Sleeping Postures

Introduction

Sleep is a complex and dynamic brain process, that is important for a number of important brain functions. Sleep plays a vital role in the optimum functioning of the brain, heart, and lungs. Furthermore, sleep decreases the risk of chronic diseases and improves immunity. Sleeping postures has a positive or negative effect on the body.

Types of Sleeping Posture

sleeping on your side

The majority of people sleep on their sides. Sleeping on the side has benefits. as it promotes healthy spinal alignment. heart burn and snoring are also reduced by side sleeping. Side sleeping is beneficial for pregnant women, back pain, sleep apnea and older people.

sleeping on your back

The stomach is the least popular sleep position. Research suggests we spend less than 10% of our night sleeping in this position.

Lying on the back is the second most popular sleep position, with plenty of benefits to rival the side sleeping position. When you’re flat on your back, it’s easy to keep your spine in alignment and to evenly distribute your body weight, preventing any potential aches in the neck or back. Sleeping on the back can also relieve the congestion of a stuffy nose or allergies, so long as you prop yourself up into an upright position.

sleeping on your stomach

The stomach position provides the least back support of all sleeping positions and increases pressure on the spine, sometimes causing pain upon waking up. sleeping on the stomach can contribute to facial wrinkles https://www.sleepfoundation.org/sleeping-positions

the worst position to sleep in for individuals who have a history of spinal injury as it delays recovery. https://www.news-medical.net/health/A-Guide-to-Healthy-Sleep-Positions.aspx

Side sleeping is https://www.verywellhealth.com/best-and-worst-sleep-positions-for-health-conditions-4158271

reported that for patients with Congestive Heart Failure (CHF), the amount of time spent in the right lateral position is significantly more than the amount of time spent in the left lateral position. This strategy might help them to avoid the discomfort caused by the enlarged apical heartbeat or further hemodynamic or autonomic compromise.

Sleep Posture Classification using Bed Sensor Data and Neural Networks

we use a hydraulic bed sensor designed for capturing ballistocardiogram (BCG) signals [15]. It is composed of a set of four water tubes each fitted with a pressure sensor (Fig. 1) which are placed under the bed mattress for the purpose of non-invasive heart motion measurement. The four-channel signal is sampled at 100 Hz and in its raw format, it contains a DC bias (the weight of the body lying on the bed). We simply ran moving averages to remove the high-frequency part of the signal. Variations in the DC values for the four channels are known to be correlated to the location of the person on the bed https://ieeexplore.ieee.org/abstract/document/8512436?casa_token=hoR3NNwHJ-EAAAAA:X9DWGXC1bR61hcKfe9Sho7lhVMC52xvwS_3_CBlEcupYv3qN6ig34XUkSfEoYWgK9YzPBMibWtc

Multimodal Sleeping Posture Classification

we focus on sleeping posture classification, which can be important not only for bedsore prevention [14], [17] but also for sleeping quality analysis https://ieeexplore.ieee.org/abstract/document/5597772?casa_token=-aeycxe8QUIAAAAA:wXpJVdyJ8dRebI4Ep7S_3N2y5PETnvieYqAsuAiLZOSovKdzc78YFb5vvsmYaNHFW6OL25cf_qU

Sleep posture classification with multi-stream CNN using vertical distance map

Sleep posture type was also considered in the study. Sleep Assessment and Advisory Service (SAAS) clusters sleep postures into six types: fetus, log, yearner, soldier, freefaller, and starfish. Most studies only focused on the identification of three sleep postures, including supine, left side, and right side incorrect sleep positions held for a considerably long duration can result in spinal alignment problems.

An HMM-based method was applied for analyzing posture changes and myoclonic twitches. However, wearable device usually cause uncomfortable sleep, and that may affect sleep quality of people

Pressure mattress was also widely used for sleep posture recognition. Jason et al. [11] monitored sleep postures using a pressure-sensitive bed sheet, and features of pressure images were extracted for identifying sleep postures using three sparse classifiers https://ieeexplore.ieee.org/abstract/document/8369761?casa_token=5NmOhTNhi8UAAAAA:p3p74V5UwUHFRFmezrzbzJ2fQkvWWDUIfvquoxqd-UmOOGSnTnPzkPyj2JSrOOISPLZcrgYgJjI

we propose to enhance the accuracy of the under-blanket sleep posture classification with a new deep learning model architecture with a guided input of anatomical features generated using a pose estimator [39]. The classification covers seven common sleep postures, including the supine posture, prone postures with the head turned left and right, left- and right-sided log postures, and left- and right-sided fetal postures. The key contributions of this study are as follows:

• We developed a posture classification system that can be generalized to various blanket conditions.
• We proposed an integrative innovation for the deep learning model to improve the classification performance through anatomical landmark features generated using a pose estimator https://www.mdpi.com/1660-4601/19/20/13491