Analisis Pengaruh Olahraga Lari Terhadap Tingkat Stres Menggunakan Photopletysmogram Dan Electrocardiogram

Lastono, Avicenna Syeh Brilliant (2025) Analisis Pengaruh Olahraga Lari Terhadap Tingkat Stres Menggunakan Photopletysmogram Dan Electrocardiogram. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5026211015-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Stres adalah respons alami tubuh yang berdampak signifikan pada kesehatan fisik dan mental. Penelitian ini menganalisis pengaruh olahraga lari terhadap tingkat stres pada masyarakat dewasa menggunakan sinyal Photoplethysmogram (PPG) dan Electrocardiogram (ECG), yang memantau aktivitas jantung melalui Heart Rate Variability (HRV). Metodologi meliputi pengumpulan data PPG dan ECG selama lari, pra-pemrosesan sinyal dengan denoising (dua langkah adaptif) dan peak-detecting berbasis ensemble, serta ekstraksi fitur HRV. Principal Component Analysis (PCA) diterapkan untuk reduksi dimensi dan menangani multikolinearitas. Model Support Vector Machine (SVM) dilatih dan dievaluasi menggunakan pendekatan Leave-One-Subject-Out (LOSO). Hasil penelitian menunjukkan olahraga lari berpengaruh signifikan terhadap stres. Perbandingan kinerja model SVM mengungkapkan bahwa data ECG (Mean Accuracy: 0.8231, Mean F1-Score: 0.5349) memberikan performa yang lebih unggul dibanding data PPG (Mean Accuracy: 0.7869, Mean F1-Score: 0.4436). Peningkatan F1-Score pada ECG mengindikasikan relevansi fitur sinyal ECG yang lebih tinggi dalam membedakan kondisi stres. Penelitian ini berkontribusi pada pemahaman manfaat lari untuk kesehatan mental dan potensi teknologi PPG dalam deteksi stres.
====================================================================================================================================
Stress is a natural bodily response that significantly impacts both physical and mental health. This research analyzes the effect of running exercise on stress levels in adults using Photoplethysmogram (PPG) and Electrocardiogram (ECG) signals, which monitor heart activity through Heart Rate Variability (HRV). The methodology includes collecting PPG and ECG data during running, signal pre-processing with adaptive two-step denoising and ensemble-based peak-detecting, and HRV feature extraction. Principal Component Analysis (PCA) was applied for dimensionality reduction and to address multicollinearity. A Support Vector Machine (SVM) model was trained and evaluated using a Leave-One-Subject-Out (LOSO) approach. The research results indicate that running exercise significantly impacts stress. A comparison of SVM model performance revealed that ECG data (Mean Accuracy: 0.8231, Mean F1-Score: 0.5349) yielded superior performance compared to PPG data (Mean Accuracy: 0.7869, Mean F1-Score: 0.4436). The more significant increase in F1-Score for ECG indicates a higher relevance of ECG signal features in distinguishing stress conditions. This study contributes to the understanding of running's benefits for mental health and the potential of PPG technology in stress detection.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Stres, Olahraga Lari, Photopletysmogram, Electrocardiogram, Heart Rate Variability, Stres, Runnning Exercise, Photopletysmogram, Electrocardiogram, Heart Rate Variability
Subjects:	R Medicine > RC Internal medicine > RC683.5.E5 Electrocardiography T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	Avicenna Syeh Brilliant Lastono
Date Deposited:	25 Jul 2025 04:36
Last Modified:	25 Jul 2025 04:59
URI:	http://repository.its.ac.id/id/eprint/121643

Actions (login required)

View Item