Authors :
Onwuka, Ugochukwu C; Asagba, Prince O.
Volume/Issue :
Volume 6 - 2021, Issue 11 - November
Google Scholar :
http://bitly.ws/gu88
Scribd :
https://bit.ly/3oxK6PM
Abstract :
Arrhythmias also known as dysrhythmia is a
heart ailment that arises when electrical signals that
coordinate the heartbeats do not work appropriately, they
are often precursors to a number of heart diseases which
may be terminal, and early detection and adequate
treatment can save life, in this paper we propose a
classification technique that blends two good performing
machine learning algorithms to enhance the accuracy of
detecting arrhythmia using Electrocardiogram (ECG)
data and Weka machine learning tool, these algorithms
include the J.48 and Random Forest algorithms combined
with an ensemble algorithm called Stacking; For this
experiment the MIT-BIH ECG dataset from Kaggle.com
was used to train, test and validate the hybrid algorithm.
This dataset used classified ECG data into the 5 super class
of arrhythmia approved by the association for the
advancement of medical instrumentation (AAMI) to be
detectable by equipment and methods, they include
normal sinus (N), fusion beat (F), supraventricular ectopic
beat (SVEB), ventricular ectopic beat (VEB), and
unknown beat (Q). the hybrid algorithm “stacked random
forest and j.48) outperformed the other individual
algorithms, the performance metrics gotten include
97.63% accuracy, an approximate sensitivity (recall) and
Positive predictivity (precision) value of 0.98, other metrics
includes a weighted precision recall curve area of 0.97,
receiver operator characteristics area of 0.96 and test time
of 1.66 seconds and finally a model size of 38.2mb which is
suitable for building application for mobile devices.
Keywords :
Machine Learning, Arrhythmia Classification, ECG, Random Forest, J.48, Stacking Ensemble.
Arrhythmias also known as dysrhythmia is a
heart ailment that arises when electrical signals that
coordinate the heartbeats do not work appropriately, they
are often precursors to a number of heart diseases which
may be terminal, and early detection and adequate
treatment can save life, in this paper we propose a
classification technique that blends two good performing
machine learning algorithms to enhance the accuracy of
detecting arrhythmia using Electrocardiogram (ECG)
data and Weka machine learning tool, these algorithms
include the J.48 and Random Forest algorithms combined
with an ensemble algorithm called Stacking; For this
experiment the MIT-BIH ECG dataset from Kaggle.com
was used to train, test and validate the hybrid algorithm.
This dataset used classified ECG data into the 5 super class
of arrhythmia approved by the association for the
advancement of medical instrumentation (AAMI) to be
detectable by equipment and methods, they include
normal sinus (N), fusion beat (F), supraventricular ectopic
beat (SVEB), ventricular ectopic beat (VEB), and
unknown beat (Q). the hybrid algorithm “stacked random
forest and j.48) outperformed the other individual
algorithms, the performance metrics gotten include
97.63% accuracy, an approximate sensitivity (recall) and
Positive predictivity (precision) value of 0.98, other metrics
includes a weighted precision recall curve area of 0.97,
receiver operator characteristics area of 0.96 and test time
of 1.66 seconds and finally a model size of 38.2mb which is
suitable for building application for mobile devices.
Keywords :
Machine Learning, Arrhythmia Classification, ECG, Random Forest, J.48, Stacking Ensemble.