OTOMATISASI DELINEASI SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN METODE LONG SHORT-TERM MEMORY BERBASIS EKSTRAKSI FITUR CONVOLUTIONAL NEURAL NETWORK 1-DIMENSI

EFFENDI, JANNES and Nurmaini, Siti (2021) OTOMATISASI DELINEASI SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN METODE LONG SHORT-TERM MEMORY BERBASIS EKSTRAKSI FITUR CONVOLUTIONAL NEURAL NETWORK 1-DIMENSI. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011181722005.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11MB) | Request a copy
	Text RAMA_56201_09011181722005_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (20MB) | Request a copy
Preview	Text RAMA_56201_09011181722005_0002085908_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011181722005_0002085908_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (605kB) | Request a copy
	Text RAMA_56201_09011181722005_0002085908_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (869kB) | Request a copy
	Text RAMA_56201_09011181722005_0002085908_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011181722005_0002085908_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (188kB) | Request a copy
	Text RAMA_56201_09011181722005_0002085908_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (316kB) | Request a copy
	Text RAMA_56201_09011181722005_0002085908_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy

Abstract

Electrocardiogram (ECG) is electrical records that contains information about human heart. In the medical field, humans heart condition can be diagnosed by analyzing the changes in hearts beat or rhythm that contain p wave, QRSComplex and T wave. Delineation can be very hard for doctor to do because of human errors. Because of that, automation of ECG delineation by using deep learning is preferred. The deep learnings methodology used in this study is Recurrent Neural Network(RNN) with Long Short-Term Memory(LSTM) combined with Convolutional Neural Network(CNN) as feature extraction. LSTM is an effective method for classifying time series data. LSTM can also overcomes vanishing gradient’s problems that occur in RNN. In this study, delineation is applied to 4 and 7 types of waves. There are 14 models generated with the best learning rate, number of hidden layers and batch size. Every time step in LSTM have 370 nodes for every types of waves. From the 14 experimental models, the best model is obtained by using CNN as feature extraction before using Bi-LSTM in both 4 and 7 types of waves. CNN and Bi-LSTM’s model have the highest evaluation values in 7 types of waves scenarios with performance value of sensitivity, precision, specificity, accuracy and F1-Score respectively 98.82%, 98,86%, 99.9%, 99.83%, and 98.84%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Elektrokardiogram, Delineasi, Convolutional Neural Network, Long Short-Term Memory,
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Users 9964 not found.
Date Deposited:	19 Jan 2021 03:00
Last Modified:	19 Jan 2021 03:00
URI:	http://repository.unsri.ac.id/id/eprint/40404

Actions (login required)

View Item