ANALISIS PERBANDINGAN METODE CNN-LSTM-GRU DALAM DIAGNOSIS PASIEN SKIZOFRENIA BERDASARKAN DATA EEG 2D

FIRMANSYAH, FIRMANSYAH and Dian Palupi Rini, Dian and Sukemi, Sukemi (2018) ANALISIS PERBANDINGAN METODE CNN-LSTM-GRU DALAM DIAGNOSIS PASIEN SKIZOFRENIA BERDASARKAN DATA EEG 2D. Masters thesis, Sriwijaya University.

	Text RAMA_55101_09042681822007.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55101_09042681822007_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55101_09042681822007_0023027804_0003126604_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (436kB)
	Text RAMA_55101_09042681822007_0023027804_0003126604_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (372kB) | Request a copy
	Text RAMA_55101_09042681822007_0023027804_0003126604_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (377kB) | Request a copy
	Text RAMA_55101_09042681822007_0023027804_0003126604_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (526kB) | Request a copy
	Text RAMA_55101_09042681822007_0023027804_0003126604_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (54kB) | Request a copy
	Text RAMA_55101_09042681822007_0023027804_0003126604_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (98kB) | Request a copy
	Text RAMA_55101_09042681822007_0023027804_0003126604_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

Schizophrenia (SZ) is a brain disease with a chronic condition that affects the ability to think. Common symptoms that are often seen in this disorder are hallucinations, delusions, abnormal behavior, speech disorders, and mood disorders. Schizophrenic patients can be diagnosed using electroencephalography (EEG) signals. This study conducted a comparative analysis of which method is best in EEG classification using the Deep Learning (DL) method. The author uses the 2D Convolutional Neural Network (2D-CNN) method which uses different layers. The first 2D-CNN uses a Long Short-Term memory (LSTM) layer and a Gate Recurrent Unit (GRU). The dataset used consists of two types of EEG signals obtained from 39 healthy individuals and 45 schizophrenic patients during resting state respectively. Test results for the accuracy of the F1 score from 5 times testing the CNN method using the LSTM layer has the best accuracy value of 94.12% and 5 times testing the CNN method using the GRU layer has the best accuracy value of 94.12%. The results of testing the two methods show that the accuracy results of the CNN-LSTM method are better than CNN-GRU. Keywords: skizofrenia, elektroensefalografi, deep learning, convolutional neural network, gated recurrent unit, long short-term memory

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	METODE CNN-LSTM-GRU
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. Q Science > Q Science (General) > Q350-390 Information theory
Divisions:	09-Faculty of Computer Science > 55101-Informatics (S2)
Depositing User:	Firmansyah Firman
Date Deposited:	06 Apr 2023 03:16
Last Modified:	06 Apr 2023 03:16
URI:	http://repository.unsri.ac.id/id/eprint/93582

Actions (login required)

View Item