KLASIFIKASI SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN DENOISING AUTOENCODER DAN CONVOLUTIONAL NEURAL NETWORK

AUDREY, BERBY FEBRIANA and Nurmaini, Siti (2022) KLASIFIKASI SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN DENOISING AUTOENCODER DAN CONVOLUTIONAL NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281823062.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011281823062_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
Preview	Text RAMA_56201_09011281823062_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011281823062_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (610kB) | Request a copy
	Text RAMA_56201_09011281823062_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011281823062_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011281823062_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (107kB) | Request a copy
	Text RAMA_56201_09011281823062_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (251kB) | Request a copy
	Text RAMA_56201_09011281823062_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (769kB) | Request a copy

Abstract

Arrhythmia is a sign or symptom of a heart rate or heart rhythm abnormality Early detection of arrhythmia can help patients in treating the disease appropriately. Arrhythmia disease can be detected using an electrocardiogram (ECG) which is a recording of electrical signals of cardiac activity. This study conducted a classification of normal cardiac and fibrillation arrhythmias on ECG signals. The Convolutional Neural Network method was proposed because it is able to process data that is non-linear in nature such as ECG signals. The data used are obtained from Physionet.org sites with an unbalanced distribution of classes containing noise. To overcome data containing noise, the Denoising Autoencoder method is used to remove noise from the ECG signal and autoencoder to extract features from the ECG signal that has been removed noise. The two techniques above showed the results of the accuracy value of 74.62%, sensitivity of 75.11%, specificity of 70%, precision of 95.93% and F1 Score of 84.26%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Elektrokardiogram, Klasifikasi, Aritmia, Convolutional Neural Network, Denoising Autoencoder, Autoencoder
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Berby Febriana Audrey
Date Deposited:	23 Sep 2022 06:40
Last Modified:	23 Sep 2022 06:40
URI:	http://repository.unsri.ac.id/id/eprint/79617

Actions (login required)

View Item