Implementasi Algoritma K-Nearest Neighbor (KNN) Untuk Identifikasi Penyakit pada Tanaman Jeruk Berdasarkan Citra Daun

HILMI, ABIYAN NAUFAL (2024) Implementasi Algoritma K-Nearest Neighbor (KNN) Untuk Identifikasi Penyakit pada Tanaman Jeruk Berdasarkan Citra Daun. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 19081010135.-cover.pdf Download (1MB)
	Text (Bab 1) 19081010135.-bab1.pdf Download (445kB)
	Text (`Bab 2) 19081010135.-bab2.pdf Restricted to Repository staff only until 5 June 2028. Download (869kB)
	Text (Bab 3) 19081010135.-bab3.pdf Restricted to Repository staff only until 5 June 2028. Download (600kB)
	Text (Bab 4) 19081010135.-bab4.pdf Restricted to Repository staff only until 5 June 2028. Download (1MB)
	Text (Bab 5) 19081010135.-bab5.pdf Download (392kB)
	Text (Daftar pustaka) 19081010135.-daftarpustaka.pdf Download (383kB)

Abstract

The development of image processing technology today can create systems that are able to effectively recognize digital images, one of which is in the field of agriculture for plant disease identification. In the context of agriculture, especially citrus crops, the need for quality oranges continues to increase, while citrus productivity in Indonesia has decreased due to pest and disease attacks. Diseases that often attack citrus plants include Black Spot, Cancer, and CVPD (Citrus Vein Phloem Degeneration), each of which is caused by a specific pathogen and causes significant damage to the plant, thus requiring disease identification based on image processing. The image processing algorithm that can be utilized to carry out the identification process on diseases that occur in citrus plants through the use of leaf images as a reference is the K-Nearest Neighbor (KNN) algorithm because it is simple and has high accuracy in image management. This research aims to implement and determine the performance of the KNN algorithm in identifying diseases that occur in citrus plants through the use of leaf images as a reference. The best accuracy results were obtained in the research scenario with 90% data splitting for training data and 10% test data, with a value of K = 2 and a random state value of 42 resulting in an accuracy value of 98.5%. The results showed that the KNN algorithm is very effective in identifying citrus plant diseases. The implementation of this technology is expected to support efforts to increase the productivity and quality of citrus plants in Indonesia.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	PUSPANINGRUM, EVA YULIA	NIDN0005078908	evapuspaningrum.if@upnjatim.ac.id
Thesis advisor	WAHANANI, HENNI ENDAH	NIDN0022097811	henniendah@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Abiyan Naufal Hilmi

Date Deposited:

05 Jun 2024 03:23

Last Modified:

05 Jun 2024 03:23

URI:

https://repository.upnjatim.ac.id/id/eprint/24289