DELINEASI SINGLE-LEAD SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN DEEP LEARNING DENGAN BAYESIAN HYPERPARAMETER TUNING OPTIMIZATION

MARCELINO, JORDAN and Darmawahyuni, Annisa (2024) DELINEASI SINGLE-LEAD SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN DEEP LEARNING DENGAN BAYESIAN HYPERPARAMETER TUNING OPTIMIZATION. Undergraduate thesis, Sriwijaya University.

	Image RAMA_55201_09021282126077_cover.jpg - Cover Image Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (230kB) | Request a copy
	Text RAMA_55201_09021282126077.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_55201_09021282126077_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021282126077_8968340022_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB)
	Text RAMA_55201_09021282126077_8968340022_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (552kB) | Request a copy
	Text RAMA_55201_09021282126077_8968340022_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (505kB) | Request a copy
	Text RAMA_55201_09021282126077_8968340022_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (481kB) | Request a copy
	Text RAMA_55201_09021282126077_8968340022_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (649kB) | Request a copy
	Text RAMA_55201_09021282126077_8968340022_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9kB) | Request a copy
	Text RAMA_55201_09021282126077_8968340022_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (79kB) | Request a copy
	Text RAMA_55201_09021282126077_8968340022_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy

Abstract

Electrocardiogram (ECG) is a medical procedure used to assess cardiac function, including its electrical activity. With the increasing prevalence of heart disease, which recorded an 18.71% rise in 2020 compared to 2010, the role of ECG interpretation has become critically important. Cardiac conditions can be analyzed through the morphology of ECG signals, consisting of the P wave, QRS complex, and T wave. This research employs a Deep Learning (DL) approach combining Convolutional Neural Network (CNN) and Bidirectional Long-Short Term Memory (BiLSTM) to delineate single-lead ECG signals. Bayesian optimization was utilized to fine-tune hyperparameters and enhance model performance. The dataset used in this research is the Lobachevsky University Database (LUDB). The study achieved an accuracy of 99.28%, specificity of 99.49%, recall of 91.99%, precision of 92.66%, and an F1-score of 92.3%. The application of DL and Bayesian optimization demonstrated high efficacy in delineating single-lead ECG signals, particularly for normal beats. For future work, this research could be expanded to explore more diverse datasets and Deep Learning architectures.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Elektrokardiogram, Deep Learning, Convolutional Neural Network, Long-Short Term Memory, Bayesian Optimization
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Jordan Marcelino
Date Deposited:	13 Jan 2025 07:57
Last Modified:	13 Jan 2025 07:57
URI:	http://repository.unsri.ac.id/id/eprint/164383

Actions (login required)

View Item