KLASIFIKASI PENYAKIT DAUN PADA POHON APEL DENGAN CNN DAN ARSITEKTUR VGG16

Azy Umardi Azhra, . (2023) KLASIFIKASI PENYAKIT DAUN PADA POHON APEL DENGAN CNN DAN ARSITEKTUR VGG16. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

	Text ABSTRAK.pdf Download (79kB)
	Text AWAL.pdf Download (906kB)
	Text BAB I.pdf Download (99kB)
	Text BAB II.pdf Restricted to Repository UPNVJ Only Download (790kB)
	Text BAB III.pdf Restricted to Repository UPNVJ Only Download (257kB)
	Text BAB IV.pdf Restricted to Repository UPNVJ Only Download (5MB)
	Text BAB V.pdf Download (79kB)
	Text DAFTAR PUSTAKA.pdf Download (90kB)
	Text DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (91kB)
	Text LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (4MB)
	Text HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (118kB)
	Text ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB)

Abstract

The Apple tree is one of the trees that produces seasonal or yearly fruits. Accurate identification of apple leaf diseases is crucial for controlling the spread of diseases and ensuring the healthy and stable development of the apple industry. The aim of this research is to develop a model and web application that can be used by users to predict diseases on apple leaves. In the implementation or development of the model, one of the deep learning technologies that excels in Computer Vision, specifically object classification in images, is used. The method used for image classification is Convolutional Neural Network (CNN) and the VGG16 architecture, which also utilizes Transfer Learning. The result of this research is a web-based image classification model for apple leaf diseases, which aims to assist apple tree farmers in predicting or anticipating apple leaf diseases. The highest accuracy achieved is 90.016% at epoch 100, and the lowest loss is 0.2434 at epoch 100. However, the validation accuracy and validation loss are far from the training accuracy and validation accuracy. The best validation accuracy of 80.74% is obtained at epoch 76, while the validation loss is significantly high. The highest validation loss of 2.5912 occurs at epoch 86. Despite the model experiencing overfitting, it is still excellent at predicting rust disease, as it achieves an accuracy of 96% in direct experiments with apple leaf images provided by apple farmers. Additionally, it achieves 100% accuracy for the healthy class.

Item Type:	Thesis (Skripsi)
Additional Information:	[No. Panggil : 1910511028] [Pembimbing : Yuni Widiastiwi] [Penguji 1 : Henki Bayu Seta] [Penguji 2 : Helena Nurramdhani Irmanda]
Uncontrolled Keywords:	Apple Leaf Diseases, Classification, CNN, VGG16, Flask
Subjects:	Q Science > QK Botany T Technology > T Technology (General)
Divisions:	Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User:	Azy Umardi Azhra
Date Deposited:	10 Aug 2023 06:25
Last Modified:	10 Aug 2023 06:25
URI:	http://repository.upnvj.ac.id/id/eprint/25111

Actions (login required)

View Item