DETEKSI GAGAL JANTUNG MELALUI SINYAL ELEKTROKARDIAGRAM DENGAN METODE RECURRENT NEURAL NETWORK

PUTRA, FAISAL BAJA ESA and Nurmaini, Siti (2021) DETEKSI GAGAL JANTUNG MELALUI SINYAL ELEKTROKARDIAGRAM DENGAN METODE RECURRENT NEURAL NETWORK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281722043.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011281722043_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_09011281722043_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011281722043_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (125kB) | Request a copy
	Text RAMA_56201_09011281722043_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (761kB) | Request a copy
	Text RAMA_56201_09011281722043_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_09011281722043_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (100kB) | Request a copy
	Text RAMA_56201_09011281722043_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (121kB) | Request a copy
	Text RAMA_56201_09011281722043_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (644kB) | Request a copy

Abstract

An electrocardiogram (ECG) is a sign in the form of an electric current generated by the continuous beating of the heart. This current can find abnormalities in the heart by storing the results of the heart's performance in the form of an electric current. The method used in this research is Recurrent Neural Network (RNN) with Long short-term memory (LSTM), Bidirectional Long short-term memory (BiLSTM), Gated Recurrent Unit (GRU) and Bidirectional Gated Recurrent Unit (BIGRU) architectures. In this case, there are four data segmentation scenarios carried out, namely on 3 classes with the number of models being 20 for the learning rate parameter, the number of hidden layers and the best batch size. 100, with a Learning Rate of 0.0001, which results from the model with an average accuracy value and f1-score of 99.05% and 94.90% for 5-minute data, 99.73% and 98.63% for 15-minute data, respectively. 99.79% and 99.21% for 20 minutes data and 99.72% and 99.00% for 30 minutes data.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Elektrokardiogram, Recurrent Neural Network, Long Short-Term Memory, Gated Recurrent Unit, Bidirectional Recurrent Neural Network, Bidiretional 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:	Faisal Baja Esa Putra
Date Deposited:	29 Nov 2021 07:23
Last Modified:	29 Nov 2021 07:23
URI:	http://repository.unsri.ac.id/id/eprint/58185

Actions (login required)

View Item