Karenina Nurmelita Malik, . (2026) IMPLEMENTASI YOLOv8 DALAM DETEKSI DINI GEJALA ANEMIA PADA REMAJA PEREMPUAN BERBASIS ANDROID. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
|
Text
ABSTRAK.pdf Download (218kB) |
|
|
Text
AWAL.pdf Download (663kB) |
|
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (286kB) |
|
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (611kB) |
|
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (587kB) |
|
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (1MB) |
|
|
Text
BAB 5.pdf Download (230kB) |
|
|
Text
DAFTAR PUSTAKA.pdf Download (247kB) |
|
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (129kB) |
|
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (31MB) |
|
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (464kB) |
Abstract
Anemia is a prevalent health issue among adolescent girls, yet invasive clinical examinations are often feared and impractical. This study develops "Palepal", an Android application for non-invasive early anemia detection. The application analyzes images of the palm, eye conjunctiva, and fingernails using a YOLOv8-based Convolutional Neural Network (CNN). The Perceptual Hashing (pHash) algorithm is applied during preprocessing to prevent data leakage. Final diagnostic decisions utilize a Weighted Decision Fusion algorithm (conjunctiva 60%, palm 20%, fingernails 20%) to minimize false positives. The system integrates Image Quality Assessment (IQA) and Sequential Model Loading to prevent mobile device memory leaks. Evaluation results demonstrate the palm model achieved the highest accuracy at 94.92%, followed by the conjunctiva (78.80%) and fingernails (72.15%). Functionality testing (black-box) recorded a 78.57% success rate, while the User Acceptance Test (UAT) involving students and medical experts scored 86.11% (Highly Feasible). In conclusion, Palepal is an effective and practical early screening alternative to enhance adolescents' awareness of anemia indications.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511089] [Pembimbing: Neny Rosmawarni] [Penguji 1: Widya Cholil] [Penguji 2: Anis Fitri Nur Masruriyah] |
| Uncontrolled Keywords: | Anemia, Non-invasive, Early Detection, YOLOv8, Android Application |
| 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: | KARENINA NURMELITA MALIK |
| Date Deposited: | 04 Sep 2026 08:24 |
| Last Modified: | 04 Sep 2026 08:24 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51666 |
Actions (login required)
![]() |
View Item |
