Polysomnography (PSG) is considered the gold standard to assess sleep accurately, but it can be expensive, time-consuming, and uncomfortable, specifically in long-term sleep studies. Actigraphy, on the other hand, is both cheap and userfriendly, but depending on the application lacks detail and accuracy. Our aim was to evaluate cardiorespiratory and movement signals in discriminating between wake, rapid-eye-movement (REM), light (N1N2), and deep (N3) sleep. The dataset comprised 85 nights of PSG from a healthy population. Starting from a total of 750 characteristic variables (features), problem-specific subsets of 40 features were forwardly selected using the combination of a wrapper method (Cohen's kappa statistic on radial basis function (RBF)-kernel support vector machine (SVM) classifier) and filter method (minimum redundancy maximum relevance criterion on mutual information). Final classification was performed using an RBF-kernel SVM. Non-subject-specific wake versus sleep classification resulted in a Cohen’s kappa value of 0.695, while REM versus NREM resulted in 0.558 and N3 versus N1N2 in 0.553. The broad pool of initial features gave insight in which features discriminated best between the different classes. The classification results demonstrate the possibility of making long-term sleep monitoring more widely available.

This study combines concepts of bed design and sleep registrations to investigate how quality of spine support affects the manifestation of sleep in healthy subjects. Altogether, 17 normal sleepers (nine males, eight females; age 24.3±7.1 years) participated in an anthropometric screening, prior to the actual sleep experiments, during which personalised sleep system settings were determined according to individual body measures. Sleep systems (i.e. mattress and supporting structure) with an adjustable stiffness distribution were used. Subjects spent three nights of 8 h in bed in the sleep laboratory in a counterbalanced order (adaptation, personalised support and sagging support). During these nights, polysomnography was performed. Subjective sleep data were gathered by means of questionnaires. Results show that individual posture preferences are a determinant factor in the extent that subjects experience a negative effect while sleeping on a sagging sleep system. STATEMENT OF RELEVANCE: This study investigated how spine support affects sleep in healthy subjects, finding that the relationship between bedding and sleep quality is affected by individual anthropometry and sleep posture. In particular, results indicate that a sagging sleep system negatively affects sleep quality for people sleeping in a prone or lateral posture.

No abstract

The sleep system (i.e. the combination of mattress and bed base) is an important factor of the sleep environment since it allows physical recuperation during sleep by providing proper body support. However, various factors influence the interaction between the human body and the sleep system. Contributing factors include body dimensions, distribution of body weight and stiffness of the sleep system across the mattress surface. During the past decade, the rise of several new bedding technologies has made it increasingly difficult for the consumer to select a proper sleep system. Therefore, this study presents a method to model human-bed interaction in order to objectively predict the ideal sleep system for a particular individual. The proposed method combines a personalized anthropometric model with standardized load-deflection characteristics of mattress and bed base. Results for lateral sleep positions show a root mean square deviation of 11.9 ± 6.1 mm between modeled spine shapes and validation shapes, derived from 3D surface scans of the back surface. The method showed to be a reliable tool to individually identify the sleep system providing superior support from a variety of possible mattress-bed base combinations.

This study investigates how integrated bed measurements can be used to assess motor patterns (movements and postures) during sleep. An algorithm has been developed that detects movements based on the time derivate of mattress surface indentation. After each movement, the algorithm recognizes the adopted sleep posture based on an image feature vector and an optimal separating hyperplane constructed with the theory of support vector machines. The developed algorithm has been tested on a dataset of 30 fully recorded nights in a sleep laboratory. Movement detection has been compared to actigraphy, whereas posture recognition has been validated with a manual posture scoring based on video frames and chest orientation. Results show a high sensitivity for movement detection (91.2%) and posture recognition (between 83.6% and 95.9%), indicating that mattress indentation provides an accurate and unobtrusive measure to assess motor patterns during sleep.