PACO is compared with various algorithms from the literature for ECG signal reconstruction, and with two random search heuristics. Experimental results are presented for ECG signals from the MIT-BIT Arrhythmia database. The influence of several algorithmic parameters and of a local search procedure is evaluated. The results show that the proposed PACO algorithm reconstructs ECG signals with high accuracy.

AB - A population based ant colony optimization algorithm (PACO) for the reconstruction of electrocardiogram (ECG) signals is proposed. Specifically, the PACO finds a subset of nonzero positions of a sparse wavelet domain ECG signal vector that is used for the reconstruction of the signal. A time window is used by the proposed PACO for fixing certain decisions of the ants during the run of the algorithm. The optimization behaviour of the PACO is compared with various algorithms from the literature for ECG signal reconstruction, and with two random search heuristics. Experimental results are presented for ECG signals from the MIT-BIT Arrhythmia database. The influence of several algorithmic parameters and of a local search procedure is evaluated. The results show that the proposed PACO algorithm reconstructs ECG signals with high accuracy.

KW - ECG signals

KW - Population based ACO

KW - Signal reconstruction

KW - Subset selection problem

UR - http://www.scopus.com/inward/record.url?scp=84979982353&partnerID=8YFLogxK

U2 - 10.1007/s12065-016-0139-0

DO - 10.1007/s12065-016-0139-0

M3 - 期刊論文

AN - SCOPUS:84979982353

SN - 1864-5909

VL - 9

SP - 55

EP - 66

JO - Evolutionary Intelligence

JF - Evolutionary Intelligence

IS - 3

ER -

Population based ant colony optimization for reconstructing ECG signals

Abstract

Keywords

Access to Document

Fingerprint

Cite this