BROWSE
Detail
Conference Paper
수면 세분화 분석을 통한 스마트 워치 기반 청소년 수면 장애 인식
Cited - time in 
Share 
Share
- Issue Date
- 2024-06
- Citation
- 대한전자공학회 학술 대회 (하계) 2024, pp.1210-1213
- Publisher
- 대한전자공학회
- Language
- Korean
- Type
- Conference Paper
- Abstract
- Inexpensive consumer-grade smartwatches capable of long-term monitoring of physiological signals such as sleep, heart rate, and activity levels have been widely utilized in various research studies. However, existing studies often lack precision in distinguishing sleep patterns, resulting in diminished accuracy. In this study, we proposed a novel sleep segmentation method that considers actual sleep duration and performed sleep disorder recognition experiments using adolescent Fitbit data from the ABCD study. Our proposed method outperformed the fixed-window approach in terms of accuracy and F1 score metrics. The results demonstrated the potential utility of consumer smartwatches for sleep disorder screening. However, the achieved accuracy did not reach the clinical level, necessitating the use of these devices as supplementary tools. Further research is needed, including analysis of domestic adolescent data, to improve sleep disorder recognition performance.
- KSP Keywords
- Heart rate, Physiological signals, long term monitoring, recognition performance, segmentation method