The Meaning of Sleep Quality: A Survey of Available Technologies

Abstract

Sleep is an important part of the human daily routine. Restoring sleep is strongly related to a better physical, cognitive, and psychological well-being. By contrast, poor or disordered sleep leads to possible impairments of cognitive and psychological functioning and to a worsened general physical health. In this context, understanding changes in sleep quality becomes a research imperative that leads to the need for the definition of what restoring or quality sleep means. This understanding of what ''sleep quality'' means requires a cross-domain investigation. It arises the need for a comprehensive study that offers a complete taxonomy of sleep monitoring systems, with a focus on sleep quality, and that gives useful insights about which combination of metrics, signals, and sleep variables is the best in relation to different categories of users. The proposed study is focused on systematically categorizing the methods and approaches for sleep quality understanding, with an emphasis on technological approaches, including wearable, on-bed, and actigraphy devices. It offers a systematic review for researchers who are interested in sleep quality identification tasks, and highlights strengths and weaknesses of state-of-the-art metrics and solutions in order to suggest the best choice for new potential research challenges in the field. Another important outcome of the proposed work is the study of the impact on the identified signal metrics and solutions of the different target user populations with their specific user requirements. INDEX TERMS Sleep quality, in-home sensing, sleep diaries, polysomnography, sleep devices, sleep monitoring, physiological parameters, smart health.

Self-Supervised Learning From Multi-Sensor Data for Sleep Recognition

“…We take the pose image in the pressure map dataset as an example to introduce the self-supervised pre-training process. First, the original input X 0 is rotated at different angles to get X 1 1 − X 3 1 and get X 4 1 through FFT, generating labels 0-4. A four-layer CNN with 2 hidden layers and one input-output layer, which uses 5 * 5 convolution kernel for convolution operation, we take the output of the second hidden layer as the final result I m of pre-training.…”

“…Sleep quality is a proven biometric that plays an eminent role in health status evaluation of patients with mental or physical disorders. According to the survey of the World Health Organization (WHO), about 1/3 of people in the world have sleep problems, and the global sleep disorder rate is 27%, which seriously affect people's health and quality of life [1]. In order to better evaluate and monitor sleep quality and state, we are committed to establishing a reliable and safe sleep model for analysis and diagnosis of sleep state.…”

A Smart Bed for Non-Obtrusive Sleep Analysis in Real World Context

“…The final step of the sleep quality algorithm was based on the sleep macro-structure estimated previously. Firstly, the sleep macro-structure was used to extrapolate the main sleep time-domain parameters [9], [40], [41] related to each night's sleep, such as: sleep efficiency, sleep latency, REM latency, total sleep time, and wake after sleep onset (WASO). The SQI was then estimated based on the following partial criteria (pc):…”

“…Systematic, preventive, personalized and non-invasive methods for sleep quality assessment are thus of paramount importance. Polysomnography is currently the gold-standard for assessing sleep quality [8], [9], since it estimates the The associate editor coordinating the review of this manuscript and approving it for publication was Mohamad Forouzanfar . macrostructure of sleep, i.e.…”

“…Several non-invasive sensor technologies have been developed for in-bed monitoring of biomedical parameters, such as sleeping posture/movements and physiological signals [9], [14]- [24]. However, no previous work has focused on the assessment of sleep quality by comparing it with the standard (i.e.…”