KLASIFIKASI GAGAL JANTUNG KONGESTIF DENGAN OPTIMISASI PARAMETER LONG SHORT-TERM MEMORY MENGGUNAKAN ALGORITMA GRID SEARCH

TRINANDA, MUHAMMAD DIVO and Nurmaini, Siti (2021) KLASIFIKASI GAGAL JANTUNG KONGESTIF DENGAN OPTIMISASI PARAMETER LONG SHORT-TERM MEMORY MENGGUNAKAN ALGORITMA GRID SEARCH. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381722103.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (13MB) | Request a copy
	Text RAMA_56201_09011381722103_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (16MB) | Request a copy
Preview	Text RAMA_56201_09011381722103_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011381722103_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (600kB) | Request a copy
	Text RAMA_56201_09011381722103_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_09011381722103_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (10MB) | Request a copy
	Text RAMA_56201_09011381722103_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (186kB) | Request a copy
	Text RAMA_56201_09011381722103_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (307kB) | Request a copy
	Text RAMA_56201_09011381722103_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (756kB) | Request a copy

Abstract

Congestive Heart Failure is a growing health problem with approximately 26 million adults worldwide having suffered from Congestive Heart Failure. Congestive heart failure generally occurs due to abnormalities in the heart muscles so that the heart cannot work normally, this can result in a lack of blood supply needed by the body. Classification of the ECG signal for Congestive Heart Failure automatically using deep learning can help doctors because of human errors in annotating the ECG signal manually. The method used in this research is Long Short-Term Memory (LSTM). LSTM is an effective method in processing time series data. In addition, LSTM can overcome vanishing and exploding gradient problems in RNN. In this study, there are two classification scenarios carried out, namely the unidirectional LSTM and Bi-LSTM models with parameter values optimized using a grid search algorithm including epoch, batch size, and learning rate resulting in a total of 40 models. Based on 40 models tested, the best classification model is Bi�LSTM with parameter values of 32 batch size, 0.0001 learning rate, and 200 epochs. The Bi-LSTM model has the highest evaluation results in the classification of ECG signals for Congestive Heart Failure with sensitivity, precision, specificity, accuracy and F1 values of 95.15%, 99.23%, 99.32%, 99.78%, and 99.69%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Gagal Jantung Kongestif, Elektrokardiogram, Klasifikasi, Long Short-Term Memory, Grid Search.
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:	Users 5547 not found.
Date Deposited:	13 Jul 2021 05:03
Last Modified:	13 Jul 2021 05:03
URI:	http://repository.unsri.ac.id/id/eprint/49784

Actions (login required)

View Item