PENINGKATAN KINERJA DELINEASI SINYAL ELEKTROKARDIOGRAM MULTI-LEAD BERBASIS DEEP LEARNING

JANDERA, GIOVANO ALVIN and Nurmaini, Siti (2024) PENINGKATAN KINERJA DELINEASI SINYAL ELEKTROKARDIOGRAM MULTI-LEAD BERBASIS DEEP LEARNING. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011282025081.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_56201_09011282025081_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (14MB) | Request a copy
	Text RAMA_56201_09011282025081_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (662kB)
	Text RAMA_56201_09011282025081_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (481kB) | Request a copy
	Text RAMA_56201_09011282025081_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (656kB) | Request a copy
	Text RAMA_56201_09011282025081_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Download (8MB) | Request a copy
	Text RAMA_56201_09011282025081_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (175kB) | Request a copy
	Text RAMA_56201_09011282025081_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (192kB) | Request a copy
	Text RAMA_56201_09011282025081_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (411kB) | Request a copy

Abstract

This research explores the processing of Electrocardiogram (EKG) signals, a field in signal processing that focuses on the analysis, manipulation, and interpretation of recorded electrical activity in the heart. EKG serves as a crucial diagnostic tool in the recognition and monitoring of heart disorders. Analyzing the patterns of changes in heart rate or rhythm, consisting of the P wave, QRS complex, and T wave, can identify heart conditions in the medical world. The study utilizes data from the Lobachevsky University Database (LUDB). The research methodology adopts an approach that combines Convolutional Neural Network (CNN) as a feature extractor and the Long Short-Term Memory (LSTM) architecture as a wave classifier. In the experiments, a bidirectional LSTM (BiLSTM) is employed. Model parameters, including epoch, batch size, and learning rate, result in a total of 48 models. The research findings indicate that CNN and Bi-LSTM models perform well in signal delineation in scenarios with 5 wave classes. For this scenario, the models achieve Recall of 95.45%, Precision of 95.46%, specificity of 99.11%, Accuracy of 98.68%, and an F1 score of 95.45%. The implications of these findings suggest significant potential in supporting the diagnosis and monitoring of heart disorders through EKG signal processing using the combination of CNN and Bi-LSTM.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	SINYAL ELEKTROKARDIOGRAM,MULTI-LEAD, DEEP LEARNING
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Giovano Alvin Jandera
Date Deposited:	23 Jan 2024 04:25
Last Modified:	23 Jan 2024 04:25
URI:	http://repository.unsri.ac.id/id/eprint/139370

Actions (login required)

View Item