Andes Kurnia, . (2026) PERANCANGAN APLIKASI ANDROID UNTUK KLASIFIKASI KESEGARAN IKAN MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK (CNN) BERBASIS MOBILENETV2. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (147kB) |
|
Text
AWAL.pdf Download (467kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (220kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (978kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
BAB 5.pdf Download (154kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (186kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (111kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (140kB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (294kB) |
Abstract
Fish freshness is an important indicator in determining the quality, safety, and economic value of fishery products. Visual assessment of fish freshness still depends on the observer's experience, which may lead to inconsistent evaluation results. This study aims to develop an Android-based application for identifying the freshness of mackerel tuna (Euthynnus affinis) using the Convolutional Neural Network (CNN) method with the MobileNetV2 architecture. The dataset consisted of 360 images of mackerel tuna eyes, comprising 180 fresh fish images and 180 non-fresh fish images. The research stages included dataset splitting, image preprocessing through resizing to 224 × 224 pixels, normalization, data augmentation, and model training using a Transfer Learning approach. The trained model was converted into the TensorFlow Lite (TFLite) format and integrated into an Android application, enabling image classification directly on the mobile device without requiring an internet connection. The experimental results showed that the proposed model achieved an accuracy of 91.67%, precision of 89.47%, recall of 94.44%, and an F1-score of 91.89%. Furthermore, Black Box Testing demonstrated that all primary application functions operated as expected. The results indicate that the MobileNetV2 model is capable of effectively classifying the freshness of mackerel tuna and has been successfully implemented in an Android application as a fast, practical, consistent, and objective decision-support tool for fish freshness identification.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511029] [Pembimbing 1: Widya Cholil] [Pembimbing 2: Nur Hafifah Matondang] [Penguji 1: Ruth Mariana Bunga Wadu] [Penguji 2: Kharisma Wiati Gusti] |
| Uncontrolled Keywords: | Keywords: Fish Freshness Classification, Convolutional Neural Network, MobileNetV2, Transfer Learning, TensorFlow Lite, Android. |
| Subjects: | Q Science > QA Mathematics Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | ANDES KURNIA |
| Date Deposited: | 31 Aug 2026 14:58 |
| Last Modified: | 31 Aug 2026 15:05 |
| URI: | http://repository.upnvj.ac.id/id/eprint/52642 |
Actions (login required)
 |
View Item |