Deteksi Sleep Apnea Secara Non Kontak Menggunakan Citra Infrared dengan Metode Analisis Termografi

Christian, Bryan (2024) Deteksi Sleep Apnea Secara Non Kontak Menggunakan Citra Infrared dengan Metode Analisis Termografi. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5023201002_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (2MB) | Request a copy

Abstract

Sleep Apnea Obstruktif (OSA) adalah gangguan pernapasan selama tidur yang dapat memiliki dampak serius pada kesehatan pasien. OSA membuat penderitanya mengalami berhenti napas selama beberapa detik saat tidur karena otot - otot dan jaringan di belakang tenggorokan menjadi terlalu rileks. Menurut penelitian jurnal Lancet Respir Med tahun 2019, sebanyak 936 juta individu yang berusia di rentang 30 – 69 tahun mengalami Sleep Apnea dengan 425 juta individu mengalami Sleep Apnea tingkat sedang sampai parah. OSA saat ini menggunakan pemeriksaan Polisomnografi (PSG) yang membutuhkan pemasangan alat pada tubuh pasien selama tidur. Pendekatan konvensional ini seringkali memengaruhi kenyamanan tidur pasien dan kualitas data yang diperoleh akibat alat yang harus dipasang semalaman di tubuh pasien. Untuk mengatasi masalah ini, penelitian ini mengusulkan sebuah metode deteksi apnea tidur secara non-kontak menggunakan kamera inframerah. Metode yang diusulkan terdiri dari empat tahapan utama: preprocessing, segmentasi, ekstraksi fitur, dan evaluasi. Pada tahapan preprocessing, citra akan diolah agar lebih memiliki kontras dan terlihat edges-nya. Segmentasi dilakukan dengan menggunakan facial landmark points untuk mengidentifikasi area nasal dan oral pada wajah subjek. Melalui facial landmark inilah ROI nasal dan oral dibentuk. Pada tahap ekstraksi fitur, data sinyal temperatur diambil dari perubahan warna pada ROI nasal dan oral saat subjek bernafas. Analisis dilakukan dalam domain waktu menggunakan metode zero crossing dan peak to peak. Selain itu dilakukan analisis sebagai validasi data pada domain frekuensi menggunakan Fast Fourier Transform (FFT) untuk menghitung Respiratory Rate (RR). Hasil pengujian menunjukkan bahwa metode termografi dapat mendeteksi kondisi apnea dengan pemrosesan sinyal menggunakan zero crossing memberikan hasil yang paling akurat dan relevan dengan nilai rata-rata error sebesar 0.83 bpm dan nilai RMSE sebesar 1.0875 bpm.

==============================================================================================

Obstructive Sleep Apnea (OSA) is a breathing disorder during sleep that can have serious health impacts on patients. OSA causes individuals to stop breathing for several seconds during sleep because the muscles and tissues at the back of the throat become overly relaxed. According to a study in the Lancet Res Med journal in 2019, approximately 936 million individuals aged between 30 and 69 years experience Sleep Apnea, with 425 million individuals experiencing moderate to severe Sleep Apnea. Currently, OSA is diagnosed using Polysomnography (PSG), which requires the attachment of devices to the patient's body during sleep. This conventional approach often affects the patient's sleep comfort and the quality of data obtained due to the devices that must be worn on the body overnight. To address this issue, this research proposes a non-contact sleep apnea detection method using an infrared camera. The proposed method consists of four main stages: preprocessing, segmentation, feature extraction, and evaluation. In the preprocessing stage, images are processed to enhance contrast and reveal edges. Segmentation is carried out using facial landmark points to identify the nasal and oral areas on the subject's face. Through these facial landmarks, the nasal and oral ROIs are formed. In the feature extraction stage, temperature signal data are captured from the color changes in the nasal and oral ROIs as the subject breathes. Analysis is conducted in the time domain using the zero crossing method and peak to peak analysis. dditionally, frequency domain analysis is performed using Fast Fourier Transform (FFT) to calculate the Respiratory Rate (RR) for data validation. The test results show that the thermographic method can detect apnea condition with the zero crossing signal processing method providing the most accurate and relevant results, with an average error of 0.83 bpm and an RMSE of 1.0875 bpm.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Sleep apnea, infrared imaging, detection, thermography,citra inframerah, deteksi, termografi
Subjects:	T Technology > T Technology (General) T Technology > T Technology (General) > T57.5 Data Processing T Technology > T Technology (General) > T57.74 Linear programming T Technology > T Technology (General) > T59.7 Human-machine systems.
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Biomedical Engineering > 11410-(S1) Undergraduate Thesis
Depositing User:	Bryan Christian
Date Deposited:	12 Aug 2024 03:18
Last Modified:	12 Aug 2024 03:18
URI:	http://repository.its.ac.id/id/eprint/112496

Actions (login required)

View Item