KLASIFIKASI PENYAKIT DAUN APEL DENGAN EFFICIENTNET V2 BERBASIS FLASK DAN SVELTEKIT

Fuji Santoso, Sri (2025) KLASIFIKASI PENYAKIT DAUN APEL DENGAN EFFICIENTNET V2 BERBASIS FLASK DAN SVELTEKIT. Undergraduate thesis, UPN Veteran Jawa Timur.

	Text (Cover) 20081010184.-cover.pdf Download (2MB)
	Text (BAB I) 20081010184.-bab1.pdf Download (21kB)
	Text (BAB II) 20081010184.-bab2.pdf Restricted to Repository staff only until 5 February 2027. Download (844kB)
	Text (BAB III) 20081010184.-bab3.pdf Restricted to Repository staff only until 5 February 2027. Download (281kB)
	Text (BAB IV) 20081010184.-bab4.pdf Restricted to Repository staff only until 5 February 2027. Download (1MB)
	Text (BAB V) 20081010184.-bab5.pdf Download (81kB)
	Text (Daftar Pustaka) 20081010184.-daftarpustaka.pdf Download (83kB)

Abstract

The apple farming industry faces challenges in managing apple leaf diseases. The current manual detection methods have several weaknesses, including dependence on variable human expertise, time-consuming processes, potential delays in identification that can result in more widespread disease spread, and difficulty distinguishing between disease types with similar visual symptoms. Therefore, this research aims to develop an accurate, efficient, and automated apple leaf disease classification system using a hybrid approach that combines the EfficientNet V2 architecture and Vision Transformer. The main objectives are to improve disease detection accuracy, reduce required computation, facilitate more effective crop management, and support modern agricultural practices in the apple industry. Experimental results demonstrate the effectiveness of this method in classifying apple leaf diseases with an accuracy rate of 98.35% and an F1 score of 0.9835 on test data, having 18.5 million parameters which is lighter than the original EfficientNetV2S model with 20 million parameters, and requiring a faster training time of 6 minutes compared to the original EfficientNetV2S model which needs 8 minutes of training time for 6 epochs on the same dataset.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Diyasa, I Gede Susrama Mas	NIDN0019067008	igsusrama.if@upnjatim.ac.id
Thesis advisor	Nugroho, Budi	NIDN0707098003	budinugroho.if@upnjatim.ac.id

Subjects:

Q Science > QA Mathematics > QA76.6 Computer Programming

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

Fuji Fuji Fujji

Date Deposited:

05 Feb 2025 04:33

Last Modified:

05 Feb 2025 04:33

URI:

https://repository.upnjatim.ac.id/id/eprint/34623