MUKTI, REZA SATIA (2026) KLASIFIKASI JENIS PENYAKIT TOMAT DAN KENTANG MENGGUNAKAN METODE CONVOLUTION NEUTRAL NETWORK BERBASIS ANDROID. S1 thesis, Universitas PGRI Madiun.
![[img]](https://eprint.unipma.ac.id/style/images/fileicons/text.png) |
Text
HALAMAN DEPAN ( COVER DEPAN sd DAFTAR LAMPIRAN).pdf Download (546kB) |
|
Text
ABSTRAK (INDONESIA & INGGRIS).pdf Download (194kB) |
|
Text
BAB 1.pdf Download (196kB) |
|
Text
BAB 2.pdf Download (573kB) |
|
Text
BAB 3.pdf Restricted to Repository staff only Download (306kB) |
|
Text
BAB 4.pdf Restricted to Repository staff only Download (1MB) |
|
Text
BAB 5.pdf Download (179kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (162kB) |
|
Text
LAMPIRAN - LAMPIRAN.pdf Restricted to Repository staff only Download (2MB) |
Abstract
Indonesia is an agrarian country in which tomato and potato are important horticultural commodities, yet their productivity is frequently threatened by various plant diseases. Manual disease identification requires specific expertise, is time-consuming, and is prone to error. This study aims to design and develop an Android-based application to classify the types of tomato and potato leaf diseases using the Convolutional Neural Network (CNN) method. The model was built by applying transfer learning to the MobileNetV2 architecture that had been pre-trained on the ImageNet dataset, and was then fine-tuned using an image dataset of 10,588 images divided into 9 classes. The dataset was split into 80% training data (8,471 images) and 20% validation data (2,117 images). The trained model was converted into the TensorFlow Lite format so that it could run offline on Android devices. The application was developed using the Rapid Application Development (RAD) method, while testing was carried out through functional testing and usability testing using the System Usability Scale (SUS). The results show that the model achieved an accuracy of 99.58% with a macro F1-score of 0.99 in classifying 9 classes. Functional testing showed that all application features worked as required, while usability testing obtained a SUS score of 83.00, which falls into the acceptable category with grade A (excellent). Thus, the developed application can serve as an accurate and easy-to-use tool for the early identification of tomato and potato plant diseases.
| Item Type: | Thesis/Skripsi/Tugas Akhir (S1) |
|---|---|
| Kata Kunci: | Convolutional Neural Network; MobileNetV2; transfer learning; plant disease classification; Android; System Usability Scale |
| Subjects: | Q Science > Q Science (General) S Agriculture > S Agriculture (General) S Agriculture > SB Plant culture T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General) |
| Divisions: | Fakultas Teknik > Teknik Informatika |
| Depositing User: | MUKTI SATIA REZA |
| Date Deposited: | 20 Oct 2026 02:27 |
| Last Modified: | 20 Oct 2026 02:27 |
| URI: | http://eprint.unipma.ac.id/id/eprint/10438 |
Actions (login required)
 |
View Item |
