Aura, Vandan Priya (2026) Sistem Deteksi Tingkat Kesegaran Daging Ayam Menggunakan You Only Look Once (YOLO) Berbasis Android. S1 thesis, Universitas PGRI Madiun.
![[img]](https://eprint.unipma.ac.id/style/images/fileicons/text.png) |
Text
Halaman Depan.pdf Download (471kB) |
|
Text
Abstrak.pdf Download (228kB) |
|
Text
BAB I.pdf Download (235kB) |
|
Text
BAB II.pdf Download (720kB) |
|
Text
BAB III.pdf Restricted to Repository staff only Download (368kB) |
|
Text
BAB IV.pdf Restricted to Repository staff only Download (1MB) |
|
Text
BAB V.pdf Download (239kB) |
|
Text
Daftar Pustaka.pdf Download (215kB) |
|
Text
Lampiran.pdf Restricted to Repository staff only Download (358kB) |
Abstract
The determination of chicken meat freshness is generally performed manually through visual observation of its color, texture, and odor. This conventional method relies heavily on individual experience, resulting in subjective and inconsistent assessments. Therefore, this study aims to develop an Android-based chicken meat freshness detection system using the You Only Look Once (YOLOv8n) object detection method. The system was developed using the V-Model software development methodology, which consists of requirement analysis, system design, implementation, and testing. The detection model was trained using 615 images collected from a combination of the Roboflow dataset and images captured by the researcher through Google Colaboratory. The trained model was subsequently converted into the TensorFlow Lite format for implementation in an Android application capable of performing real-time detection. The model performance was evaluated using Precision, Recall, F1-Score, mean Average Precision (mAP50), and mAP50-95 metrics. The experimental results demonstrated that the model achieved a Precision of 97,62%, Recall of 97,62%, F1-Score of 97,62%, mAP50 of 97.50%, and mAP50-95 of 95.15%. The developed application is capable of detecting chicken meat freshness quickly and accurately, displaying the detection results along with the model confidence score, and storing detection history. Based on the testing results, the proposed system can assist users in identifying the freshness level of chicken meat in a practical and efficient manner using Android devices.
| Item Type: | Thesis/Skripsi/Tugas Akhir (S1) |
|---|---|
| Kata Kunci: | Chicken Meat Freshness Detection; YOLO; Android; Digital Image Processing. |
| Subjects: | T Technology > T Technology (General) |
| Divisions: | Fakultas Teknik > Teknik Informatika |
| Depositing User: | VANDAN PRIYA AURA |
| Date Deposited: | 19 Aug 2026 04:01 |
| Last Modified: | 19 Aug 2026 04:01 |
| URI: | http://eprint.unipma.ac.id/id/eprint/8483 |
Actions (login required)
 |
View Item |
