Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.<br>

An Automated Heart Rate-based Algorithm for Sleep Stage Classification: Validation Using Conventional PSG and Innovative Wearable ECG Device

Study Objectives: Validate a HR-based deep-learning algorithm for sleep staging named Neurobit-HRV (Neurobit Inc., New York, USA). Methods: The algorithm can perform classification at 2-levels (Wake; Sleep), 3-levels (Wake; NREM; REM) or 4- levels (Wake; Light; Deep; REM) in 30-second epochs. The algorithm was validated using an open-source dataset of PSG recordings (Physionet CinC dataset, n=994 participants) and a proprietary dataset (Z3Pulse, n=52 participants), composed of HR recordings collected with a chest-worn, wireless sensor. A simultaneous PSG was collected using SOMNOtouch. We evaluated the performance of the models in both datasets using Accuracy (A), Cohen's kappa (K), Sensitivity (SE), Specificity (SP). Results: CinC - The highest value of accuracy was achieved by the 2-levels model (0.8797), while the 3-levels model obtained the best value of K (0.6025). The 4-levels model obtained the lowest SE (0.3812) and the highest SP (0.9744) for the classification of Deep sleep segments. AHI and biological sex did not affect sleep scoring, while a significant decrease of performance by age was reported across the models. Z3Pulse - The highest value of accuracy was achieved by the 2-levels model (0.8812), whereas the 3-levels model obtained the best value of K (0.611). For classification of the sleep states, the lowest SE (0.6163) and the highest SP (0.9606) were obtained for the classification of Deep sleep segment. Conclusions: Results demonstrate the feasibility of accurate HR-based sleep staging. The combination of the illustrated sleep staging algorithm with an inexpensive HR device, provides a cost-effective and non-invasive solution easily deployable in the home.

Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.<br>

Unsupervised Domain Adaptation by Statistics Alignment for Deep Sleep Staging Networks

Deep sleep staging networks have reached top performance on large-scale datasets. However, these models perform poorer when training and testing on small sleep cohorts due to data inefficiency. Transferring well-trained models from large-scale datasets (source domain) to small sleep cohorts (target domain) is a promising solution but still remains challenging due to the domain-shift issue. In this work, an unsupervised domain adaptation approach, domain statistics alignment (DSA), is developed to bridge the gap between the data distribution of source and target domains. DSA adapts the source models on the target domain by modulating the domain-specific statistics of deep features stored in the Batch Normalization (BN) layers. Furthermore, we have extended DSA by introducing cross-domain statistics in each BN layer to perform DSA adaptively (AdaDSA). The proposed methods merely need the well-trained source model without access to the source data, which may be proprietary and inaccessible. DSA and AdaDSA are universally applicable to various deep sleep staging networks that have BN layers. We have validated the proposed methods by extensive experiments on two state-of-the-art deep sleep staging networks, DeepSleepNet+ and U-time. The performance was evaluated by conducting various transfer tasks on six sleep databases, including two large-scale databases, MASS and SHHS, as the source domain, four small sleep databases as the target domain. Thereinto, clinical sleep records acquired in Huashan Hospital, Shanghai, were used. The results show that both DSA and AdaDSA could significantly improve the performance of source models on target domains, providing novel insights into the domain generalization problem in sleep staging tasks.<br>

Effect of a Recliner Chair with Rocking Motions on Sleep Efficiency

In this study, we analyze the effect of a recliner chair with rocking motions on sleep quality of naps using automated sleep scoring and spindle detection models. The quality of sleep corresponding to the two rocking motions was measured quantitatively and qualitatively. For the quantitative evaluation, we conducted a sleep parameter analysis based on the results of the estimated sleep stages obtained on the brainwave and spindle estimation, and a sleep survey assessment from the participants was analyzed for the qualitative evaluation. The analysis showed that sleep in the recliner chair with rocking motions positively increased the duration of the spindles and deep sleep stage, resulting in improved sleep quality.

Pilot Sleep Behavior across Time during Ultra-Long-Range Flights

Fatigue risk to the pilot has been a deterrent for conducting direct flights longer than 12 h under normal conditions, but such flights were a necessity during the COVID-19 pandemic. Twenty (N = 20) pilots flying across five humanitarian missions between Brazil and China wore a sleep-tracking device (the Zulu watch), which has been validated for the estimation of sleep timing (sleep onset and offset), duration, efficiency, and sleep score (wake, interrupted, light, or deep Sleep) throughout the mission period. Pilots also reported sleep timing, duration, and subjective quality of their in-flight rest periods using a sleep diary. To our knowledge, this is the first report of commercial pilot sleep behavior during ultra-long-range operations under COVID-19 pandemic conditions. Moreover, these analyses provide an estimate of sleep score during in-flight sleep, which has not been reported previously in the literature.

Simulation, Fetishism and World Domination

According to Jean Baudrillard, in a totally functional world people become irrational and subjective, given to projecting their fantasies of power into the efficiency of the system, a state of ‘spectacular alienation’. I argue that Americans as a society have accommodated themselves to such a system to the detriment of their ability to make sense in their public discourse. Baudrillard finds pathology in the system of objects as it determines social relations. In one symptom, people may obsess over a fetish object. For American society, the magical mechanical object is the gun. I show evidence for this weapons fetish in American fiction, cinema, television and serious journalism. Then, using Baudrillard and other analysts, I show how the American obsession with the superior functionality of weapons joins its myth of exceptionality and preference for simulation over reality to create a profound American dream state that protects a very deep sleep.

The Psychoanalysis of Sleep-Paralysis – Perspectives on Oneirology

Dream is the reflection of our unconscious mind when we are in deep slumber. The duration of dream varies from 14 sec - 40sec and are characterized by Rapid Eye Movement (REM). Dreams occur in the transition period from light sleep to deep sleep or from deep sleep to light sleep. The associated study of dreams is known as Oneirology. It is sometimes associated by physical bodily movement

Effects of Lactobacillus plantarum PS128 on Depressive Symptoms and Sleep Quality in Self-Reported Insomniacs: A Randomized, Double-Blind, Placebo-Controlled Pilot Trial

Recent animal studies have supported that Lactobacillus plantarum PS128 (PS128) can reduce the severity of anxiety and depression. However, previous studies did not focus on the sleep quality and mood of humans. This study determines whether PS128 reduces the severity of anxiety and depressive symptoms, regulates autonomic nervous system function, and improves sleep quality. Forty participants between 20 and 40 years of age with self-reported insomnia were randomly assigned to two groups, a PS128 group and a placebo group, in a double-blind trial. Participants took two capsules of either PS128 or a placebo after dinner for 30 days. Study measures included subjective depressive symptoms, anxiety and sleep questionnaires, and miniature-polysomnography recordings at baseline and on the 15th and 30th days of taking capsules. Overall, all outcomes were comparable between the two groups at baseline and within the 30-day period, yet some differences were still found. Compared to the control group, the PS128 group showed significant decreases in Beck Depression Inventory-II scores, fatigue levels, brainwave activity, and awakenings during the deep sleep stage. Their improved depressive symptoms were related to changes in brain waves and sleep maintenance. These findings suggest that daily administration of PS128 may lead to a decrease in depressive symptoms, fatigue level, cortical excitation, and an improvement in sleep quality during the deep sleep stage. Daily consumption of PS128 as a dietary supplement may improve the depressive symptoms and sleep quality of insomniacs, although further investigation is warranted.