KLASIFIKASI 15 KELAS BEAT GANGGUAN ARITMIA MENGGUNAKAN AUTOENCODER DAN DEEP NEURAL NETWORK

PUTRA, TOMI MANDALA and Nurmaini, Siti (2021) KLASIFIKASI 15 KELAS BEAT GANGGUAN ARITMIA MENGGUNAKAN AUTOENCODER DAN DEEP NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281722076.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011281722076_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
Preview	Text RAMA_56201_09011281722076_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (921kB) | Preview
	Text RAMA_56201_09011281722076_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (752kB) | Request a copy
	Text RAMA_56201_09011281722076_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (688kB) | Request a copy
	Text RAMA_56201_09011281722076_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_09011281722076_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (184kB) | Request a copy
	Text RAMA_56201_09011281722076_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (304kB) | Request a copy
	Text RAMA_56201_09011281722076_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (328kB) | Request a copy

Abstract

Electrocardiography (ECG) is a medical test to examine the condition of the heart in a representation of electrical signals that provide clinical information about the patient's heart. With ECG, cardiologists are able to diagnose the patient's heart condition either by heart rate or heart rhythm. ECG beat classification with a large amount of data has its own challenges, so the Deep Learning method which has a high level of abstraction in studying features is highly superior. With the Autoencoder method as feature extraction to study features and reduce feature dimensions and Deep Neural Network as an ECG beat classifier. This study found that 48 records of the best model were superior using a Learning rate of 0.0001 with a good division on the train test split with an accuracy value of 99.82% and Stratified K-Fold with an accuracy value of 99.83%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Aritmia, elektrokardiograf, klasifikasi, Autoencoder, Deep Neural Network
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Tomi Mandala Putra
Date Deposited:	24 Nov 2021 06:20
Last Modified:	24 Nov 2021 06:20
URI:	http://repository.unsri.ac.id/id/eprint/57814

Actions (login required)

View Item