Rafie Rojagat Bachri, . (2026) IMPLEMENTASI RANDOM FOREST UNTUK KLASIFIKASI KUALITAS TIDUR MAHASISWA BERBASIS ANDROID. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (151kB) |
|
Text
AWAL.pdf Download (818kB) |
|
Text
BAB I.pdf Restricted to Repository UPNVJ Only Download (216kB) |
|
Text
BAB II.pdf Restricted to Repository UPNVJ Only Download (433kB) |
|
Text
BAB III.pdf Restricted to Repository UPNVJ Only Download (646kB) |
|
Text
BAB IV.pdf Restricted to Repository UPNVJ Only Download (886kB) |
|
Text
BAB V.pdf Download (193kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (233kB) |
|
Text
DAFTAR RIWAYAT HIDUP.pdf Restricted to Repository staff only Download (120kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (954kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (15MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (430kB) |
Abstract
Poor sleep quality is a common issue among university students, negatively impacting physical health and academic performance. Although various sleep monitoring applications are available, most only provide diagnostic results without connecting users to appropriate educational interventions or medical services. This study aims to develop an Android sleep monitoring application that implements the Random Forest algorithm for sleep quality classification, while also facilitating users with static educational literature and tele-medicine service integration. Research data was collected through daily self-reported questionnaires adapted from the Pittsburgh Sleep Quality Index (PSQI) guidelines and student lifestyle factors. Imbalanced data handling in the model was effectively resolved using a Cost-Sensitive Learning approach, yielding an accuracy rate of 92.06% and an F1-Score of 0.92. To ensure computational efficiency and privacy on mobile devices, the model was extracted into a Native Java Class, allowing the inference process to run offline. To avoid medical ethics violations in providing unilateral clinical instructions, the system is designed to provide interventions in the form of sleep hygiene education and direct users to professional tele-medicine portals. Testing results prove that the implementation of the Model-View-ViewModel (MVVM) architecture successfully created a responsive application ecosystem. The integration of this offline Machine Learning modeling makes the application not only a precise measurement tool but also a preventive facilitator to increase students' sleep health awareness.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 2210511043] [Pembimbing 1: Jayanta] {Pembimbing 2: Nurhuda Maulana} [Penguji 1: Musthofa Galih Pradana] [Penguji 2: Nurul Afifah Arifuddin] |
| Uncontrolled Keywords: | Android, Cost-Sensitive Learning, Random Forest, Sleep Quality, Tele-medicine. |
| Subjects: | Q Science > QA Mathematics > QA76 Computer software R Medicine > R Medicine (General) T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | RAFIE ROJAGAT BACHRI |
| Date Deposited: | 01 Sep 2026 04:46 |
| Last Modified: | 01 Sep 2026 04:46 |
| URI: | http://repository.upnvj.ac.id/id/eprint/51061 |
Actions (login required)
 |
View Item |