Prediction Model for Obstructive Sleep Apnea from Facial Depth Maps using Transfer Learning

Main Article Content

Ramadevi Javvaji , Ravikiran Biroju, Hanuja Korukonda

Abstract

Obstructive Sleep Apnea (OSA) occurs when obstruction happens repeatedly in the airway during sleep due to relaxation of the tongue and airway-muscles. Usual indicators of OSA are snoring, poor night sleep due to choking or gasping for air and waking up unrefreshed. OSA diagnosis is costly both in the monetary and timely manner. That is why many patients remain undiagnosed and unaware of their condition. Previous research has shown the link between facial morphology and OSA. In this paper, investigated the application of deep learning techniques to diagnose the disease through depth map of human facial scans. Depth map will provide more information about facial morphology as compared to the plain 2-D color image. Even with very less amount of sample data, we can get around 69 validation accuracy using transfer learning. We are predicting patients with above moderate > 15 or below moderate ≤ 15 OSA. Finally, the simulations revealed that the proposed VGG 19 resulted in superior performance as compared to existing model.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Article Details

How to Cite
Ramadevi Javvaji , Ravikiran Biroju, Hanuja Korukonda. (2023). Prediction Model for Obstructive Sleep Apnea from Facial Depth Maps using Transfer Learning. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 13(03), 1247–1257. https://doi.org/10.17762/turcomat.v13i03.13439
Section
Research Articles