122 results about "Sleep staging" 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 relates to the technical field of electroencephalography, in particular to a sleep staging automatic identification method and system based on multi-mode electroencephalography, and the method comprises the following steps: extracting a waveform period to construct dominant distribution, correcting label boundary positioning mutation response, unifying a time axis to form an alignment structure, clustering mutation fragments to establish an alternating relation, and identifying the sleep staging based on multi-mode electroencephalography. And identifying a main channel range to construct an automatic identification scheme. According to the method, a reference channel is positioned through area distribution difference, a boundary change section is judged in combination with a frequency band energy change trend, a channel region with dense and stable mutation points is extracted as an anchor point, time axis unified adjustment is completed according to main response starting and ending time, and an alternating fragment graph is further constructed through a cross-channel time coverage relation of the mutation points. The sequential structure coordination ability and mutation form aggregation expression efficiency among multi-source signals are improved, and accurate recognition of boundary drift and asynchronous response and dynamic extraction of steady-state rhythm in sleep stage division are achieved.

The invention provides an electroencephalogram signal processing method and device based on a non-invasive brain-computer interface, and belongs to the technical field of medical equipment. According to the change risk of the amplitude data of the electrode of the analysis processing target, the similarity degree of other analysis processing targets and the signal stabilization electrode, the identification processing scheme of the electroencephalogram staging model of the analysis processing target is determined, and based on the deviation data of the electroencephalogram staging result between different identification processing schemes, the electroencephalogram staging model of the analysis processing target is obtained. Determining the interference risk type of the analysis processing target and the position of the interference electrode, and determining the electroencephalogram signal processing method of the position of the interference electrode according to the similarity degree of the identification processing scheme with the identification deviation of the position of the interference electrode in each analysis processing target and the interference risk type of the analysis processing target. And the accuracy of the sleep staging result is improved.

The invention discloses a sleep staging method and a storage medium, and belongs to the technical field of sleep staging, and the method comprises the following steps: inputting heart rate data into a pre-constructed sleep staging model according to a time sequence, and sequentially outputting sleep staging results; the sleep staging model comprises a KGNN module, a Sleep MLSTM module, a Sleep SLSTM module and an output module; the KGNN module calculates a context vector according to the heart rate data; the SleepMLSTM module calculates the hidden state of the last time step according to the heart rate data, and adds the hidden state with the context vector to serve as the final output feature of the SleepMLSTM module; the SleepSLSTM module takes the final output feature as an input to generate an output feature; and splicing the final output features of the SleepMLSTM module and the output features of the SleepSLSTM module, and inputting the spliced features into an output module to generate a sleep staging result. The method can solve the problems that an existing sleep staging method is difficult to capture complex physiological correlation between heart rate variability characteristics and is difficult to resist the influence of time-varying noise of original heart rate signals.

The invention provides a sleep regulation and control method and device based on a non-invasive brain-computer interface, and belongs to the technical field of sleep regulation and control. The method specifically comprises the steps that the coincidence condition of a reliable user and a user with the environment temperature changing is determined and recognized, and verification data of a sleep stage recognition model for recognizing the reliable user are combined; determining an update processing strategy of the sleep staging identification model, performing update processing on the sleep staging identification model according to the update processing strategy of the sleep staging identification model, and determining the sleep staging identification model according to an update processing result of the sleep staging identification model and historical regulation and control data of the sleep environment temperature in the user with the environment temperature changing. According to the regulation and control method for determining the sleep environment temperature of the user with the environment temperature changing, determination of differentiated temperature regulation strategies of the sleep environment temperature under different staging results is achieved, and then the user experience is improved.

The invention discloses a sleep staging method based on a piezoelectric sensing signal and related equipment, and the method comprises the steps: obtaining the piezoelectric sensing signal of a target object in a sleep period, and segmenting the piezoelectric sensing signal in the sleep period into a plurality of piezoelectric sensing signals according to a preset time length; performing signal amplitude alignment processing on the piezoelectric sensing signal of each segment to obtain an amplitude alignment signal of each segment; performing continuous wavelet transform on the amplitude alignment signal of each segment to generate a time-frequency graph corresponding to each segment; fusing the time-frequency graph of each segment with the time-frequency graph of the adjacent segment to obtain a context time-frequency graph; inputting the context time-frequency graph into a preset sleep staging model to obtain an initial sleep staging result of each segment; and correcting the initial sleep staging result of each segment to obtain a final sleep staging result of each segment. The method can effectively improve the accuracy of sleep staging, and can be widely applied to the technical field of sleep monitoring.

The invention discloses a portable electroencephalogram sleep detection and analysis system and method. The portable electroencephalogram sleep detection and analysis system comprises an in-ear electroencephalogram acquisition unit which is used for acquiring differential EEG signals in ear canals and converting the signals into digital data streams for transmission; the data processing and calculating unit is used for carrying out preprocessing operation on the digital data flow transmitted by the in-ear electroencephalogram acquisition unit; and the sleep staging unit is used for inputting the preprocessed data into an event-driven time sequence classification model, and the model reads a signal sequence in a sliding window mode, completes judgment and classification of sleep stages and generates a corresponding sleep quality evaluation report. According to the invention, the calculation amount is reduced by using the snn with low power consumption, so that the staging system is integrated into the embedded platform, meanwhile, the problem of poor staging effect of wearable sleep monitoring equipment is solved, and the intelligent sleep staging system is high in portability, simple and convenient to use, high in integration and relatively low in cost.

The application discloses a single-channel electroencephalogram sleep staging method based on deep learning, and comprises the following steps: 1, constructing a training set from a polysomnogram and a sleep label; 2, building an electroencephalogram sleep staging network based on deep learning; 3, constructing an MFE loss function; 4, training a deep learning model; and 5, performing sleep staging on original single-channel electroencephalogram signals by using a single-channel sleep staging network which has been trained, so that automatic sleep staging of the electroencephalogram signals can be realized.

The present application relates to a kind of automatic sleep staging method, its steps include: the EEG original data is processed to obtain EEG feature map, while the EOG original data is processed to obtain EOG feature map;EEG feature map and EOG feature map are multiplied and fused, and highlight feature map is obtained;Highlight feature map is directly added with EEG feature map and EOG feature map and fused to obtain initial fusion feature map;Initial fusion feature map is processed to obtain the most weight feature map by weight adjustment;Initial fusion feature map and the most weight feature map are multiplied and fused to obtain the final fusion feature map with weight information;According to the weight information of final fusion feature map, each sleep stage prediction probability is output.The automatic sleep staging method described in the present application is further trained and optimized, does not need too much artificial intervention, and can be simply and effectively applied in sleep staging of healthy individuals and patients with consciousness disorders.

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 discloses a sleep monitoring and intelligent early warning system and method based on a multi-modal time sequence signal, and the system comprises a multi-modal sensor module which is used for collecting an original heterogeneous time sequence signal of a subject in a sleep period; the time sequence data preprocessing module is used for performing timestamp alignment, band-pass filtering noise reduction, baseline drift correction and sliding window segmentation on the original heterogeneous time sequence signals and extracting multi-modal feature vectors; the sleep feature recognition module is used for receiving the multi-modal feature vector, performing deep feature learning and outputting sleep staging probability distribution and a sleep apnea event detection mark; the large language model module is used for performing joint coding on an output result, a historical sleep file of the subject and a clinical diagnosis text to generate a structured sleep quality assessment report and health risk association analysis; and the multi-level intelligent early warning and decision support module is used for triggering early warning signals of different levels and generating personalized sleep intervention suggestions.

The embodiment of the invention provides an IMU and EOG-based intelligent sleep monitoring method and wearable equipment, and relates to the technical field of computers. The method comprises the following steps: acquiring sleep data of a monitored object in a sleep process; extracting a first feature in the current time window from the target EOG data, and extracting a second feature in the current time window from the target IMU data; according to the exercise intensity index, determining a first weight value corresponding to the target EOG data and a second weight value corresponding to the target IMU data in the current time window; and weighting the first feature by using the first weight value, weighting the second feature by using the second weight value, and determining a sleep staging result and a target apnea event probability of the monitored object in the current time window according to the weighted first feature and the weighted second feature. In this way, deep weighted fusion is carried out on the EOG data and the IMU data, and the accuracy of sleep staging and apnea monitoring is improved.

The invention provides a mobile terminal sleep staging method based on lightweight deep learning and mixed time sequence correction, and the method comprises the steps: constructing and training a lightweight feature extraction network based on double-flow separable convolution at a server side, converting a trained model into a special format for a mobile terminal, extracting parameters of the hidden Markov model to generate a configuration file; the method comprises the following steps: receiving a single-channel electroencephalogram signal data stream in real time at a mobile terminal, constructing a data buffer area in a memory for caching, and generating an input tensor when data accumulation reaches a preset duration; loading a lightweight feature extraction network at a mobile terminal, performing forward reasoning on an input tensor, and outputting an initial probability vector of each sleep stage; sequentially carrying out Savitzky-Golay filter smoothing processing and Viterbi decoding based on a hidden Markov model on the initial probability vector to obtain a global optimal sleep state sequence; and generating a local sleep time phase diagram and sleep indexes according to the global optimal sleep state sequence, and locally storing and displaying the local sleep time phase diagram and the sleep indexes at the mobile terminal without uploading to the cloud.

The application provides a non-contact sleep staging method and device based on ultrasonic sensing and presence state recognition, a terminal and a medium. The method comprises: obtaining echo signals by using an ultrasonic transceiving mode for sleep monitoring and demodulating the echo signals to obtain an IQ signal sequence; detecting the presence state of the IQ signal sequence to obtain a stable in-bed time interval; obtaining corresponding stable in-bed interval respiratory waveform data based on the IQ signal sequence according to the stable in-bed time interval; inputting the stable in-bed interval respiratory waveform data into a sleep staging model obtained by stage-by-stage training to obtain corresponding sleep staging results. The application introduces a presence state detection mechanism before sleep staging, effectively avoids the problem that off-bed or environmental static fragments are misjudged as sleep states, and improves the accuracy of subsequent sleep staging. At the same time, through stage-by-stage model training, the model can still obtain stable sleep staging performance under small sample conditions.

The invention provides a sleep quality evaluation method and device based on intelligent ring multi-mode sensing, the method is applied to an intelligent ring, and the method comprises the following steps: collecting multi-mode sleep data of a user in a sleep cycle; determining a multi-dimensional sleep score according to the multi-modal sleep data based on a preset sleep model; and determining a comprehensive sleep score according to the multi-dimensional sleep score. According to the method, the anti-interference performance and medical credibility of the sleep staging and scoring result are fundamentally improved, and the evaluation misaccuracy caused by misjudgment of a single signal is avoided, so that the evaluation depth and reliability close to professional medical analysis are realized on consumer equipment, and unprecedented accurate health insight is provided for users.

The invention discloses a few-sample sleep staging method and system based on dynamic weight, and the method comprises the steps: collecting original polysomnogram data, extracting an electroencephalogram signal channel, and carrying out the standardization processing; constructing a one-dimensional convolutional neural network as a feature extractor, and performing supervised learning pre-training; dividing a data set, and constructing a meta-learning task; inputting all samples in the support set and the query set into a pre-training feature extractor, and outputting corresponding support set sample feature vectors and query set sample feature vectors; calculating a feature prototype vector of each sleep stage, and calculating a dynamic weight of each stage; calculating the similarity between the feature vector of the query sample and the prototype vector of each stage, combining the similarity with the corresponding dynamic weight to obtain a weighted similarity score, and selecting the sleep stage with the highest score as a classification result; according to the method, the problems of poor model generalization and class imbalance are solved, and the technical performance is remarkably improved.

The application discloses a sleep staging basic model, a training method of the sleep staging basic model, and the model comprises: a feature projection module, which is used for acquiring electroencephalogram signals of multiple electrode channels, and performing featureization on a time sequence segment of each electrode channel to obtain time domain features and frequency domain features; a cross attention module, which is used for calculating first cross features and second cross features of the time domain features and the frequency domain features, and integrating to obtain double-domain fusion features; a topology embedding module, which is used for superimposing spatial topology embedding on the double-domain fusion features corresponding to each electrode channel to obtain target fusion features, and the spatial topology embedding is used for representing the collection positions of the electrode channels; a deep semantic representation learning module, which is used for performing sparse multi-expert representation learning on the target fusion features to generate high-level semantic representations; and an output layer, which is used for performing decoding processing based on the high-level semantic representations to obtain sleep staging results. The sleep staging accuracy of the sleep staging basic model can be effectively improved.

The invention discloses a sleep health management method based on multi-modal physiological data, which comprises the following steps of: acquiring a multi-modal physiological signal of a user, extracting characteristic parameters of the multi-modal physiological signal to obtain multi-modal physiological characteristic parameters of the user, the multi-modal physiological signal comprises resting heart rate, heartbeat interval, exercise load, pressure level, sleep liability, sleep storage and personal information of the user; preprocessing the multi-modal physiological feature parameters of the user to obtain a physiological signal feature set of the user; a first neural network model is adopted to calculate the user physiological signal feature set, and a user sleep staging result is obtained; performing primary feature fusion on the user sleep staging result and the user physiological signal feature set, and inputting into a first training set to obtain a user sleep score; and performing secondary feature fusion on the user sleep score, the user sleep staging result and the user physiological signal feature set, and inputting into a random forest model to obtain a user sleep guidance suggestion.

This invention relates to the fields of biomedical signal processing, intelligent sleep monitoring, and multimodal machine learning, specifically to a method and system for sleep staging with missing modalities based on latent space distribution alignment. The method includes: acquiring complete EEG, EOG, and EMG data and preprocessing them; encoding single-modal features respectively; mapping each single-modal feature to a unified latent space to generate Gaussian latent distributions for each single modality; constructing a joint latent distribution based on the complete trimodal information; aligning the distributions by minimizing the KL divergence between each single-modal latent distribution and the joint latent distribution to establish a shared latent space; training a classifier based on the joint latent distribution; and, during the testing phase when modalities are missing, using only the latent distributions generated from the observable modalities for classification. This invention maintains high robustness and high accuracy in sleep staging even under modality-missing conditions, making it suitable for applications prone to modality loss, such as clinical monitoring, home sleep detection, and wearable devices.

The invention belongs to the technical field of human body electroencephalogram signal processing and brain regulation and control. The invention provides an ultrasonic-electrical stimulation collaborative lymphatic system enhanced closed-loop regulation and control system, which integrates noradrenaline oscillation core driving signals to realize sleep staging and conversion detection, decides an ultrasonic-electrical stimulation collaborative mode based on a staging coupling index, completes parameter linear transition in a conversion period, and improves sleep quality. Stimulation parameters are dynamically optimized in combination with reinforcement learning and a PID fusion algorithm. According to the device, the defects of core signal deficiency, inaccurate stimulation coordination, one-sided coupling analysis and poor safety adaptability of an existing device are overcome, the lymphatic system metabolic waste removal efficiency is remarkably improved, the sleep interruption risk is reduced, regulation and control are accurate, safety and noninvasive are achieved, the device is suitable for prevention and adjuvant therapy of neurodegenerative diseases such as Alzheimer's disease, and the device has a wide application prospect. And the method can also be expanded to be used for lymphatic-like function mechanism research and early disease screening.

This invention relates to the field of biosensor technology, specifically to a sleep staging method and system based on the fusion of label calibration and inference calibration. The method includes the following steps: constructing a sleep stage transition matrix M driven by both data statistics and domain knowledge; performing a light calibration on the original sleep staging labels of the training set based on the transition matrix M to obtain calibration labels; extracting the time-frequency features of the electroencephalogram (EEG) signal, and training an LSTM model using the calibration labels to obtain a base model; and using the LSTM model to perform preliminary staging on a fixed-length EEG signal sequence to obtain an initial staging sequence. This invention employs a fusion scheme of a dual-driven transition matrix, light label calibration, dynamic programming global calibration, and iterative feedback.

The invention provides a sleep electroencephalogram staging method, device and equipment and a storage medium, and relates to sleep electroencephalogram signal processing. The method comprises the following steps: preprocessing an original signal; inputting the data into a multi-scale feature extraction module, and extracting delta wave, alpha wave and theta wave features in parallel by using wide and narrow kernel convolution branches; re-calibrating a channel weight through adaptive residual channel attention; the features are input into a parallel time sequence attention network, in the first path, bidirectional LSTM is combined with time attention to extract time sequence dependence in epochs, and in the second path, hierarchical attention is adopted to capture context information between epochs with different granularities; fusing the two paths of features through double-path sparse cross attention, and modeling a time step dynamic difference through differential attention to obtain a time sequence representation; and finally, a sleep staging result is output through the classification head. According to the method, through multi-scale feature extraction and multi-level time sequence attention modeling, sleep electroencephalogram dynamic characteristics are comprehensively captured, and accurate feature representation is provided.

The application discloses a lightweight single-channel electroencephalogram sleep staging method and system based on multi-level fusion, and relates to the technical field of biomedical signal processing and artificial intelligence. The method comprises the following steps: a time window sequence centered on a target period is constructed and input into a sleep staging prediction model to predict and output a sleep stage; the model is trained according to the following method: low-frequency features, medium-frequency features and high-frequency features are extracted, and then fused and abstracted to obtain a spatial feature vector; the spatial feature vector is subjected to time series modeling to obtain a time series feature vector; the spatial feature vector and the time series feature vector are fused to obtain a time-space complementary fusion feature; and the sleep stage of the target period is predicted and output. The method has the characteristics of lightweight high performance, high N1 stage recognition capability, cross-scale collaborative fusion, time-space complementary fusion and compliance with physiological rules.

Provided are a method and a system for training a sleep stage classification model of a self-supervised learning infrastructure using a small number of labels. A sleep stage classification method executed by a computer system according to an embodiment includes inputting sleep test data into a sleep stage classification model of a self-supervised learning infrastructure, and classifying a sleep stage from the sleep test data using the sleep stage classification model of the self-supervised learning infrastructure. The sleep classification model of the self-supervised learning infrastructure may be one in which a pattern for sleep stage classification is learned from new sleep data by transfer learning by finely adjusting a weight value based on a representation learning model in which a representation is learned using sleep signal data.

The application discloses a sleep staging method and system, and the method comprises the following steps: acquiring a physiological characteristic original signal of a target object; performing signal state detection on the physiological characteristic original signal; if the target object is out of bed or the signal is invalid, performing data cleaning on the sleep staging data of the day to obtain a final sleep staging result; if the target object is in bed and the signal is valid, performing a preprocessing operation on the physiological characteristic original signal to separate at least two physiological parameter signals related to sleep states; performing multi-dimensional feature extraction on the physiological parameter signals to construct a target physiological characteristic array; and obtaining a sleep staging result corresponding to a current time based on the target physiological characteristic array, a target object information array and a sleep state information array through a preset sleep staging model. The application can rely on non-invasive devices such as intelligent mattresses and intelligent pillows in the intelligent home scene to realize non-invasive home monitoring, and effectively improve the signal anti-interference capability and sleep staging accuracy.

The invention relates to the technical field of biological signal processing and intelligent health equipment, in particular to a dream monitoring and visualization method and system based on multi-modal physiological signal fusion. The intelligent monitoring terminal is integrated in the portable sleep eyeshade and comprises a flexible dry electrode array (used for EEG acquisition), an integrated photoelectric sensor (used for PPG signal acquisition), a miniature millimeter wave radar chip (used for non-contact EOG acquisition), a signal processing module, a wireless transmission module, a semiconductor temperature control module and a double-beat audio module; and the user terminal APP is used for receiving, storing and displaying sleep data (a sleep staging chart and REM period information), a dream intensity index (DII) and a dream cloud chart, and generating a sleep health report and trend analysis. The method has the advantages that high-precision recognition is achieved, the problems that a single sensor is prone to interference and high in misjudgment rate are solved through EEG, EOG and PPG three-mode signal fusion judgment, and the REM period recognition accuracy is improved by 40% or above compared with single EEG monitoring.

The invention discloses an interpretable sleep staging method based on training after visual language model supervision fine tuning, which comprises the following steps: acquiring multi-channel sleep data and a corresponding sleep reasoning text to construct a data set; performing numbering based on interpretation rules related to sleep in clinical rule knowledge to construct a corresponding rule base; taking a pre-trained visual language model as a basic model, and performing supervision fine tuning training on the basic model through the data set to obtain a visual language model; multi-channel sleep data to be analyzed and preset cue words are input into the visual language model to generate a structured JSON result, and the JSON result comprises a sleep stage label, a judgment reason text and a rule number list of related interpretation rules. The invention further provides a device capable of explaining sleep staging. According to the method provided by the invention, the thinking process of experts can be simulated, so that comprehensive data support conforming to clinical rules is provided for each sleep staging result.

The embodiment of the invention provides a sleep electroencephalogram signal detection method based on a CLIP model. The sleep electroencephalogram signal detection method comprises the steps that electroencephalogram signals are collected and subjected to time-frequency conversion to obtain a frequency domain graph; taking the maximum value of the feature vectors of each preset sleep stage as a clustering center, and performing clustering according to Euclidean distances between other feature vectors and the clustering center to obtain corresponding clusters; calculating a characteristic value of each cluster, and splicing the characteristic values according to a time sequence to form a characteristic curve of the electroencephalogram signals; weighting the characteristic curve according to the collection channel to obtain a channel characteristic curve; and inputting the weighted channel characteristic curve into a CLIP model, and finally outputting a sleep staging detection result through comparative learning or similarity matching. According to the method, the advanced signal processing technology and the powerful cross-modal learning ability of the CLIP model are integrated, and intelligent, high-precision and high-generalization automatic staging detection of the sleep quality is achieved. The embodiment of the invention further provides a sleep electroencephalogram signal detection system based on the CLIP model.