PENINGKATAN KINERJA KLASIFIKASI MULTI KELAS INFARK MIOKARD BERBASIS DEEP LEARNING

NURMULYANA, FAKHRUL and Nurmaini, Siti (2025) PENINGKATAN KINERJA KLASIFIKASI MULTI KELAS INFARK MIOKARD BERBASIS DEEP LEARNING. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_56201_09011282126076_cover.jpg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (906kB) | Preview
	Text RAMA_56201_09011282126076.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011282126076_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011282126076_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (781kB)
	Text RAMA_56201_09011282126076_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011282126076_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_09011282126076_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011282126076_0002085908_05.pdf.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (115kB) | Request a copy
	Text RAMA_56201_09011282126076_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (100kB) | Request a copy
	Text RAMA_56201_09011282126076_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (782kB) | Request a copy

Abstract

Heart disease, particularly myocardial infarction (IM), is a leading cause of global death that requires early and accurate detection to prevent fatal outcomes. This study aims to develop a deep learning-based IM multi-class classification system using ECG signals from the PTB-XL dataset. The model was built with a combination architecture of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), and compared with CNN-BiLSTM architecture. The study included 15 classification classes based on the location of IM. The research stages include preprocessing (denoising, normalization, segmentation), model training with various layer combinations, and evaluation using accuracy, precision, recall, and f1-score metrics. The segmentation process with sliding window and denoising technique using db4 wavelet, level 8, and hard threshold proved to improve the signal quality. The best model is obtained from the combination of 25 layer CNN architecture and 1 layer LSTM. Experimental results show that the optimal combination of architecture and preprocessing can improve classification performance. The findings are expected to be a solution in assisting the automatic and efficient diagnosis of IM in clinical practice.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Klasifikasi, Infark Miokard, Deep Learning, CNN, LSTM, BiLSTM
Subjects:	R Medicine > R Medicine (General) > R858-859.7 Computer applications to medicine. Medical informatics
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Fakhrul Nurmulyana
Date Deposited:	15 Jul 2025 07:49
Last Modified:	15 Jul 2025 07:49
URI:	http://repository.unsri.ac.id/id/eprint/178563

Actions (login required)

View Item