Text

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

---

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

---

Availability

Detail Information

Series Title

-

Call Number

T935822023

Publisher

Inderalaya : Prodi Magister Ilmu Komputer, Fakultas Ilmu Komputer., 2023

Collation

xiv, 64 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.507

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem Pakar
Prodi Magister Ilmu Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment