Zah Rainy Raushana Kuwada, . (2026) RANCANG BANGUN APLIKASI CNN-MOBILENETV2 MENGGUNAKAN QUANTIZATION UNTUK DETEKSI PENYAKIT PADA PADI. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (224kB) |
|
Text
AWAL.pdf Download (473kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (274kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (863kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (896kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB 5.pdf Restricted to Repository UPNVJ Only Download (253kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (243kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (92kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (34MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
Rice plant diseases are a primary cause of reduced harvest productivity in Indonesia. Farmers' limitations in identifying disease symptoms often result in delayed treatment. This study aims to develop an Android application, AgriScan Padi, utilizing the Convolutional Neural Network (CNN)-MobileNetV2 algorithm to detect diseases based on rice leaf images. The dataset is categorized into eight classes: Blast, Bacterial Leaf Blight, Brown Spot, Leaf Smut, deficiencies in nitrogen (N), phosphorus (P), and potassium (K), and healthy rice. Preprocessing stages include image sharpening, resizing, and data augmentation. The model was trained and evaluated using a confusion matrix, achieving a peak accuracy of 96%. Subsequently, the model was converted to TensorFlow Lite format and integrated into the Android application for offline inference. Black-box testing conducted by agricultural experts demonstrated a 100% success rate across all 11 test scenarios, with an average prediction time of 42.2 ms, confirming the application's capability for rapid and efficient detection.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511163] [Pembimbing 1: Neny Rosmawarni] [Pembimbing 2: Muhammad Panji Muslim] [Penguji 1: Muhammad Adrezo] [Penguji 2: I Wayan Rangga Pinastawa] |
| Uncontrolled Keywords: | Rice Plant, CNN-MobileNetV2, TensorFlow Lite, Android |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software S Agriculture > S Agriculture (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | ZAH RAINY RAUSHANA KUWADA |
| Date Deposited: | 08 Sep 2026 06:28 |
| Last Modified: | 08 Sep 2026 06:28 |
| URI: | http://repository.upnvj.ac.id/id/eprint/52051 |
Actions (login required)
 |
View Item |