Malique Abdul Aziz, . (2025) DETEKSI DINI SKOLIOSIS SECARA REAL-TIME PADA TUBUH MANUSIA MENGGUNAKAN YOLO. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (253kB) |
|
Text
AWAL.pdf Download (567kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (275kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (902kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (347kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB 5.pdf Download (255kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (262kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (153kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (543kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (18MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (829kB) |
Abstract
This study was conducted because idiopathic scoliosis often goes undetected at an early stage due to limited access to medical examinations and a general lack of public awareness regarding abnormal body posture. The research aims to develop a real-time early detection system for scoliosis based on the YOLOv8n-Pose algorithm and implement it into an Android application. YOLOv8n-Pose was selected for its ability to perform object detection while simultaneously estimating human pose through keypoints. A total of 102 images were collected through data scraping using the Bing Search API, followed by preprocessing and augmentation, resulting in 218 images. The model was trained using a dataset of 218 back view images, classified into two categories: normal and abnormal. Evaluation results showed that the model could effectively detect scoliosis from the spinal line, achieving a satisfactory accuracy with an mAP@0.5 of 0.958 and an mAP@0.5:0.95 of 0.727. The trained model was then integrated into an Android application using Flutter and TensorFlow Lite, enabling real-time scoliosis detection directly through the smartphone camera. The application displays a visualization of the spinal line and scoliosis detection based on pose estimation, providing users with an accessible tool for early screening before consulting a medical expert.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2110511044] [Pembimbing 1: Widya Cholil] [Pembimbing 2: Neny Rosmawarni] [Penguji 1: Nur Hafifah Matondang] [Penguji 2: Muhammad Panji Muslim] |
| Uncontrolled Keywords: | Scoliosis, YOLOv8n-Pose, Real-Time Detection, Pose Estimation, 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: | MALIQUE ABDUL AZIZ |
| Date Deposited: | 13 Jul 2025 04:36 |
| Last Modified: | 21 Jul 2025 08:11 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37491 |
Actions (login required)
 |
View Item |