Klasifikasi Penyakit pada Tanaman Kacang Tanah Berdasarkan Citra Daun Menggunakan Model Hibrida EfficientNet-B2 dan Extreme Gradient Boosting

Rohman, Safiqur (2025) Klasifikasi Penyakit pada Tanaman Kacang Tanah Berdasarkan Citra Daun Menggunakan Model Hibrida EfficientNet-B2 dan Extreme Gradient Boosting. Undergraduate thesis, Universitas Pembangunan Nasional "Veteran" Jawa Timur.

	Text (Cover) Cover.pdf Download (393kB)
	Text (Bab 1) BAB 1_removed.pdf Download (88kB)
	Text (Bab 2) BAB 2.pdf Restricted to Repository staff only until 5 December 2027. Download (349kB)
	Text (Bab 3) BAB 3_removed.pdf Restricted to Repository staff only until 5 December 2027. Download (373kB)
	Text (Bab 4) BAB 4_removed.pdf Restricted to Repository staff only until 5 December 2027. Download (577kB)
	Text (Bab 5) BAB 5_removed.pdf Download (13kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf Download (73kB)
	Text (Lampiran) Lapiran.pdf Restricted to Repository staff only until 2027. Download (59kB)

Abstract

Peanut (Arachis hypogaea L.) is one of the main food commodities in Indonesia that is frequently affected by various leaf diseases. The manual identification process still relies heavily on expert knowledge and requires a considerable amount of time. Therefore, this study proposes an image-based classification system using a hybrid model combining EfficientNet-B2 and Extreme Gradient Boosting (XGBoost). In this system, EfficientNet-B2 functions as a feature extractor to obtain deep and efficient visual representations, while XGBoost serves as a classifier to enhance the accuracy and stability of the classification results. The dataset used in this research consists of two sources local (mandiri) and Kaggle each representing five classes of peanut leaves. The research includes data splitting, preprocessing, feature extraction, and classification with hyperparameter optimization. Experimental results show that the proposed hybrid model achieved the best accuracy of 89.69% on the local dataset and 97.02% on the Kaggle dataset, with precision, recall, and F1-score values exceeding 0.89 and 0.96, respectively. The model also demonstrates strong generalization capability. Overall, the combination of EfficientNet-B2 and XGBoost proves to be effective in classifying peanut leaf diseases.

Item Type:

Thesis (Undergraduate)

Contributors:

Contribution	Contributors	NIDN/NIDK	Email
Thesis advisor	Puspaningrum, Eva Yulia	NIDN0005078908	evapuspaningrum.if@upnjatim.ac.id
Thesis advisor	Rahajoe, R.r Ani Dijah	NIDN0012057301	anidijah.if@upnjatim.ac.id

Subjects:

T Technology > T Technology (General)

Divisions:

Faculty of Computer Science > Departemen of Informatics

Depositing User:

safiqur rohman safi

Date Deposited:

05 Dec 2025 08:15

Last Modified:

05 Dec 2025 08:42

URI:

https://repository.upnjatim.ac.id/id/eprint/48087