期刊
IEEE INTERNET OF THINGS JOURNAL
卷 9, 期 15, 页码 14126-14136出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JIOT.2022.3146926
关键词
Internet of Things; Monitoring; Heart rate; Biomedical monitoring; Accelerometers; Sleep apnea; Temperature sensors; Flexible belt; MEMS accelerometer; pressure sensor; snoring recognition; vital signs and sleep monitoring
资金
- National Natural Science Foundation of China [62104047, U2001201]
Sleep monitoring is crucial for maintaining good health. A newly developed smart flexible belt with sensors is capable of detecting vital signs, snore events, and sleep stages. Detailed algorithms and methods for data processing and analysis are proposed. Experimental results show high accuracy in heart rate and respiration rate detection, as well as snoring recognition. Sleep stage prediction accuracy is higher for 2-stage analysis compared to 4-stage analysis.
People spend about one third of their lifetime in sleep, and sleep quality has a great impact on people's health. Therefore, vital signs and sleep quality monitoring are more and more important. In this article, a novel smart flexible sleep monitoring belt with MEMS triaxial accelerometer and pressure sensor is developed to detect vital signs, snore events, and sleep stages. Besides, the related algorithms and methods for data preprocessing, heart and respiration rates detection, snoring recognition, and sleep stages classification are proposed in detail. Then, a series of sleep experiments is performed based on the experimental platform for the smart flexible belt, and the test results measured by PolySomnoGraphy are used as the golden standards for comparison. The experimental results demonstrate that the detection accuracies of heart rate and respiration rate of the belt are about 1.5 and 0.7 bpm, respectively. The accuracy of 97.2% is achieved by the proposed snoring recognition method. In addition, as for 2-stage analysis, the sensitivities of awake and asleep stages are 90.2% and 100%, respectively; meanwhile, the corresponding accuracy of sleep stages prediction is as high as 95.1%. However, as for 4-stage analysis, the sensitivities of awake, rapid eye movement, light sleep, and deep sleep stages are 90.2%, 77.1%, 78.1%, and 73.5%, respectively; meanwhile, the corresponding accuracy of sleep stages prediction decreases to 79.7%. In general, the test results indicate that vital signs detection, snoring recognition, and sleep stages classification based on the sleep monitoring belt are feasible and effective. Hence, this smart flexible belt can be widely used for sleep monitoring at home due to low cost and high performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据