Cardiac Arrhythmias Automated Screening Using Discrete Fractional-Order Integration Process and Meta Learning Based Intelligent Classifier

Chia Hung Lin, Chung-Dann Kan, Jieh-Neng Wang, Wei Ling Chen, Pi Yun Chen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Cardiac arrhythmias reveal multiple morphologies in time-domain waveforms. Abnormal beats reflect the origin and the conduction path of the ectopic heart activation pulses, including supraventricular, junctional, and ventricular arrhythmias and conduction abnormalities. This paper proposes a method for automated screening of cardiac arrhythmias using the discrete fractional-order integration (DFOI) and the meta-learning-based intelligent classifier. The DFOI process with the specific fractional order is used to extract the QRS features with the finite computations. It can deal with the irregular time-varying signals. The meta-learning-based intelligent classifier is used to identify the abnormal classes, consisting of a primary multilayer network and several agent networks. Since abnormal QRS complexes are multi-waveforms such as ventricular premature contraction, the classifier needs to retrain with new training patterns for meeting new condition in clinical applications. Thus, this model possesses the learning-to-optimization capability for retraining generalized regression neural network using the particle swarm optimization algorithm. Using incremental new training patterns, each inducer is used to track the past learning experiences through several agent networks. This pattern scheme can gradually enhance the accuracy by refining the optimal parameters of each sub-estimator for pattern recognition. Using the arrhythmia database of the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) database, the proposed intelligent classifier demonstrated greater efficiency and promising results in average accuracy, positive predictivity, and true negative rate for recognizing electrocardiography signals.

Original languageEnglish
Article number8466771
Pages (from-to)52652-52667
Number of pages16
JournalIEEE Access
Volume6
DOIs
Publication statusPublished - 2018 Sep 15

Fingerprint

Screening
Classifiers
Electrocardiography
Particle swarm optimization (PSO)
Refining
Pattern recognition
Multilayers
Chemical activation
Neural networks

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Cite this

@article{770390a200d14bbd8224f238ceb2f668,
title = "Cardiac Arrhythmias Automated Screening Using Discrete Fractional-Order Integration Process and Meta Learning Based Intelligent Classifier",
abstract = "Cardiac arrhythmias reveal multiple morphologies in time-domain waveforms. Abnormal beats reflect the origin and the conduction path of the ectopic heart activation pulses, including supraventricular, junctional, and ventricular arrhythmias and conduction abnormalities. This paper proposes a method for automated screening of cardiac arrhythmias using the discrete fractional-order integration (DFOI) and the meta-learning-based intelligent classifier. The DFOI process with the specific fractional order is used to extract the QRS features with the finite computations. It can deal with the irregular time-varying signals. The meta-learning-based intelligent classifier is used to identify the abnormal classes, consisting of a primary multilayer network and several agent networks. Since abnormal QRS complexes are multi-waveforms such as ventricular premature contraction, the classifier needs to retrain with new training patterns for meeting new condition in clinical applications. Thus, this model possesses the learning-to-optimization capability for retraining generalized regression neural network using the particle swarm optimization algorithm. Using incremental new training patterns, each inducer is used to track the past learning experiences through several agent networks. This pattern scheme can gradually enhance the accuracy by refining the optimal parameters of each sub-estimator for pattern recognition. Using the arrhythmia database of the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) database, the proposed intelligent classifier demonstrated greater efficiency and promising results in average accuracy, positive predictivity, and true negative rate for recognizing electrocardiography signals.",
author = "Lin, {Chia Hung} and Chung-Dann Kan and Jieh-Neng Wang and Chen, {Wei Ling} and Chen, {Pi Yun}",
year = "2018",
month = "9",
day = "15",
doi = "10.1109/ACCESS.2018.2870689",
language = "English",
volume = "6",
pages = "52652--52667",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Cardiac Arrhythmias Automated Screening Using Discrete Fractional-Order Integration Process and Meta Learning Based Intelligent Classifier. / Lin, Chia Hung; Kan, Chung-Dann; Wang, Jieh-Neng; Chen, Wei Ling; Chen, Pi Yun.

In: IEEE Access, Vol. 6, 8466771, 15.09.2018, p. 52652-52667.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Cardiac Arrhythmias Automated Screening Using Discrete Fractional-Order Integration Process and Meta Learning Based Intelligent Classifier

AU - Lin, Chia Hung

AU - Kan, Chung-Dann

AU - Wang, Jieh-Neng

AU - Chen, Wei Ling

AU - Chen, Pi Yun

PY - 2018/9/15

Y1 - 2018/9/15

N2 - Cardiac arrhythmias reveal multiple morphologies in time-domain waveforms. Abnormal beats reflect the origin and the conduction path of the ectopic heart activation pulses, including supraventricular, junctional, and ventricular arrhythmias and conduction abnormalities. This paper proposes a method for automated screening of cardiac arrhythmias using the discrete fractional-order integration (DFOI) and the meta-learning-based intelligent classifier. The DFOI process with the specific fractional order is used to extract the QRS features with the finite computations. It can deal with the irregular time-varying signals. The meta-learning-based intelligent classifier is used to identify the abnormal classes, consisting of a primary multilayer network and several agent networks. Since abnormal QRS complexes are multi-waveforms such as ventricular premature contraction, the classifier needs to retrain with new training patterns for meeting new condition in clinical applications. Thus, this model possesses the learning-to-optimization capability for retraining generalized regression neural network using the particle swarm optimization algorithm. Using incremental new training patterns, each inducer is used to track the past learning experiences through several agent networks. This pattern scheme can gradually enhance the accuracy by refining the optimal parameters of each sub-estimator for pattern recognition. Using the arrhythmia database of the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) database, the proposed intelligent classifier demonstrated greater efficiency and promising results in average accuracy, positive predictivity, and true negative rate for recognizing electrocardiography signals.

AB - Cardiac arrhythmias reveal multiple morphologies in time-domain waveforms. Abnormal beats reflect the origin and the conduction path of the ectopic heart activation pulses, including supraventricular, junctional, and ventricular arrhythmias and conduction abnormalities. This paper proposes a method for automated screening of cardiac arrhythmias using the discrete fractional-order integration (DFOI) and the meta-learning-based intelligent classifier. The DFOI process with the specific fractional order is used to extract the QRS features with the finite computations. It can deal with the irregular time-varying signals. The meta-learning-based intelligent classifier is used to identify the abnormal classes, consisting of a primary multilayer network and several agent networks. Since abnormal QRS complexes are multi-waveforms such as ventricular premature contraction, the classifier needs to retrain with new training patterns for meeting new condition in clinical applications. Thus, this model possesses the learning-to-optimization capability for retraining generalized regression neural network using the particle swarm optimization algorithm. Using incremental new training patterns, each inducer is used to track the past learning experiences through several agent networks. This pattern scheme can gradually enhance the accuracy by refining the optimal parameters of each sub-estimator for pattern recognition. Using the arrhythmia database of the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) database, the proposed intelligent classifier demonstrated greater efficiency and promising results in average accuracy, positive predictivity, and true negative rate for recognizing electrocardiography signals.

UR - http://www.scopus.com/inward/record.url?scp=85053342462&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053342462&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2870689

DO - 10.1109/ACCESS.2018.2870689

M3 - Article

AN - SCOPUS:85053342462

VL - 6

SP - 52652

EP - 52667

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8466771

ER -