DETEKSI SINYAL ATRIAL FIBRILLATION PADA ELEKTROKARDIOGRAM MENGGUNAKAN RECURRENT NEURAL NETWORKS

AULIYA, GHINA and Nurmaini, Siti (2021) DETEKSI SINYAL ATRIAL FIBRILLATION PADA ELEKTROKARDIOGRAM MENGGUNAKAN RECURRENT NEURAL NETWORKS. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281722055.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (17MB) | Request a copy
	Text RAMA_56201_09011281722055_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (25MB) | Request a copy
Preview	Text RAMA_56201_09011281722055_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (7MB) | Preview
	Text RAMA_56201_09011281722055_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281722055_0002085908_03.pdf.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011281722055_0002085908_04.pdf.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011281722055_0002085908_05.pdf.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281722055_0002085908_06_ref.pdf.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281722055_0002085908_07_lamp.pdf.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Atrial fibrillation is a disturbance in the function of the heart's electrical system which is characterized by an irregular heartbeat. Conventional detection of AF is often diagnosed through data visualization using an electrocardiograph by cardiologists with the results of the evaluation in the form of a recorded electrocardiogram (ECG) wave. The method used in this research is Recurrent Neural Networks (RNN) Long Short-Term Memory (LSTM) architecture. The RNN method is very suitable for processing sequential data such as ECG signals. LSTM is an effective method for processing time series data. In this study, the classification for 3 classes was carried out on the parameters of the learning rate, the number of hidden layers and the best batch size. In addition, the use of the K-fold Cross Validation method is carried out to find the best data combination, both in terms of accuracy, precision, error and others. The number of features per one time step is 500 points with 3 classes. Of the 22 models that have been tested, the best model is obtained by adding the number of hidden layers and using the Bi-LSTM model for 3 classes. The Bi-LSTM model achieved the highest evaluation results on the classification of 3 classes of ECG signals with an average sensitivity, precision, specificity, accuracy and F1 values of 94.14%, 94.04%, 97.41%, 96.41%, and 94.08%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Elektrokardiogram, Atrial Fibrillation, Recurrent Neural Networks, Long Short-Term Memory
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 11319 not found.
Date Deposited:	12 Apr 2021 08:05
Last Modified:	12 Apr 2021 08:05
URI:	http://repository.unsri.ac.id/id/eprint/45414

Actions (login required)

View Item