Skripsi

DETEKSI PENYAKIT PADA TANAMAN MANGGA BERDASARKAN CITRA DAUN DENGAN ALGORITMA YOLO11 BERBASIS ANDROID

---

Healthy and diseased mango plants are difficult to distinguish at early stages due to insignificant differences in leaf color, texture, and spot patterns, which often leads to delayed identification and results in decreased mango production and fruit quality. This study develops an Android-based application to detect diseases in mango plants based on leaf images using the YOLO11 algorithm. The dataset consists of 1,405 images of Harum Manis mango leaves categorized into three classes: two disease classes (Anthracnose and Sooty Mould) and one healthy class. Experiments were conducted using the YOLO11n variant with hyperparameter variations including batch sizes of 16 and 24, 50 epochs, a learning rate of 0.01, Adam and SGD optimizers, and a patience value of 10. Based on validation results, the scenario using the SGD optimizer with a batch size of 16 achieved the best performance, with precision of 0.989, recall of 0.992, F1-score of 0.991, accuracy of 0.981, mAP50 of 0.995, and mAP50-95 of 0.918. On the testing dataset, the model achieved high performance, with a precision of 0.993, recall of 0.983, F1-score of 0.988, accuracy of 0.990, mAP50 of 0.995, and mAP50-95 of 0.917. These results indicate that the proposed model is capable of accurately detecting mango leaf diseases and is effective for automatic disease detection through an Android application.

---

Availability

Detail Information

Series Title

-

Call Number

T1950952026

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xiv, V-14 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.180 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Prodi Teknik Informatika
YOLO11

Specific Detail Info

-

Statement of Responsibility

KA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment