ANALISA CITRA HASIL POTRET DADA UNTUK DIAGNOSA COVID-19 MENGGUNAKAN DEPTHWISE SEPARABLE CONVOLUTIONAL NEURAL NETWORK

SUYASMINI, KADEK DWI (2021) ANALISA CITRA HASIL POTRET DADA UNTUK DIAGNOSA COVID-19 MENGGUNAKAN DEPTHWISE SEPARABLE CONVOLUTIONAL NEURAL NETWORK. S1 thesis, Universitas Mercu Buana Jakarta.

[img]
Preview
Text (HAL COVER)
01 Cover.pdf

Download (155kB) | Preview
[img] Text (BAB I)
02 Bab 1.pdf
Restricted to Registered users only

Download (37kB)
[img] Text (BAB II)
03 Bab 2.pdf
Restricted to Registered users only

Download (182kB)
[img] Text (BAB III)
04 Bab 3.pdf
Restricted to Registered users only

Download (216kB)
[img] Text (BAB IV)
05 Bab 4.pdf
Restricted to Registered users only

Download (231kB)
[img] Text (BAB V)
06 Bab 5.pdf
Restricted to Registered users only

Download (24kB)
[img] Text (DAFTAR PUSTAKA)
07 Daftar Pustaka.pdf
Restricted to Registered users only

Download (35kB)
[img] Text (LAMPIRAN)
08 Lampiran.pdf
Restricted to Registered users only

Download (108kB)

Abstract

In September 2019 the corona virus began to spread in the Wuhan area, China. Chest radiography is an imaging method that can be used to assess the chest and is the most common medical imaging study in the world. In this final project, the convolution network will be used to detect the severity of COVID-19 which can damage the lungs and cause pneumonia in sufferers. This method is used to facilitate medical personnel in making a diagnosis. Considering the increasing number of Covid-19 cases, especially in Indonesia, especially Java Island. Comparing several CNN models that have been sold such as vgg16, alexnet, and resnet50 and using a model with a depthwise separable convolutional neural network. The depthwise separable convolutional neural network model is expected to reduce the time for the model training process. From the test results obtained that this model has the highest accuracy can be seen from the number of images that can be classified correctly in the testing process, namely 86 images, 60 images alexnet, 57 images vgg16, 50 82 images resnet, and 85 images CNN13. Keywords: Convolution, covid-19, chest portrait, Model, deep learning Pada September 2019 virus corona mulai merebak di daerah Wuhan, Tiongkok. Radiografi dada adalah metode pencitraan yang umum digunakan yang dapat digunakan untuk menilai dada dan merupakan studi pencitraan medis paling umum di dunia. Pada tugas akhir ini jaringan konvolusi akan dimanfaatkan untuk mendeteksi tingkat keparahan dari covid-19 yang dapat merusak paru-paru hingga menyebabkan pneumonia pada penderitanya. Metode ini digunakan untuk memudahkan tenaga medis dalam melakukan diagnosa. Mengingat banyaknya kenaikan kasus covid-19 terutama di Indonesia khususnya Pulau Jawa. Membandingkan beberapa model CNN yang sudah terlatih seperti vgg16, alexnet, dan resnet50 serta menggunakan model dengan depthwise separable convolutional neural network. Model depthwise separable convolutional neural network ini diharapkan akan mengurangi waktu untuk proses pelatihan model. Dari hasil pengujian diperoleh bahwa model ini memiliki keakurasian yang paling tinggi dapat dilihat dari jumlah gambar yang dapat diklasifikasikan dengan benar pada proses pengujian yaitu sebanyak 86 gambar, alexnet 60 gambar, vgg16 57 gambar, resnet 50 82 gambar, dan CNN13 85 gambar. Kata Kunci: Konvolusi, covid-19, potret dada, Model, deep learning.

Item Type: Thesis (S1)
NIM/NIDN Creators: 41419120060
Uncontrolled Keywords: Konvolusi, covid-19, potret dada, Model, deep learning.
Subjects: 600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan
600 Technology/Teknologi > 620 Engineering and Applied Operations/Ilmu Teknik dan operasi Terapan > 621 Applied Physics/Fisika terapan
Divisions: Fakultas Teknik > Teknik Elektro
Depositing User: Dede Muksin Lubis
Date Deposited: 30 Oct 2023 02:24
Last Modified: 30 Oct 2023 02:24
URI: http://repository.mercubuana.ac.id/id/eprint/83501

Actions (login required)

View Item View Item