DZIKRI FAUZAN, FIQIH (2026) KLASIFIKASI TAHAPAN TIDUR MENGGUNAKAN DATA FISIOLOGIS NON-INVASIVE BERBASIS ALGORITMA SUPERVISED LEARNING. S1 thesis, Fakultas Teknik Universitas Sultan Ageng Tirtayasa.
![[img]](https://eprints.untirta.ac.id/style/images/fileicons/text.png) |
Text (Fulltext)
FIQIH DZIKRI FAUZAN_3332220031_Fulltext.pdf Restricted to Registered users only Download (3MB) | Request a copy |
|
Text (BAB 1)
FIQIH DZIKRI FAUZAN_3332220031_01.pdf Restricted to Registered users only Download (1MB) | Request a copy |
|
Text (BAB 2)
FIQIH DZIKRI FAUZAN_3332220031_02.pdf Restricted to Registered users only Download (572kB) | Request a copy |
|
Text (BAB 3)
FIQIH DZIKRI FAUZAN_3332220031_03.pdf Restricted to Registered users only Download (485kB) | Request a copy |
|
Text (BAB 4)
FIQIH DZIKRI FAUZAN_3332220031_04.pdf Restricted to Registered users only Download (1MB) | Request a copy |
|
Text (BAB 5)
FIQIH DZIKRI FAUZAN_3332220031_05.pdf Download (260kB) |
|
Text (DAFTAR PUSTAKA)
FIQIH DZIKRI FAUZAN_3332220031_Ref.pdf Restricted to Registered users only Download (242kB) | Request a copy |
|
Text (LAMPIRAN SKRIPSI)
FIQIH DZIKRI FAUZAN_3332220031_Lamp.pdf Restricted to Registered users only Download (1MB) | Request a copy |
|
Text (HASIL TURNITIN)
FIQIH DZIKRI FAUZAN_3332220031_CP.pdf Restricted to Registered users only Download (17MB) | Request a copy |
Abstract
Sleep is a vital physiological process that affects physical and mental health, with stages such as wakefulness, Rapid Eye Movement (REM), and Non-Rapid Eye Movement (NREM), which is further divided into stages N1, N2, and N3, which play a role in physical recovery and emotional regulation. Sleep disorders, such as poor sleep quality, are associated with an increased risk of hypertension and chronic diseases. Conventional polysomnography (PSG) methods have limitations, including high costs and discomfort. This study aims to develop a sleep stage classification model using non-invasive physiological parameters (BVP, ACC_X, ACC_Y, ACC_Z, TEMP, EDA, HR, IBI) as an alternative, and evaluate its effectiveness using Supervised Learning algorithms. The research methods include the use of a Kaggle dataset, data preprocessing (filtering, handling missing data, segmentation, min-mix scaling normalization), and model training with Support Vector Machine (SVM) using RBF kernel and Random Forest Algorithm, including hyperparameter optimization and cross-validation. Performance evaluation uses accuracy, precision, recall, and F1-score metrics. This study found that the use of the Random Forest algorithm with all parameters and the SMOTE method yielded the best results for the five-stage classification of wake, N1, N2, N3, and REM, with a performance matrix of 79.11% accuracy, 79.54% precision, 79.11% recall, and 79.28% F1-score.
| Item Type: | Thesis (S1) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
|||||||||
| Additional Information: | Tidur merupakan proses fisiologis vital yang memengaruhi kesehatan fisik dan mental, dengan tahapan seperti wake, Rapid Eye Movement (REM), dan Non-Rapid Eye Movement (NREM) yang dibagi kembali menjadi tahap N1, N2, dan N3 yang berperan dalam pemulihan tubuh dan regulasi emosi. Gangguan tidur, seperti kualitas tidur buruk, dikaitkan dengan risiko hipertensi dan penyakit kronis. Metode konvensional polysomnography (PSG) memiliki keterbatasan berupa biaya tinggi dan rasa tidak nyaman. Penelitian ini bertujuan mengembangkan model klasifikasi tahapan tidur menggunakan parameter fisiologis non-invasive (BVP, ACC_X, ACC_Y, ACC_Z, TEMP, EDA, HR, IBI) sebagai alternatif, serta mengevaluasi efektivitasnya dengan algoritma Supervised Learning. Metode penelitian meliputi penggunaan dataset Kaggle, preprocessing data (filtering, handling missing data, segmentasi, normalisasi min-mix scaling), dan pelatihan model dengan Support Vector Machine (SVM) menggunakan kernel RBF serta Algoritma Random Forest, termasuk optimasi hyperparameter dan validasi silang. Evaluasi hasil performa menggunakan metrik akurasi, presisi, recall,dan F1-score. Pada penelitian ini mendapatkan hasil bahwasanya penggunaan algoritma Random Forest dengan keseluruhan parameter dengan metode SMOTE merupakan hasil terbaik untuk klasifikasi 5 tahap yaitu wake, N1, N2, N3, dan REM dengan hasil performance matrix Accuracy 79,11%, Precission 79,54%, Recall 79,11%, F1-Score 79,28%. | |||||||||
| Uncontrolled Keywords: | Klasifikasi Tahap Tidur, Fisiologis Non-Invasive, Supervised Learning, Support Vector Machine, Random Forest. | |||||||||
| Subjects: | T Technology > TK Electrical engineering. Electronics Nuclear engineering | |||||||||
| Divisions: | 03-Fakultas Teknik 03-Fakultas Teknik > 20201-Jurusan Teknik Elektro |
|||||||||
| Depositing User: | Mr Fiqih Dzikri Fauzan | |||||||||
| Date Deposited: | 20 Jan 2026 02:32 | |||||||||
| Last Modified: | 20 Jan 2026 02:32 | |||||||||
| URI: | http://eprints.untirta.ac.id/id/eprint/57256 |
Actions (login required)
 |
View Item |