Al'Afaf, Banie (2025) Implementasi Algoritma Convolutional Neural Network (CNN) untuk klasifikasi posisi tidur manusia berbasis citra. Sarjana thesis, UIN Sunan Gunung Djati Bandung.
|
Text (COVER)
1_cover.pdf Download (156kB) | Preview |
|
|
Text (ABSTRAK)
2_abstrak.pdf Download (196kB) | Preview |
|
|
Text (LEMBAR PERNYATAAN)
F.29 Form Surat Pernyataan Karya Sendiri.pdf Download (296kB) | Preview |
|
|
Text (DAFTAR ISI)
4_daftarisi.pdf Download (246kB) | Preview |
|
|
Text (BAB I)
5_bab1.pdf Download (256kB) | Preview |
|
![[img]](https://digilib.uinsgd.ac.id/style/images/fileicons/text.png) |
Text (BAB II)
6_bab2.pdf Restricted to Registered users only Download (579kB) | Request a copy |
|
|
Text (BAB III)
7_bab3.pdf Restricted to Registered users only Download (643kB) | Request a copy |
|
|
Text (BAB IV)
8_bab4.pdf Restricted to Registered users only Download (2MB) | Request a copy |
|
|
Text (BAB V)
9_bab5.pdf Restricted to Registered users only Download (237kB) | Request a copy |
|
|
Text (DAFTAR PUSTAKA)
10_daftarpustaka.pdf Restricted to Registered users only Download (214kB) | Request a copy |
|
|
Text (LAMPIRAN)
11_lampiran (8).pdf Restricted to Repository staff only Download (829kB) | Request a copy |
Abstract
Sleep is an important biological need for humans, and sleeping position has a significant impact on sleep quality and health. This study aims to develop a non-invasive and affordable human sleeping position classification system using static RGB images based on the Convolutional Neural Network (CNN) algorithm. The dataset used is from the IEEE VIP Cup 2021, which consists of three sleeping position classes: supine, left side, and right side. Two custom CNN architectures, CNN3 and CNN4, were tested with two data splitting ratios (80:20 and 70:30). Evaluation results showed that the CNN3 model with an 80:20 ratio achieved the best performance with a test accuracy of 98.57% and average precision, recall, and F1-score values of 0.99. The best model was then implemented into a prototype system based on Flask API and an Android application capable of offline/semi-real-time classification. The prototype testing results demonstrated that the system can function end-to-end as a proof of concept for sleep position monitoring using common devices such as smartphones.
| Item Type: | Thesis (Sarjana) |
|---|---|
| Uncontrolled Keywords: | Convolutional Neural Network; Sleep Position Classification; RGB image; Computer Vision; Deep Learning; Flask API; Android |
| Subjects: | Data Processing, Computer Science Special Computer Methods > Artificial Intelligence Special Computer Methods > Computer Vision |
| Divisions: | Fakultas Sains dan Teknologi > Program Studi Teknik Informatika |
| Depositing User: | Banie Al'Afaf |
| Date Deposited: | 03 Sep 2025 08:03 |
| Last Modified: | 03 Sep 2025 08:03 |
| URI: | https://digilib.uinsgd.ac.id/id/eprint/117207 |
Actions (login required)
 |
View Item |
