Text

DIAGNOSA PENDERITA SKIZOFRENIA MELALUI SINYAL EEG-1D MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK

---

Penilaian

---

Schizophrenia is a mental disorder that generally appears in the form of auditory hallucinations, paranoia, or disorganized speech and thinking. Schizophrenia can be diagnosed using an EEG signal examination. This study conducted a comparative analysis of the best method for classifying EEG using the Deep Learning (DL) method. The author uses the 1D Convolutional Neural Network (1D CNN) method which uses different layers. The first 1D-CNN uses a simple 1D-CNN architecture which has three convolution layers. The second method is a simple CNN architecture which adds a Long short-term memory (LSTM) layer after convolution and the second CNN model is the same as the second model but uses a Gated Recurrent Unit (GRU) layer instead of the LSTM layer. The dataset used is 28 types of EEG signals consisting of 14 Schizophrenia sufferers and 14 normal subjects. The results of testing the accuracy of the F1 Score from CNN using a simple 1D-CNN model have an accuracy value of 86%. The second CNN model with the LSTM layer has a value of 95% and the CNN model using the GRU layer has a value of 96%. Testing of both methods shows that the value of CNN-GRU is greater than 1D-CNN and CNN-LSTM.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207004982	T82209	T822092022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T822092022

Publisher

Inderalaya : Prodi Magister Ilmu Komputer, Fakultas Ilmu Komputer., 2022

Collation

xi, 43 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.650 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jaringan Komunikasi Komputer
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