RANCANG BANGUN APLIKASI PENDETEKSI PENYAKIT PADI MENGGUNAKAN ALGORITMA EFFICIENTNETV2-S BERBASIS ANDROID

Bara Rifqi Ath Thoriq, . (2025) RANCANG BANGUN APLIKASI PENDETEKSI PENYAKIT PADI MENGGUNAKAN ALGORITMA EFFICIENTNETV2-S BERBASIS ANDROID. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (11kB)
[img] Text
AWAL.pdf
Download (322kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (184kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (709kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (205kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (667kB)
[img] Text
BAB 5.pdf
Download (176kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (143kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (172kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (583kB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (433kB)

Abstract

Rice plant diseases are one of the major factors contributing to decreased crop yields in Indonesia. Farmers often struggle to recognize disease symptoms, leading to delays in proper treatment. This study aims to develop an Android-basesd rice disease detection application using the EfficientNetV2-S algorithm to classify disease type based on rice leaf images. The research stages include data collection of rice leaf images from five classes:Bacterial Leaf Blight, Blast, Brown Spot, Tungro, and Healthy. The collected data underwent preprocessing, including image sharpening, resizing, and augmentation, to enhance dataset variation. The EfficientNetV2-S model was then designed,trained, and evaluated using the Confusion matrix, achieving an accuracy of 89%. Furthemore, system requirements analysis and application interface design were carried out using the UML approach and designed in Figma. The trained model was converted into TensorFlow Lite (TFLite) format and integrated into Android Application, allowing local inference on mobile device. The implemented application includes key feature such as disease diagnosis, a disease encyclopedia, and prediction recordd storage. Black-box Testing was conducted by a agricultural extension staff from Agro Edu Wisata (AEW) Ragunan. The developed application performs efficiently with an average prediction speed of approximately one second.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 2010511088] [Pembimbing 1: Tjahjanto] [Pembimbing 2: Novi Trisman Hadi] [Penguji 1: Neny Rosmawarni] [Penguji 2: Nurul Afifah Arifuddin]
Uncontrolled Keywords: EfficientNetV2-S, TensorFlow Lite, Rice Disease Detection, Android, Deep Learning
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: BARA RIFQI ATH THORIQ
Date Deposited: 17 Mar 2026 02:15
Last Modified: 17 Mar 2026 02:15
URI: http://repository.upnvj.ac.id/id/eprint/42424

Actions (login required)

View Item View Item