Penerapan Convolutional Neural Network pada Klasifikasi Tanaman Menggunakan ResNet50

KULSUM, UMI (2023) Penerapan Convolutional Neural Network pada Klasifikasi Tanaman Menggunakan ResNet50. S1 thesis, Universitas Mercu Buana Jakarta.

[img]
Preview
Text (COVER)
1. Hal Cover.pdf

Download (950kB) | Preview
[img]
Preview
Text (ABSTRAK)
2. Abstrak.pdf

Download (289kB) | Preview
[img] Text (BAB I)
3. BAB I.pdf
Restricted to Registered users only

Download (436kB)
[img] Text (BAB II)
4. BAB II.pdf
Restricted to Registered users only

Download (486kB)
[img] Text (BAB III)
5. BAB III.pdf
Restricted to Registered users only

Download (412kB)
[img] Text (BAB IV)
6. BAB IV.pdf
Restricted to Registered users only

Download (1MB)
[img] Text (BAB V)
7. BAB V.pdf
Restricted to Registered users only

Download (277kB)
[img] Text (DAFTAR PUSTAKA)
8. Daftar Pustaka.pdf
Restricted to Registered users only

Download (424kB)
[img] Text (LAMPIRAN)
9. Lampiran.pdf
Restricted to Registered users only

Download (2MB)

Abstract

This research aims to classify healthy and rotten plants and develop a desktop-based software that is useful for classifying plant species based on digital images using Convolutional Neural Network (CNN) to determine the type of plant the image belongs to. The training data used consists of 1545 image samples, while the test data used in this study consists of 661 samples. The classification will be performed with two classes: healthy apple leaf images and rotten apple leaf images, using the Convolutional Neural Network (CNN) algorithm with the ResNet50 model. Based on the evaluation results of the model using the Confusion Matrix, an accuracy of 91% was obtained with the training data over 50 epochs. Furthermore, the accuracy results in the desktop-based software only display the selected leaf type, indicating whether it belongs to the healthy or rotten category. Keywords: Convulotional Neural Network, ResNet50, Apple Leaf Penelitian ini bertujuan untuk mengklasifikasikan tanaman sehat dan busuk serta membuat perangkat lunak berbasis desktop yang berguna juga untuk mengklasifikasikan jenis tanaman berdasarkan citra digital menggunakan Convulotional Neural Network untuk mengetahui data gambar termasuk kedalam jenis apa. Data yang digunakan sebagai data latih sebanyak 1545 data gambar. Sedangkan data uji yang digunakan pada penelitian ini sebanyak 661 data. Klasifikasi akan dilakukan dengan dua kelas berupa citra daun apel sehat dan citra daun apel busuk menggunakan algoritma Convolutional Neural Network (CNN) dengan model ResNet50. Berdasarkan hasil evaluasi model dengan Confusion Matrix mendapatkan hasil akurasi 91% dengan data latih pada 50 epoch. Kemudian, hasil akurasi pada perangkat lunak berbasis desktop hanya menampilkan hasil jenis daun yang dipilih yang hasolnya hanya menampilkan daun tersebut termasuk kedalam jenis sehat atau busuuk. Kata Kunci: Convulotional Neural Network, ResNet50, Daun Apel

Item Type: Thesis (S1)
Call Number CD: FIK/INFO. 23 082
NIM/NIDN Creators: 41519010021
Uncontrolled Keywords: Convulotional Neural Network, ResNet50, Daun Apel
Subjects: 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 003 Systems/Sistem-sistem
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 003 Systems/Sistem-sistem > 003.5 Computer Modeling and Simulation/Model dan Simulasi Komputer
100 Philosophy and Psychology/Filsafat dan Psikologi > 150 Psychology/Psikologi > 154 Subconscious and Altered States and Process/Psikologi Bawah Sadar > 154.6 Sleep Phenomena/Fenomena Tidur > 154.63 Dreams/Mimpi > 154.634 Analysis/Analisis
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: CALVIN PRASETYO
Date Deposited: 15 Sep 2023 08:14
Last Modified: 15 Sep 2023 08:14
URI: http://repository.mercubuana.ac.id/id/eprint/80969

Actions (login required)

View Item View Item