Sleep Apnea detection using Deep Learning Methodologies

Jain, Gunjit (2022) Sleep Apnea detection using Deep Learning Methodologies. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

One of the most common sleep disorders in the present world is Sleep apnea, which is a condition in which a person stops breathing while in sleep for 10 seconds up to a minute. This happens due to the blockage in the upper airway in the throat muscles. Polysomnography has been the gold standard for the detection of sleep apnea, where a person needs to visit a sleep clinic and sleep the whole night under the supervision of a sleep expert. Numerous sensors are attached to the body to capture the readings. Hence the process is very expensive, time taking, and intrusive. The readings include heart rate variability, SpO2, and other physiological data. This research aims to detect sleep apnea at home using smartwatches. The ECG and SpO2 readings have been analyzed using a spectogram. The models used in this study are CNN and hybrid neural network DenseNet121 + CNN for classifying whether a person is suffering from Sleep Apnea or not. The findings of this research can be used to detect sleep apnea at home.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	Sleep Apnea; Obstructive Sleep Apnea; Convolutional Neural Network; Deep Learning; DenseNet121; Spectogram
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > RF Otorhinolaryngology Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning H Social Sciences > HM Sociology > Information Science > Communication > Medical Informatics
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	26 Jan 2023 17:20
Last Modified:	03 Mar 2023 11:08
URI:	https://norma.ncirl.ie/id/eprint/6142

Actions (login required)

View Item