97 results about "Sleeping stages" patented technology

A computing device for monitoring a sleep stage of a user in a contactless manner includes a processor, a radar unit, and a memory. The processor executes instructions from memory to cause the computing device to perform a series of signal processing methodologies on the waveforms received from the radar unit to accurately determine the sleep stage of the user in a contactless manner.

The invention discloses a multi-region pressure monitoring and feedback method for a sleep monitoring mattress, which comprises the following steps: step 1, arranging a monitoring feedback system to collect pressure data and biological characteristic signals, step 2, dynamically planning a human body contact region during sleep, step 3, identifying a sleep stage and an abnormal sleep event, and step 4, determining the sleep stage and the abnormal sleep event. 4, dynamic feedback is output based on cooperation of multiple actuators; by means of dynamic area reconstruction and high-density sensor layout, millisecond-level pressure changes of key parts of a human body can be captured, the detection precision is greatly improved, active intervention of user health is achieved through multi-actuator collaborative dynamic adjustment, meanwhile, the method is combined with user body shape parameters, sleep monitoring of the whole crowd can be covered, and the method is suitable for being popularized and applied. The applicability of the mattress is effectively improved.

The invention discloses a sleep staging detection method and system based on a smart watch, and the method comprises the steps: S1, obtaining the heart rate variability, triaxial accelerometer data and body movement intensity index signals of a wearer through a sensor of the smart watch, and carrying out the multi-source signal fusion and time synchronization; s2, carrying out noise reduction processing on the synchronized multi-source signal, and constructing a feature vector; s3, calculating a time sequence self-correlation feature of the feature vector; s4, based on a bidirectional long and short time memory network structure, performing time sequence modeling on the input feature vector and the time sequence self-correlation feature to obtain fused bidirectional feature representation; and S5, performing multi-classification processing on the fused bidirectional feature representation based on a Softmax classifier to realize accurate classification of sleep stages. According to the method, the heart rate variability signal and the three-axis acceleration signal can be fused, and the sleep state of the human body can be accurately recognized and classified in combination with the bidirectional long-short-term memory network and time sequence self-correlation feature analysis.

The present invention relates to a smart mattress that primarily uses non-contact sensors to measure the user's physiological data. Through a non-contact sensing method, it is capable of detecting REM sleep stages, monitoring heart rhythm, and measuring vital information such as respiration, as well as recording and storing physiological data such as bed-leaving movements and sleeping position. By connecting to a mobile device or a computer via a control box, all the recorded information can be displayed as a screen output or uploaded to a cloud database for storage. This enables long-term measurement of the user's physiological data or real-time monitoring, thus contributing to targeted patient care.

The embodiments of this specification disclose a personalized dynamic sleep staging method and system. The method includes determining the user category of a user based on the user's characteristic information. The basic sleep staging algorithm corresponding to the user category of the user in the branch algorithm library is used as the target sleep staging algorithm. Based on the target sleep staging algorithm and the user's current sleep data, sleep staging data suitable for different user groups is generated. In addition, the method also includes obtaining user feedback information, determining the optimal sleep staging algorithm based on the user's feedback information, current sleep data, and historical sleep data; and updating the target sleep staging algorithm to the optimal sleep staging algorithm, so that the target sleep staging algorithm can take into account the user's sleep data while also taking into account the actual sleep state reported by the user to ensure the real-time accuracy of the generated sleep staging data.

A sleep staging method based on semi-supervised learning belongs to the field of artificial intelligence and health monitoring, and comprises the following steps: preprocessing original PPG signals, extracting heart rate and respiration signals, calculating morphological and frequency domain features, extracting sleep staging related representation features, modeling short-time features and long-time changes of sleep, and outputting a classification result of each sleep stage; calculating supervised loss by using the labeled PPG data, predicting unlabeled PPG data to obtain a soft label, screening a high-confidence sample, and converting the soft label into a hard label to calculate unsupervised loss; calculating a confidence coefficient, calculating category center features of each sleep stage category, and performing feature adjustment; performing confidence weighting on the sample features and the category center features; and constructing positive and negative sample pairs to carry out semi-supervised contrast learning. According to the method, the generalization ability of the sleep staging model is enhanced, the sleep staging accuracy is improved, and the method can be applied to scenes such as family health management, auxiliary diagnosis and sleep monitoring.

The invention discloses a patient sleep awakening three-classification monitoring method and device based on a machine learning model, equipment and a medium, and the method comprises the steps: collecting acceleration data and activity counting and heart rate data of a subject, and carrying out the preprocessing of the collected data; extracting data features based on the preprocessed data, wherein the data features comprise a motion feature, a heart rate feature and a clock proxy feature; the extracted data features are input into a classification model, prediction state data of each Epoch are output, each row in the prediction state data comprises an Epoch starting timestamp, a real sleep staging label and a three-classification prediction result of the model, and therefore the prediction state data of each Epoch can be obtained. According to the method, the three-classification prediction accuracy of awakening, non-fast eye movement sleep and fast eye movement sleep can be effectively improved, and the method can be widely applied to sleep monitoring.

The invention discloses a sleep staging method and system based on self-adaptive trigger time characteristics, belongs to the technical field of plateau sleep stage staging, and solves the problem that accidental events in sleep cannot be effectively identified and extracted when multi-mode signal characteristics are extracted by the existing method. The method comprises the following steps: judging whether a physiological monitoring signal is an accidental event associated signal based on a preset accidental event judgment mechanism, calculating an accidental event value in a single group of time windows by adopting the accidental event judgment mechanism, and identifying and extracting the accidental events by a feature extraction model. The sleep stage staging model analyzes and processes the feature fusion result and outputs a sleep stage staging result; according to the method, an accidental event judgment mechanism with a time decay function is introduced, event data are screened, features are extracted from PPG signals and the event data, the features are input into the sleep stage staging model for sleep stage prediction, and meanwhile, the accuracy of feature extraction is improved by combining a dynamically adjusted trigger threshold value.

Method for controlling a ventilation system, ventilation system, and associated ventilation installation. This method for controlling a ventilation system includes a remote control and a ventilation grille, which includes battery-powered receiving means. Cyclically, the ventilation grille switches between a sleep phase (ΔTs), during which the receiving means are off, and a wake-up phase (ΔTr), during which the receiving means are on and ready to receive a control signal sent by the remote control. The control method also includes actuation of the remote control by a user, so as to send a control signal for a transmission time (ΔTt) that is longer than the sleep time (ΔTs). Figure for the abstract: Figure 2

The application relates to the technical field of air conditioners, and discloses a method for controlling an air conditioner, which comprises the following steps: acquiring a current comfort value of an SPMV model associated with a sleep stage of a user; and controlling operation parameters of a fresh air mode associated with the air conditioner according to a matching condition of the comfort value and a preset comfort value. The method can regulate the oxygen content of an environment where the user is located, and improve the comfort of the user in the sleep stage. The application further discloses a device for controlling an air conditioner, an air conditioner and a storage medium.

The invention provides a sleep staging method based on non-contact electrocardiosignals and body movement signals. Firstly, electrocardio and body movement signals are collected on a bed sheet in a non-contact mode through a capacitive coupling type sensor and a pressure sensor, preprocessing such as filtering, oversampling and signal segmentation is carried out, and a data set is formed. Secondly, a CNN-biLSTM-sleep network model is constructed, the model comprises two paths of input of electrocardiosignals and body movement signals, a CNN feature extraction module and a bidirectional LSTM sequence information extraction module, and six sleep stages of REM, N1, N2, N3, WK and LV are output; and then training and optimizing the model by using the training set. And finally, outputting a classification result through a verification set test model. The method does not need extra feature extraction, is suitable for a non-contact electrocardio acquisition scene, and can effectively recognize sleep stages.

The present disclosure relates to the technical field of brain wave signal processing, and more specifically, to a sleep staging method, apparatus, device, and computer-readable storage medium. The sleep staging method includes: determining the power spectral density of the brain wave signal of each sleep frame during sleep; performing dimensionality reduction processing on the power spectral density to obtain a reduced dimensionality data set; determining multiple characteristic signals of the brain wave signal of the sleep frame based on the power spectral density; for each sleep frame, performing kernel density estimation on the reduced dimensionality data set with weights determined according to each characteristic signal to obtain a probability density corresponding to the characteristic signal; and determining that the sleep frame belongs to the sleep stage corresponding to the characteristic signal when the probability density meets the preset condition corresponding to the characteristic signal, wherein different characteristic signals correspond to different sleep stages.

The invention belongs to the cross technical field of biomedical engineering and signal processing, and discloses a fixed-length sleep staging sequence global correction method based on dynamic programming, which comprises the following steps of: defining an original sleep staging sequence which is divided by taking 30 seconds as a fixed time window and comprises a plurality of continuous fixed time windows, the target generates a corrected sequence, the number of fixed time windows of the corrected sequence is kept consistent with that of the original sequence, only the sleep state value corresponding to each fixed time window is corrected, and the fixed time windows are not added or deleted; a sleep state coding rule is set, and the waking state, the first light sleep stage, the second light sleep stage, the deep sleep stage and the rapid eye movement sleep stage correspond to unique digital codes respectively. Through a global cost accumulation mechanism, subsequent illegal transfer caused by local correction is avoided in advance, iteration is not needed, and the correction efficiency is remarkably improved.

The invention relates to the technical field of intelligent control, and discloses an air conditioner regulation and control method and device based on user sleep parameters, and the method comprises the steps that when it is detected that an air conditioner is in a running state and a user is in a sleep state, sleep sign parameters of the user are obtained; analyzing a current sleep cycle parameter of the user according to the sleep sign parameter; the sleep cycle parameters comprise a current sleep cycle and a current sleep stage corresponding to the current sleep cycle; according to the sleep cycle parameter, determining a comfortable sleep demand parameter corresponding to the user; according to the comfortable sleep demand parameters, regulation and control parameters corresponding to the air conditioner are determined; and according to the regulation and control parameters, the air conditioner is controlled to execute air outlet operation corresponding to the regulation and control parameters. Therefore, operation of the air conditioner can be regulated and controlled in real time based on the user sleep parameters, so that regulation and control flexibility of the air conditioner can be improved, and sleep comfort of the user can be improved.

The invention relates to a data processing method, device and system of a sleep staging algorithm based on a BCG signal. According to the method, a BCG signal sent by an optical fiber sensor mattress system and a sleep staging signal sent by PSG equipment are received; generating a data set according to the BCG signals, and performing feature data extraction on the BCG signals in the data set to obtain a feature set; filtering correlation deletion, L1 regularization logistic regression and a random forest algorithm are sequentially used for carrying out feature screening on the feature set, and a feature set after feature screening is obtained; performing feature standardization on the feature set after feature screening to obtain a feature set after feature standardization; dividing the feature set with the standardized features into a training set and a test set according to the proportion, inputting the training set and the test set into the sleep staging model for training to obtain a sleep staging test result, evaluating the sleep staging model in multiple dimensions, and if the evaluation is passed, obtaining a convergent sleep staging model, and the sleep staging method has the advantage of improving the accuracy and reliability of sleep staging.

A method for controlling home appliances and an electronic device performing the method may be provided. In detail, a method for controlling home appliances and an electronic device performing the method may be provided, the method comprising the steps of: obtaining sleep information about a user and driving information about each of a plurality of home appliances present in home; determining, from among the plurality of home appliances, a noise causing device that generates noise outside a deep-sleepable range at the time of change in a sleep stage of the user included in the sleep information; and controlling the operation of the noise causing device so that the noise generated from the noise causing device is generated within the deep-sleepable range.

To provide a smart mattress which can solve conventional technical problems that require contact measurement, instant monitoring, and long-time monitoring, when measuring biological data of a human body.SOLUTION: The present invention provides a smart mattress which is useful for performing a measurement or instant monitoring of long-term biological data of a user to establish an accurate care mode by: measuring biological data of a human body mainly using a non-contact sensor; tracing a rapid-eye-movement phase of a user through a detection method of measuring vital signs remotely; monitoring cardiac beat; sensing biological information such as respiration; detecting and recording biological information on getting up and sleeping posture and the like of the user; pairing and connecting a mobile device and computer via a control box; and then outputting and displaying, or uploading and storing, in a cloud database, all the acquiring information.SELECTED DRAWING: Figure 1

A first bed includes a first mattress, a first pressure sensor, and a first controller in data communication with the first pressure sensor, the first controller configured to receive pressure readings and to transmit the first pressure readings to a remote server. The system further includes a second bed that includes a second mattress having an inflatable chamber. The system further includes a second pressure sensor in fluid communication with the second mattress inflatable chamber to sense pressure applied to the second mattress of the inflatable chamber. The system further includes a second controller in data communication with the second pressure sensor, the controller configured to receive the one or more sleep-state classifiers and to run the received sleep-state classifiers in order to collect one or more sleep-state votes. The second controller is further configured to determine a sleep-state and operate the bed system according to the determined sleep-state.

This invention relates to the field of sleep staging technology, specifically to a method, apparatus, and storage medium for identifying REM (Rapid Eye Movement) sleep stages, aiming to solve the problem that existing sleep staging methods cannot accurately identify REM stages. To this end, the method of this invention includes: dividing the acquired user heart rate data of the sleep stage to be tested into multiple segmented intervals; obtaining sleep heart rate data for each segmented interval based on the currently stored average baseline value; identifying the proportion of REM stages in each segmented interval based on the obtained sleep heart rate data; and thus obtaining the REM stage in the entire sleep stage to be tested. The initial value of the average baseline value is obtained by combining medical-grade sleep feature data. The solution provided by this invention can effectively improve the accuracy of REM stage identification in sleep staging.

Techniques for improved respiratory therapy are provided. Glucose data of a user collected during a sleep session is accessed. Based at least in part on the glucose data, a plurality of transitions between sleep stages experienced by the user during the sleep session is determined. A sleep quality measure for the sleep session is generated based at least in part on the plurality of transitions. An apnea risk score for the user is generated based at least in part on the sleep quality measure, and one or more medical interventions for the user are provided based on the apnea risk score.

The invention discloses an end-to-end sleep monitoring and event detection method based on a wrist accelerometer, and the method comprises the following steps: collecting original motion data through the wrist accelerometer, extracting a basic feature vector, generating a sleep rhythm prior feature based on the basic feature vector by using historical activity data of a user, and carrying out the end-to-end sleep monitoring and event detection. Splicing the prior feature and the basic feature vector to form an enhanced feature vector; converting the enhanced feature vector into a two-dimensional feature map, and outputting the sleep state probability of each time point by using a time sequence-variable interaction model; performing multi-scale Gaussian smoothing processing on the original binary event tag to generate a soft tag, and training a time sequence-variable interaction model by taking the soft tag as a supervision signal; performing forward propagation on new accelerometer data based on the trained model, outputting a probability sequence, and detecting sleep events and performing sleep staging through post-processing operation; according to the invention, high-precision sleep staging and sleep event detection are realized by only using accelerometer data.

The invention provides an oxygen generation air conditioning device control method and an oxygen generation air conditioning device. The oxygen generation air conditioning device comprises an oxygen generation module, and the control method of the oxygen generation air conditioning device comprises the steps that S1, the number i of times when a user enters a sleep cycle is obtained, and each sleep cycle comprises a plurality of different sleep stages; s2, in each sleep stage, acquiring indoor oxygen concentration Y, and controlling at least one of the on-off state, the oxygen generation amount and the oxygen generation duration of an oxygen generation module according to the relationship between the indoor oxygen concentration Y and the first preset oxygen concentration Ypre1; wherein the multiple different sleep stages comprise a light sleep stage, a moderate sleep stage, a deep sleep stage and a rapid eye movement stage which are sequentially ranked according to a time sequence. The problem that in the prior art, an oxygen generation air conditioning device cannot be accurately matched with oxygen demand changes of the human body in different sleep stages in the oxygen generation process is effectively solved.

The invention discloses a sleep staging result determination method, device and equipment, a medium and a product, and the method comprises the steps: obtaining a BCG signal of a detection target, the BCG signal being obtained through the detection of a sensor arranged below the detection target; performing data preprocessing on the BCG signal, and determining a comprehensive input feature; inputting the comprehensive input features into a pre-trained staging model to obtain a prediction result; and correcting the prediction result based on a smoothing rule, a stage transition probability rule and a sleep cycle rule to obtain a final sleep staging result. According to a BCG signal obtained through non-contact measurement, multiple features are extracted and input into a pre-training staging model, different stages of a model output result are corrected, and a final sleep staging result is obtained. Non-contact, non-interference and non-intrusive sleep staging continuous monitoring is realized, so that a user can conveniently obtain a sleep staging result of the user and know the overall sleep condition of the user, and the sleep quality and health are improved.

The application relates to the technical field of model correction, and discloses a method for correcting a thermal comfort model, which comprises the following steps: obtaining environmental perception information of user feedback; determining a third correction amount for correcting an SPMV model according to the environmental perception information; and correcting the SPMV model according to the third correction amount for correcting the SPMV model. According to the scheme, the third correction amount for correcting the SPMV model is determined, and the SPMV model is corrected in combination with the third correction amount, so that a thermal comfort model with higher precision can be obtained in combination with actual environmental requirements of a user, the corrected thermal comfort model is more in line with actual change rules of the thermal comfort of the user, and therefore the accuracy of thermal comfort judgment in a sleep stage of the user is improved, and the demand of the user for the thermal comfort is met. The application further discloses a device for correcting a thermal comfort model and a storage medium.

The present application relates to the field of intelligent health monitoring and digital technology of traditional Chinese medicine, and particularly relates to a traditional Chinese medicine sleep health monitoring system based on millimeter wave radar. The system comprises: a data acquisition module for acquiring original vital sign signals through millimeter wave radar; a data processing module for extracting a sleep physiological parameter set; a sleep staging identification module for identifying sleep staging results corresponding to wakefulness, light sleep, deep sleep and rapid eye movement; a traditional Chinese medicine sleep evaluation module for converting sleep parameters into traditional Chinese medicine quantitative indicators through a quantitative mapping unit, generating traditional Chinese medicine syndrome differentiation labels through a space-time correlation unit, and outputting traditional Chinese medicine health monitoring results after fusion analysis by an analysis and decision unit; and a monitoring result output module for generating a visual health report. The present application realizes the deep integration of non-invasive, continuous sleep monitoring and objective, quantitative traditional Chinese medicine syndrome differentiation, and provides a systematic solution for sleep health management.

This invention discloses a sleep staging system based on multi-threshold neighborhood extreme value pattern statistics, comprising an EEG signal acquisition unit, a signal preprocessor, a multi-threshold neighborhood extreme value time-domain feature extractor, a gray wolf optimizer, and a random forest classifier. The preprocessing involves initial filtering and 30-second segmentation of selected EEG signals. Based on the duration of the single-channel EEG signal annotation, the single-channel EEG signals are divided into two categories: original signal segments and signal segments requiring data augmentation. Next, data augmentation is performed on specified segments, and the extreme values ​​of the augmented data segments are selected. Then, the neighborhood differences of the extreme values ​​are calculated, and multi-threshold and multi-state processing is performed on the 5-stage matrix obtained from these differences to derive the multi-threshold neighborhood extreme value pattern statistical code. The thresholds in the multi-threshold processing are determined by the gray wolf optimizer. Finally, the obtained feature matrix is ​​input into the random forest classifier. This invention enhances the automatic sleep staging capability based on EEG signal augmentation and designs and manufactures a complete system encompassing EEG acquisition and sleep analysis visualization.

The application relates to the technical field of intelligent household appliances, and discloses a method for controlling an air conditioner, which comprises the following steps: acquiring a current sleep state of a user associated with the air conditioner in a sleep stage; obtaining a current comfort value of an SPMV model associated with the user; and in the case that the current comfort value does not match a preset comfort value, executing an environment control strategy corresponding to the current sleep state according to the current sleep state, so that an adjusted current comfort value matches the preset comfort value. The method can improve the accuracy of comfort degree judgment in the sleep stage of the user and meet the demand of the user for thermal comfort degree. The application also discloses a device for controlling the air conditioner, the air conditioner and a storage medium.