Dimara, Denis Lizard Sambawo (2025) KLASIFIKASI PENYAKIT DAUN PADI MENGGUNAKAN MOBILENET DAN SUPPORT VECTOR MACHINE BERBASIS ANDROID. Undergraduate thesis, UPN Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (COVER)
21081010159_Cover Skripsi Fixxx.pdf Download (1MB) |
|
Text (BAB 1)
21081010159_BAB 1.pdf Download (225kB) |
|
Text (BAB 2)
21081010159_BAB 2.pdf Restricted to Repository staff only until 19 June 2028. Download (1MB) |
|
Text (BAB 3)
21081010159_BAB 3.pdf Restricted to Repository staff only until 19 June 2028. Download (1MB) |
|
Text (BAB 4)
21081010159_BAB 4.pdf Restricted to Repository staff only until 19 June 2028. Download (1MB) |
|
Text (BAB 5)
21081010159_BAB 5.pdf Download (219kB) |
|
Text (DAFTAR PUSTAKA)
21081010159_DAFTAR PUSTAKA.pdf Download (203kB) |
|
Text (LAMPIRAN)
21081010159_LAMPIRAN.pdf Restricted to Repository staff only until 19 June 2028. Download (678kB) |
Abstract
Rice, as a key commodity in Indonesian agriculture, is vulnerable to diseases such as Brownspot, BacterialBlight, Blast, and Tungro, which can significantly reduce crop yields. Manual disease identification by farmers is often inefficient and prone to errors. This study develops a rice leaf disease Classification system using a hybrid approach of MobilenetV3Small and Support Vector Machine (SVM) based on Android. Parameter Tuning with a Linear kernel and a C parameter value of 0.1 resulted in an accuracy of 99.66%, higher than the initial 98.87% before Tuning. The Data splitting of 70% for training, 15% for validation, and 15% for testing gave the best results compared to other data splits.. Model evaluation shows that the MobilenetV3Small-SVM combination outperforms the MobilenetV3Small model (99.43%) and SVM (94.90%) with an accuracy of 99.66%. A decrease in accuracy after Deployment on the Android platform highlights the importance of broader data representation during training to improve performance in real-world scenarios. This study is expected to contribute to the development of an Android application that helps farmers identify rice leaf diseases quickly and accurately, thereby enhancing efficiency and agricultural productivity.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T385 Computer Graphics |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Informatics | ||||||||||||
| Depositing User: | DENIS DIMARA | ||||||||||||
| Date Deposited: | 19 Jun 2025 03:22 | ||||||||||||
| Last Modified: | 19 Jun 2025 03:22 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/38617 |
Actions (login required)
 |
View Item |