Rancang Bangun Wearable Electrocardiography untuk Mendeteksi Myocardial Ischemia Menggunakan Artificial Neural Network Classifiers

Fachturrohman, Achmad (2022) Rancang Bangun Wearable Electrocardiography untuk Mendeteksi Myocardial Ischemia Menggunakan Artificial Neural Network Classifiers. Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img] Text
07311740000025-Undergraduate_Thesis.pdf
Restricted to Repository staff only

Download (3MB) | Request a copy
[img] Text
07311740000025-Undergraduate_Thesis.pdf - Accepted Version
Restricted to Repository staff only until 1 April 2024.

Download (3MB) | Request a copy

Abstract

Penyakit jantung adalah suatu penyakit yang disebabkan oleh kondisi kebugaran tubuh dan pembuluh darah. Iskemia merupakan penyakit jantung yang disebabkan oleh arterosklerosis, yaitu penyempitan pembuluh darah arteri yang disebabkan penumpukan kolesterol berupa plak pada pembuluh darah arteri yang mengakibatkan aliran darah balik menuju jantung terhambat. Sehingga otot jantung kekurangan pasokan oksigen dan menurunkan kemampuannya memompa darah. Keadaan seperti ini apabila terjadi terus-menerus dapat menimbulkan komplikasi serangan jantung atau myocardial infarction. Pemantauan sinyal listrik jantung dengan Electrocardiograph (ECG) telah menjadi metode non-invasif paling banyak digunakan di rumah sakit. Oleh karena itu, pada penelitian ini diusulkan device untuk mendeteksi dan memantau keadaan jantung pasien. Penelitian ini bertujuan untuk membantu pasien untuk mengetahui secara dini kondisi jantungnya terhadap penyakit jantung iskemia serta menghindari terjadinya komplikasi serangan jantung dengan menunjukkan keakuratan hasil klasifikasi. Device yang diusulkan digunakan untuk perekaman sinyal jantung dengan pengolahan sinyal digital menggunakan discrete wavelet transforms. Kemudian didapatkan puncak gelombang P, QRS, T dan dekomposisi skala 5, dilanjutkan klasifikasi menggunakan artificial neural network. Proses klasifikasi mengkategorikan sinyal ke dalam 2 class yaitu normal dan iskemia. Dengan pengujian menggunakan dua data yang memuat puncak gelombang ECG dan dekomposisi skala 5 yang didapatkan dari pengolahan dengan dicrete wavelet transform. Diperoleh hasil klasifikasi terbaik pada pengujian dengan data memuat dekomposisi skala 5 dengan 96,17% akurasi, 93,08% presisi, 95,6% spesifisitas, dan 97,11% sensitivitas. Sehingga implementasi pada device menggunakan data dari pengujian dengan hasil klasifikasi yang paling baik. =============================================================================================== Heart disease is a disease caused by the condition of the body's fitness and blood vessels. Ischemia is a heart disease caused by atherosclerosis, which is narrowing of the arteries caused by the buildup of cholesterol in the form of plaque in the arteries which results in obstructed blood flow back to the heart. So that the heart muscle lacks oxygen supply and reduces its ability to pump blood. This condition, if it occurs continuously, can lead to complications of a heart attack or myocardial infarction. Electrocardiograph (ECG) monitoring of the heart's electrical signals has become the most widely used non-invasive method in hospitals. Therefore, in this study a device is proposed to detect and monitor the patient's heart condition. This study aims to help patients to find out early on their heart condition against ischemic heart disease and avoid complications of heart attack by showing the accuracy of the classification results. The proposed device is used for recording cardiac signals by processing digital signals using discrete wavelet transforms. Then obtained P, QRS, T wave peaks and a 5th scale of decomposition, followed by classification using an artificial neural network. The classification process categorizes signals into 2 classes, namely normal and ischemia. By testing using two data containing the peak of the ECG wave and a 5th scale of decomposition obtained from processing with the discrete wavelet transform. The best classification results were obtained on the test with data containing 5th scale of decomposition with 96.17% accuracy, 93.08% precision, 95.6% specificity, and 97.11% sensitivity. So that the implementation on the device uses data from testing with the best classification results.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Iskemia, Penyakit Jantung, discrete wavelet transforms, artificial neural network, Myocardial Ischemia, Heart Disease, Discrete Wavelet Transforms, Artificial Neural Network.
Subjects: Q Science > Q Science (General) > Q325.5 Machine learning.
Q Science > QA Mathematics > QA336 Artificial Intelligence
Q Science > QA Mathematics > QA403.3 Wavelets (Mathematics)
R Medicine > R Medicine (General) > R858 Deep Learning
R Medicine > RC Internal medicine > RC683.5.E5 Electrocardiography
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.9 Signal processing.
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7878 Electronic instruments
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Biomedical Engineering > 11410-(S1) Undergraduate Thesis
Depositing User: Achmad Fachturrohman
Date Deposited: 09 Feb 2022 07:25
Last Modified: 10 Feb 2022 02:43
URI: https://repository.its.ac.id/id/eprint/93176

Actions (login required)

View Item View Item