KLASIFIKASI MYOCARDIAL INFARCTION PADA SINYAL ELEKTROKARDIOGRAM MULTILEAD MENGGUNAKAN UNIDIRECTIONAL-BIDIRECTIONAL GATED RECURRENT UNIT

SUNOKI, RIBOWO AGUSTI and Nurmaini, Siti (2021) KLASIFIKASI MYOCARDIAL INFARCTION PADA SINYAL ELEKTROKARDIOGRAM MULTILEAD MENGGUNAKAN UNIDIRECTIONAL-BIDIRECTIONAL GATED RECURRENT UNIT. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281722047.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281722047_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
Preview	Text RAMA_56201_09011281722047_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (547kB) | Preview
	Text RAMA_56201_09011281722047_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (372kB) | Request a copy
	Text RAMA_56201_09011281722047_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (398kB) | Request a copy
	Text RAMA_56201_09011281722047_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_09011281722047_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (99kB) | Request a copy
	Text RAMA_56201_09011281722047_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (105kB) | Request a copy
	Text RAMA_56201_09011281722047_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (352kB) | Request a copy

Abstract

Myocardial Infarction (MI) is caused by blockage of blood flow to the myocardial segment, ECG monitoring is a major factor in reducing mortality. Electrocardiogram (ECG) is electrical records that contains information about human heart. Classification can be very hard for doctor to do because of human errors. Because of that, automation of ECG classification by using deep learning is preferred. The deep learnings methodology used in this study is Recurrent Neural Network (RNN) with Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) by using Bidirectional. GRU is an effective method for classifying time series data. LSTM can also overcome vanishing gradient’s problems that occur in RNN. In this study, delineation is applied to 2 and 4 types of class. There are 14 models generated with the best learning rate, number of hidden layers and batch size for every type of class. From the 14 experimental models, the best model is obtained by using Bi-GRU in both types of class scenarios. Bi-GRU’s model have the highest evaluation values in 4 types of waves scenarios with performance value of sensitivity, precision, specificity, accuracy and F1-Score respectively 87.75%, 88,66%, 96.27%, 96.80%, dan 88.19%

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Elektrokardiogram, Klasifikasi, Recurrent Neural Network, Myocardial Infarction, Gated Recurrent Unit
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:	RIBOWO AGUSTI SUNOKI
Date Deposited:	29 Nov 2021 07:19
Last Modified:	29 Nov 2021 07:19
URI:	http://repository.unsri.ac.id/id/eprint/58153

Actions (login required)

View Item