DELINEASI SINYAL ELEKTROKARDIOGRAM UNTUK DETEKSI T WAVE ALTERNANS MENGGUNAKAN DENOISING AUTO ENCODER DAN CONVOLUTIONAL NEURAL NETWORK 1-DIMENSI DENGAN BIDIRECTIONAL LONG SHORT TERM MEMORY

TEGUH, SAMUEL BENEDICT PUTRA and Nurmaini, Siti (2022) DELINEASI SINYAL ELEKTROKARDIOGRAM UNTUK DETEKSI T WAVE ALTERNANS MENGGUNAKAN DENOISING AUTO ENCODER DAN CONVOLUTIONAL NEURAL NETWORK 1-DIMENSI DENGAN BIDIRECTIONAL LONG SHORT TERM MEMORY. Undergraduate thesis, Sriwijaya University.

[img] Text
RAMA_56201_09011281823076.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (5MB) | Request a copy
[img] Text
RAMA_56201_09011281823076_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[img]
Preview
Text
RAMA_56201_09011281823076_0002085908_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Preview
[img] Text
RAMA_56201_09011281823076_0002085908_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (797kB) | Request a copy
[img] Text
RAMA_56201_09011281823076_0002085908_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (506kB) | Request a copy
[img] Text
RAMA_56201_09011281823076_0002085908_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (2MB) | Request a copy
[img] Text
RAMA_56201_09011281823076_0002085908_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (131kB) | Request a copy
[img] Text
RAMA_56201_09011281823076_0002085908_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (127kB) | Request a copy
[img] Text
RAMA_56201_09011281823076_0002085908_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (568kB) | Request a copy

Abstract

Electrocardiogram (ECG) is a biological signal that results from the electrical activity of the heart that is tapped through electrodes that are attached to the body. T Wave Alternans (TWA) is associated with several diseases and their accurate detection can contribute to the early diagnosis of complications that occur in the heart. The ECG signal is a very weak bioelectric signal. The method that will be used in this research is a deep learning method using a denoising autoencoder to reduce noise from the ECG signal. The methods that will be used are Denosing Autoencoder (DAE) and Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM). In this research, the datasets used are QT Database (QTDB) and T Wave Alternans Database (TWADB). QTDB will be used in the training process for model testing while TWADB as a testing process uses several DAE parameters. The model that produces the best model is DAE with SNR 36.94 with CNN model with 4 layers CNN hidden layer and 1 layer BiLSTM. This model is tested by parameter batch size 8, learning rate 0.0001, and 300 epochs. This model produces the best evaluation results with recall, precision, specificity, accuracy and FQ values of 98.55%, 98.26%, 99.89%, 99.81%, and 98.40%. The results of this delineation detected 20 of 30 data on patients who experienced TWA.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Denoising Auto-encoder, EKG Delineasi, T-wave Alternans, ConvBiLSTM, Deep Learning, Long Short-Term Memory.
Subjects: Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning
Divisions: 09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User: Samuel Benedict Putra Teguh
Date Deposited: 22 Sep 2022 05:25
Last Modified: 22 Sep 2022 05:25
URI: http://repository.unsri.ac.id/id/eprint/79179

Actions (login required)

View Item View Item