Sleep (system call)

About: Sleep (system call) is a research topic. Over the lifetime, 2633 publications have been published within this topic receiving 27806 citations. The topic is also known as: Sleep() & sleep().

Sleep stage determinig method and sleep stage determining device

Abstract: PROBLEM TO BE SOLVED: To measure the sleep stage of a subject in on-invasive state by extraction a palmus signal and a breath signal from output signals of a living body signal detecting means disposed under the body of the subject, and discriminating a non-REM sleep and as REM sleep from at least one variation pattern between a palmus signal waveform and a breath signal waveform. SOLUTION: In a bed 7 where a subject lies, an air mat is disposed in a position to which the body of a tested person is applied, and a micro-differential pressure sensor 13 and an absolute pressure sensor 2 are installed through an air tube 12 connected to one end of the air mat 11 to constitute a living body signal detecting means 1 for detecting a living body signal of the subject. A signal extract means 4 of a sleep stage determination control device 3 is adapted to extract a signal by application of a suitable filter and a data processing means, and a sleep stage determining means 5 determines the sleep stage from a palmus signal and a breath signal extracted by the signal extract means 4. The determination result of the sleep stage is continuously recorded.

Biosensor, pulse wave sensor, sleep information processing method, sleep information processing device, program and recording medium

Abstract: PROBLEM TO BE SOLVED: To provide a biosensor, a sleep information processing device, a program and a recording medium capable of more precisely analyzing a sleep state and performing a more accurate advice. SOLUTION: Whether a drink termination time T is inputted or not is judged at a step 100. The step is advanced to a step 110 if affirmatively judged here. At the step 110, whether the present time t reaches the time which is the sum of the drink termination time T and elapsed hours until high quality sleep is attained or not, namely whether X hours has elapsed after drinking or not is judged. The step is advanced to a step 120 if affirmatively judged here. At the step 120, the time suitable for sleep is judged to have reached since X hours have elapsed after drinking, and this fact is reported to a subject by vibration or the like by driving for instance a vibration part 39 or the like. By this, the subject receiving the report about this can sleep at an appropriate time and can obtain high quality sleep. COPYRIGHT: (C)2007,JPO&INPIT

Data-driven modeling of sleep states from EEG

Abstract: Sleep analysis is critical for the diagnosis, treatment, and understanding of sleep disorders. However, the current standards for sleep analysis are widely considered oversimplified and problematic. The ability to automatically annotate different states during a night of sleep in a manner that is more descriptive than current standards, as well as the ability to train these models on a patient-by-patient basis, would provide a complementary approach for sleep analysis. We present a method that discovers latent structure in sleep EEG recordings, by extracting symbols from the continuous EEG signal and learning “topics” for a recording. These sleep topics are derived in a fully automatic and data-driven manner, and can represent the data with mixtures of states. The proposed method allows for identification of states in a patient-specific way, as opposed to the one-size-fits-all approach of the current standard. We demonstrate on a publicly available dataset of 15 sleep recordings that not only do the states discovered by this approach encompass the standard sleep stage structure, they provide additional information about sleep architecture with the potential to provide new insights into sleep disorders.

An Improved Neural Network Based on SENet for Sleep Stage Classification

Abstract: Sleep staging is an important step in analyzing sleep quality. Traditional manual analysis by psychologists is time-consuming. In this paper, we propose an automatic sleep staging model with an improved attention module and hidden Markov model (HMM). The model is driven by single-channel electroencephalogram (EEG) data. It automatically extracts features through two convolution kernels with different scales. Subsequently, an improved attention module based on Squeeze-and-Excitation Networks (SENet) will perform feature fusion. The neural network will give a preliminary sleep stage based on the learned features. Finally, an HMM will apply sleep transition rules to refine the classification. The proposed method is tested on the sleep-EDFx dataset and achieves excellent performance. The accuracy on the Fpz-Cz channel is 84.6%, and the kappa coefficient is 0.79. For the Pz-Oz channel, the accuracy is 82.3% and kappa is 0.76. The experimental results show that the attention mechanism plays a positive role in feature fusion. And our improved attention module improves the classification performance. In addition, applying sleep transition rules through HMM helps to improve performance, especially N1, which is difficult to identify.

Method for modifying life rhythm

Abstract: PROBLEM TO BE SOLVED: To provide a method for modifying a life rhythm used for returning a once disturbed life rhythm to a normal life rhythm which allows comfortable awakening while a required sleeping time is assured. SOLUTION: Sleep stages are detected using characteristic values of power spectral density signals acquired from heart rate signals or R-R interval values of the heart rate signals. An amount of sleeping is calculated by multiplying each of the lengths of the REM sleep, the light non-REM sleep and the deep non-REM sleep by each weighting factor and by adding the obtained values together. In an alarm control step, a set amount of sleeping is calculated on the basis of preexamined amount of sleeping that allows a subject to awake comfortably, and an alarm signal is put out during the REM sleep period in the late sleep stage. Part or all of the measured data and the control data of a sleeping time calculating step for calculating the amount of sleeping from the sleep stages and of the alarm control step for determining the set amount of sleeping and the time of rising are acquired via a communication means. COPYRIGHT: (C)2005,JPO&NCIPI