摘要
Abstract
Obstructive sleep apnea(OSA)is a serious sleep disorder that affects quality of life and causes complications.Traditional polysomnography(PSG)is difficult to be applied on a large scale due to high cost and complex operation.In this paper,we propose a face recognition-based OSA screening tool,which realizes a convenient screening scheme through facial feature analysis and deep learning techniques.Experimental results show that the tool has a sensitivity of 77.1％and a specificity of 84.8％,providing a contactless solution for large-scale population screening.关键词
阻塞性睡眠呼吸暂停/人脸识别/ResNet50/Grad-CAMKey words
obstructive sleep apnea/face recognition/ResNet50/Grad-CAM分类
信息技术与安全科学
