Biological Rhythm Based Wearable Sleep State Observer

2007 ◽  
Vol 11 (2) ◽  
pp. 232-241 ◽  
Author(s):  
Yuki Wakuda ◽  
◽  
Akiko Noda ◽  
Yasuhisa Hasegawa ◽  
Fumihito Arai ◽  
...  
Keyword(s):  
Sleep Stage ◽  
Biological Rhythm ◽  
Sleep Cycle ◽  
Stress System ◽  
Sleep State ◽  
Human Sleep ◽  
Sensor Device ◽  
Preset Time ◽  
Pulse Waves ◽  
Life Cycle Pattern

This research aimed to observe human biological rhythm and adjust the human sleep wake pattern based on controlling wakeup timing using low stress system. An ordinary alarm clock operates according to preset time. Biological rhythm determines the human sleep cycle, which affects sleep depth and wakeup timing, which in turn resets the daily rhythm that affects human’s behavior, life-cycle pattern, life-style related disease. We developed a wearable biological rhythm based awakening controller (BRAC) that determines the biological rhythm in the sleep state (sleep cycle) and stimulates the user at a suitable time to enable the person to wakeup refreshed. The proposed system BRAC gauges human’s sleep quality and rhythms from peak to peak interval time of fingertip-pulse waves, that are measured more easily than polysomnography (PSG). In this paper, we detail the method of sleep cycle estimation using a wearable sensor device as the first feature of BRAC, then, in experiments, evaluate the performance of sleep cycle estimation based on a comparison of the BRAC-sleep cycle and the PSG-determined sleep stage.

scholarly journals Capturing the Development of Internal Representations in a High-Performing Deep Network for Sleep Stage Classification

2021 ◽  
Vol 2 (4) ◽  
Author(s):  
Sarun Paisarnsrisomsuk ◽  
Carolina Ruiz ◽  
Sergio A. Alvarez
Keyword(s):  
Input Data ◽  
Single Channel ◽  
Sleep Stage ◽  
Quantitative Measure ◽  
Classification Performance ◽  
Sleep Stages ◽  
Layer Depth ◽  
Human Sleep ◽  
Stage Classification ◽  
Sleep Stage Classification

AbstractDeep neural networks can provide accurate automated classification of human sleep signals into sleep stages that enables more effective diagnosis and treatment of sleep disorders. We develop a deep convolutional neural network (CNN) that attains state-of-the-art sleep stage classification performance on input data consisting of human sleep EEG and EOG signals. Nested cross-validation is used for optimal model selection and reliable estimation of out-of-sample classification performance. The resulting network attains a classification accuracy of $$84.50 \pm 0.13\%$$ 84.50 ± 0.13 % ; its performance exceeds human expert inter-scorer agreement, even on single-channel EEG input data, therefore providing more objective and consistent labeling than human experts demonstrate as a group. We focus on analyzing the learned internal data representations of our network, with the aim of understanding the development of class differentiation ability across the layers of processing units, as a function of layer depth. We approach this problem visually, using t-Stochastic Neighbor Embedding (t-SNE), and propose a pooling variant of Centered Kernel Alignment (CKA) that provides an objective quantitative measure of the development of sleep stage specialization and differentiation with layer depth. The results reveal a monotonic progression of both of these sleep stage modeling abilities as layer depth increases.

scholarly journals Spontaneous Hemodynamic Oscillations during Human Sleep and Sleep Stage Transitions Characterized with Near-Infrared Spectroscopy

PLoS ONE ◽  
2011 ◽  
Vol 6 (10) ◽  
pp. e25415 ◽  
Author(s):  
Tiina Näsi ◽  
Jaakko Virtanen ◽  
Tommi Noponen ◽  
Jussi Toppila ◽  
Tapani Salmi ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Sleep Stage ◽  
Human Sleep

Autonomic activity during human sleep as a function of time and sleep stage

2001 ◽  
Vol 10 (4) ◽  
pp. 253-264 ◽  
Author(s):  
John Trinder ◽  
Jan Kleiman ◽  
Melinda Carrington ◽  
Simon Smith ◽  
Sibilah Breen ◽  
...  
Keyword(s):  
Sleep Stage ◽  
Autonomic Activity ◽  
Human Sleep

scholarly journals Discrepancies in the Time Course of Sleep Stage Dynamics, Electroencephalographic Activity and Heart Rate Variability Over Sleep Cycles in the Adaptation Night in Healthy Young Adults

2021 ◽  
Vol 12 ◽  
Author(s):  
Ai Shirota ◽  
Mayo Kamimura ◽  
Akifumi Kishi ◽  
Hiroyoshi Adachi ◽  
Masako Taniike ◽  
...  
Keyword(s):  
Heart Rate ◽  
Heart Rate Variability ◽  
Young Adults ◽  
Time Course ◽  
Sleep Stage ◽  
Transition Probability ◽  
Sleep Cycle ◽  
The Central Nervous System ◽  
Electroencephalographic Activity ◽  
Sleep Cycles

ObjectiveThe aim of the present study was to characterize the cyclic sleep processes of sleep-stage dynamics, cortical activity, and heart rate variability during sleep in the adaptation night in healthy young adults.MethodsSeventy-four healthy adults participated in polysomnographic recordings on two consecutive nights. Conventional sleep variables were assessed according to standard criteria. Sleep-stage continuity and dynamics were evaluated by sleep runs and transitions, respectively. These variables were compared between the two nights. Electroencephalographic and cardiac activities were subjected to frequency domain analyses. Cycle-by-cycle analysis was performed for the above variables in 34 subjects with four sleep cycles and compared between the two nights.ResultsConventional sleep variables reflected lower sleep quality in the adaptation night than in the experimental night. Bouts of stage N1 and stage N2 were shorter, and bouts of stage Wake were longer in the adaptation night than in the experimental night, but there was no difference in stage N3 or stage REM. The normalized transition probability from stage N2 to stage N1 was higher and that from stage N2 to N3 was lower in the adaptation night, whereas that from stage N3 to other stages did not differ between the nights. Cycle-by-cycle analysis revealed that sleep-stage distribution and cortical beta EEG power differed between the two nights in the first sleep cycle. However, the HF amplitude of the heart rate variability was lower over the four sleep cycles in the adaptation night than in the experimental night.ConclusionThe results suggest the distinct vulnerability of the autonomic adaptation processes within the central nervous system in young healthy subjects while sleeping in a sleep laboratory for the first time.

Change in recruitment order of motor units in human parasternal intercostal muscles with sleep state

1993 ◽  
Vol 74 (6) ◽  
pp. 2718-2723 ◽  
Author(s):  
W. A. Whitelaw ◽  
K. P. Rimmer ◽  
H. S. Sun
Keyword(s):  
Sleep Stage ◽  
Human Subjects ◽  
Motor Units ◽  
Excitatory Input ◽  
Sleep State ◽  
Intercostal Muscles ◽  
Intramuscular Electrodes ◽  
Normal Human ◽  
Low Threshold ◽  
Recruitment Order

Recruitment order of individual motor units in the early part of inspiration in parasternal intercostal muscles was observed in normal human subjects during wakefulness and non-rapid-eye-movement sleep. Electromyograms from bipolar fine wire intramuscular electrodes were recorded while the subjects lay supine in a sleep laboratory, and sleep stage was determined by polysomnography. From wakefulness to sleep there were numerous examples of shifts in order of recruitment among the low threshold units of early inspiration. There were corresponding shifts in the order of derecruitment of these units. Analysis of frequency of firing of units also suggested that the levels of excitatory input to one unit of a pair could be altered relative to the level of input of the other one. The data imply that there are at least minor differences in distribution of excitatory inputs from various sources among motoneurons of this muscle pool.

scholarly journals Automatic Human Sleep Stage Scoring Using Deep Neural Networks

2018 ◽  
Vol 12 ◽  
Author(s):  
Alexander Malafeev ◽  
Dmitry Laptev ◽  
Stefan Bauer ◽  
Ximena Omlin ◽  
Aleksandra Wierzbicka ◽  
...  
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Sleep Stage ◽  
Human Sleep ◽  
Sleep Stage Scoring

scholarly journals Cardiovascular responses to nonrespiratory and respiratory arousals in a porcine model

2001 ◽  
Vol 90 (1) ◽  
pp. 114-120 ◽  
Author(s):  
Sandrine H. Launois ◽  
Nathan Averill ◽  
Joseph H. Abraham ◽  
Debra A. Kirby ◽  
J. Woodrow Weiss
Keyword(s):  
Porcine Model ◽  
Sleep Stage ◽  
Cardiovascular Responses ◽  
Hemodynamic Response ◽  
Rapid Eye Movement Sleep ◽  
Sleep State ◽  
Renal Vasoconstriction ◽  
Airway Occlusion ◽  
Arterial Blood ◽  
Renal Vascular

Spontaneous and provoked nonrespiratory arousals can be accompanied by a patterned hemodynamic response. To investigate whether a patterned response is also elicited by respiratory arousals, we compared nonrespiratory arousals (NRA) to respiratory arousals (RA) induced by airway occlusion during non-rapid eye movement sleep. We monitored mean arterial blood pressure (MAP), heart rate, iliac and renal blood flow, and sleep stage in 7 pigs during natural sleep. Iliac and renal vascular resistance were calculated. Airway occlusions were obtained by manually inflating a chronically implanted tracheal balloon during sleep. The balloon was quickly deflated as soon as electroencephalogram arousal occurred. As previously reported, NRA generally elicited iliac vasodilation, renal vasoconstriction, little change in MAP, and tachycardia. In contrast, RA generally elicited iliac and renal vasoconstriction, an increase in MAP and tachycardia. The frequent occurrence of iliac vasoconstriction and arterial pressure elevation following RA but not NRA suggests that sleep state change alone does not account for the hemodynamic response to airway occlusion during sleep.

Human Sleep EEG Analysis Using the Correlation Dimension

2001 ◽  
Vol 32 (3) ◽  
pp. 112-118 ◽  
Author(s):  
Toshio Kobayashi ◽  
Shigeki Madokoro ◽  
Yuji Wada ◽  
Kiwamu Misaki ◽  
Hiroki Nakagawa
Keyword(s):  
Rem Sleep ◽  
Correlation Dimension ◽  
Degrees Of Freedom ◽  
Slow Wave Sleep ◽  
Sleep Stage ◽  
Sleep Eeg ◽  
Sleep Cycle ◽  
Sleep Stages ◽  
The Mean ◽  
Male Subjects

Sleep electroencephalograms (EEG) were analyzed by non-linear analysis. Polysomnography (PSG) of nine healthy male subjects was analyzed and the correlation dimension (D2) was calculated. The D2 characterizes the dynamics of the sleep EEG, estimates the degrees of freedom, and describes the complexity of the signal. The mean D2 decreased from the awake stage to stages 1,2,3 and 4 and increased during rapid eye movement (REM) sleep. The D2 during each REM sleep stage were high and those during each slow wave sleep stage were low, respectively, for each sleep cycle. The mean D2 of the sleep EEG in the second half of the night was significantly higher than those in the first half of the night. Significant changes were also observed during sleep stage 2, but were not seen during REM sleep and sleep stages 3 and 4. The D2 may be a useful method in the analysis of the entire sleep EEG.

Sign in / Sign up

Export Citation Format

Share Document