Maulana, Faris Rajendra (2026) Penerapan CNN Arsitektur MobileNetV2 untuk Deteksi Penyakit Tanaman Bayam pada Sistem Akuaponik SeaRex. Undergraduate thesis, Politeknik Negeri Jember.
![[img]](https://sipora.polije.ac.id/style/images/fileicons/text.png) |
Text (Abstract)
Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (191kB) |
|
Text (Bab 1 Pendahuluan)
Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (213kB) |
|
Text (Daftar Pustaka)
Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (171kB) |
|
Text (Laporan Lengkap)
Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (9MB) | Request a copy |
Abstract
This study aims to develop a smart mobile application based on the MobileNetV2 deep learning architecture for early detection of spinach leaf diseases in aquaponics systems. This approach provides a precision solution to overcome the limitations of slow and subjective manual detection. The image dataset was classified into five classes: Healthy Leaf, Anthracnose, Bacterial Spot, Downy Mildew, and Pest Damage. To handle extreme class imbalance, the model was optimized using Focal Loss (Gamma 2.5), MixUp Augmentation data engineering, and Full Fine-Tuning methods. Model evaluation executed using Test-Time Augmentation (TTA) with 20 iterations yielded an overall accuracy of 70.05%. The model also recorded a high sensitivity (Recall) rate in isolating the majority Healthy Leaf class (87.13%) and the minority Anthracnose class (72.22%). The final model was converted into a TensorFlow Lite (TFLite) format sized under 15 MB, enabling the classification processing to run 100% offline without network latency. The result of this research is a practical decision-support application for farmers to rapidly and accurately identify pathogens and apply targeted organic treatments.
| Item Type: | Thesis (Undergraduate) | ||||||
|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||
| Uncontrolled Keywords: | Akuaponik, Tanaman Bayam, MobileNetV2, Deteksi Penyakit, Aplikasi Mobile, Focal Loss. | ||||||
| Subjects: | 410 - Rumpun Ilmu Teknik > 450 - Teknik Elektro dan Informatika > 458 - Teknik Informatika | ||||||
| Divisions: | Jurusan Teknologi Informasi > Prodi D4 Teknik Informatika (Sidoarjo) > Tugas Akhir | ||||||
| Depositing User: | Faris Rajendra Maulana | ||||||
| Date Deposited: | 20 Jul 2026 00:29 | ||||||
| Last Modified: | 20 Jul 2026 00:30 | ||||||
| URI: | https://sipora.polije.ac.id/id/eprint/58294 |
Actions (login required)
 |
View Item |
