The impact of Negative to Positive Training Dataset Ratio on Atrial Fibrillation Classification Machine Learning Algorithms Performance
-
Published:2020-04-01
Issue:1
Volume:1500
Page:012131
-
ISSN:1742-6588
-
Container-title:Journal of Physics: Conference Series
-
language:
-
Short-container-title:J. Phys.: Conf. Ser.
Author:
Firdaus ,Herviant Juliano Andre,Rachmatullah Naufal,Putri Rafflesia Sarifah,Yunika Hardiyanti Dinna,Zarkasi Ahmad,Pratiwi Arisanti Ferlita,Nurmaini Siti
Abstract
Abstract
With the few numbers of cardiologists in Indonesia who not evenly distributed, especially in rural areas, there has been a lot of smart telehealth specifically developed for heart monitoring using ECG. Many techniques have been developed to improve the accuracy of this device by using datasets that are mostly imbalanced, more positive data than negative. This paper presents the comparison of negative to positive training dataset ratio on atrial fibrillation classification machine learning algorithms performance. An AliveCor ECG recording dataset is train with deep neural networks, support vector machine and logistic regression as classifier with three different ratios, 1:1, 1:5 to 1:All. Results show an increase in classifier performance along with the increasing number of negative data.
Subject
General Physics and Astronomy
Reference26 articles.
1. Cardiac Arrhythmias Classification Using Deep Neural Networks and Principle Component Analysis Algorithm;Nurmaini;Int. J. Adv. Soft Compu. Appl.,2018
2. Cardiac Arrhythmia Detection from ECG Combining Convolutional and Long Short-Term Memory Networks;Warrick,2017
3. Computer-aided diagnosis of atrial fibrillation based on ECG Signals: A review;Hagiwara;Inf. Sci. (Ny).,2018