Edwina Martha Putri, . (2026) PERANCANGAN APLIKASI MOBILE UNTUK KLASIFIKASI JENIS IKAN KONSUMSI DI INDONESIA MENGGUNAKAN ARSITEKTUR MOBILENETV2. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (171kB) |
|
Text
AWAL.pdf Download (716kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (278kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (713kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (664kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB V.pdf Download (260kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (245kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (117kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (13MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (627kB) |
Abstract
The lack of understanding amongst the general public in Indonesia, as well as difficulties in identifying edible fish species, still occur frequently, in particular with fish that look similar. This study aims to develop an Android application to classify nine types of edible fish in Indonesia and provide dietary information for each fish. The classification model was developed using the MobileNetV2 architecture with a transfer learning approach on 2,700 images. The application was developed using the Rapid Application Development method through the stages of requirements planning, system design, development, and implementation. The model was converted to the TensorFlow Lite format using dynamic range quantization and integrated into a Java-based application with a Model-View-ViewModel architecture to enable offline inference. Test results showed that the model achieved an accuracy of 92.96% on 270 test data. The application achieved an average classification time of 85.57 ms on the test device. All 18 black-box testing scenarios were successfully passed, while User Acceptance Testing (UAT) achieved an acceptance rate of 90.6%, which was rated as “very good.” These results indicate that the application successfully integrates MobileNetV2 for offline fish classification, meets its primary functional requirements, and has received positive feedback from users.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511072] [Pembimbing 1: Indra Permana Solihin] [Pembimbing 2: Nurul Afifah Arifuddin] [Penguji 1: Widya Cholil] [Penguji 2: Muhammad Panji Muslim] |
| Uncontrolled Keywords: | Android, Edible Fish Classification, MobileNetV2, Rapid Application Development, TensorFlow Lite |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | EDWINA MARTHA PUTRI |
| Date Deposited: | 04 Aug 2026 07:54 |
| Last Modified: | 04 Aug 2026 07:55 |
| URI: | http://repository.upnvj.ac.id/id/eprint/52151 |
Actions (login required)
 |
View Item |